fix: export fallback availability from traced module

Remove applyLayout(select-layout main-vertical) call after spawn which
was destroying grid arrangements by forcing vertical stacking. Now only
enforceMainPaneWidth is called, preserving the grid created by manual
split directions. Also fix enforceMainPaneWidth to use config's
main_pane_size percentage instead of hardcoded 50%.

.github/workflows/ci.yml

@@ -52,12 +52,32 @@ jobs:
           bun test src/hooks/atlas
           bun test src/hooks/compaction-context-injector
           bun test src/features/tmux-subagent
+          bun test src/cli/doctor/formatter.test.ts
+          bun test src/cli/doctor/format-default.test.ts
+          bun test src/tools/call-omo-agent/sync-executor.test.ts
+          bun test src/tools/call-omo-agent/session-creator.test.ts
+          bun test src/tools/session-manager
+          bun test src/features/opencode-skill-loader/loader.test.ts
 
       - name: Run remaining tests
         run: |
-          # Run all other tests (mock-heavy ones are re-run but that's acceptable)
-          bun test bin script src/cli src/config src/mcp src/index.test.ts \
-            src/agents src/tools src/shared \
+          # Enumerate subdirectories/files explicitly to EXCLUDE mock-heavy files
+          # that were already run in isolation above.
+          # Excluded from src/cli: doctor/formatter.test.ts, doctor/format-default.test.ts
+          # Excluded from src/tools: call-omo-agent/sync-executor.test.ts, call-omo-agent/session-creator.test.ts, session-manager (all)
+          bun test bin script src/config src/mcp src/index.test.ts \
+            src/agents src/shared \
+            src/cli/run src/cli/config-manager src/cli/mcp-oauth \
+            src/cli/index.test.ts src/cli/install.test.ts src/cli/model-fallback.test.ts \
+            src/cli/config-manager.test.ts \
+            src/cli/doctor/runner.test.ts src/cli/doctor/checks \
+            src/tools/ast-grep src/tools/background-task src/tools/delegate-task \
+            src/tools/glob src/tools/grep src/tools/interactive-bash \
+            src/tools/look-at src/tools/lsp \
+            src/tools/skill src/tools/skill-mcp src/tools/slashcommand src/tools/task \
+            src/tools/call-omo-agent/background-agent-executor.test.ts \
+            src/tools/call-omo-agent/background-executor.test.ts \
+            src/tools/call-omo-agent/subagent-session-creator.test.ts \
             src/hooks/anthropic-context-window-limit-recovery \
             src/hooks/claude-code-compatibility \
             src/hooks/context-injection \
@@ -70,7 +90,11 @@ jobs:
             src/features/builtin-skills \
             src/features/claude-code-session-state \
             src/features/hook-message-injector \
-            src/features/opencode-skill-loader \
+            src/features/opencode-skill-loader/config-source-discovery.test.ts \
+            src/features/opencode-skill-loader/merger.test.ts \
+            src/features/opencode-skill-loader/skill-content.test.ts \
+            src/features/opencode-skill-loader/blocking.test.ts \
+            src/features/opencode-skill-loader/async-loader.test.ts \
             src/features/skill-mcp-manager
 
   typecheck:

.github/workflows/cla.yml

@@ -25,7 +25,7 @@ jobs:
           path-to-signatures: 'signatures/cla.json'
           path-to-document: 'https://github.com/code-yeongyu/oh-my-opencode/blob/master/CLA.md'
           branch: 'dev'
-          allowlist: code-yeongyu,bot*,dependabot*,github-actions*,*[bot],sisyphus-dev-ai
+          allowlist: code-yeongyu,bot*,dependabot*,github-actions*,*[bot],sisyphus-dev-ai,web-flow
           custom-notsigned-prcomment: |
             Thank you for your contribution! Before we can merge this PR, we need you to sign our [Contributor License Agreement (CLA)](https://github.com/code-yeongyu/oh-my-opencode/blob/master/CLA.md).
             

.github/workflows/publish.yml

@@ -51,13 +51,33 @@ jobs:
           # Run them in separate processes to prevent cross-file contamination
           bun test src/plugin-handlers
           bun test src/hooks/atlas
+          bun test src/hooks/compaction-context-injector
           bun test src/features/tmux-subagent
+          bun test src/cli/doctor/formatter.test.ts
+          bun test src/cli/doctor/format-default.test.ts
+          bun test src/tools/call-omo-agent/sync-executor.test.ts
+          bun test src/tools/call-omo-agent/session-creator.test.ts
+          bun test src/features/opencode-skill-loader/loader.test.ts
 
       - name: Run remaining tests
         run: |
-          # Run all other tests (mock-heavy ones are re-run but that's acceptable)
-          bun test bin script src/cli src/config src/mcp src/index.test.ts \
-            src/agents src/tools src/shared \
+          # Enumerate subdirectories/files explicitly to EXCLUDE mock-heavy files
+          # that were already run in isolation above.
+          # Excluded from src/cli: doctor/formatter.test.ts, doctor/format-default.test.ts
+          # Excluded from src/tools: call-omo-agent/sync-executor.test.ts, call-omo-agent/session-creator.test.ts
+          bun test bin script src/config src/mcp src/index.test.ts \
+            src/agents src/shared \
+            src/cli/run src/cli/config-manager src/cli/mcp-oauth \
+            src/cli/index.test.ts src/cli/install.test.ts src/cli/model-fallback.test.ts \
+            src/cli/config-manager.test.ts \
+            src/cli/doctor/runner.test.ts src/cli/doctor/checks \
+            src/tools/ast-grep src/tools/background-task src/tools/delegate-task \
+            src/tools/glob src/tools/grep src/tools/interactive-bash \
+            src/tools/look-at src/tools/lsp src/tools/session-manager \
+            src/tools/skill src/tools/skill-mcp src/tools/slashcommand src/tools/task \
+            src/tools/call-omo-agent/background-agent-executor.test.ts \
+            src/tools/call-omo-agent/background-executor.test.ts \
+            src/tools/call-omo-agent/subagent-session-creator.test.ts \
             src/hooks/anthropic-context-window-limit-recovery \
             src/hooks/claude-code-compatibility \
             src/hooks/context-injection \
@@ -70,7 +90,11 @@ jobs:
             src/features/builtin-skills \
             src/features/claude-code-session-state \
             src/features/hook-message-injector \
-            src/features/opencode-skill-loader \
+            src/features/opencode-skill-loader/config-source-discovery.test.ts \
+            src/features/opencode-skill-loader/merger.test.ts \
+            src/features/opencode-skill-loader/skill-content.test.ts \
+            src/features/opencode-skill-loader/blocking.test.ts \
+            src/features/opencode-skill-loader/async-loader.test.ts \
             src/features/skill-mcp-manager
 
   typecheck:
@@ -223,110 +247,23 @@ jobs:
         with:
           fetch-depth: 0
 
+      - run: git fetch --force --tags
+
+      - uses: oven-sh/setup-bun@v2
+        with:
+          bun-version: latest
+
+      - name: Install dependencies
+        run: bun install
+        env:
+          BUN_INSTALL_ALLOW_SCRIPTS: "@ast-grep/napi"
+
       - name: Generate changelog
-        id: changelog
         run: |
-          VERSION="${{ needs.publish-main.outputs.version }}"
-          
-          PREV_TAG=""
-          if [[ "$VERSION" == *"-beta."* ]]; then
-            BASE="${VERSION%-beta.*}"
-            NUM="${VERSION##*-beta.}"
-            PREV_NUM=$((NUM - 1))
-            if [ $PREV_NUM -ge 1 ]; then
-              PREV_TAG="${BASE}-beta.${PREV_NUM}"
-              git rev-parse "v${PREV_TAG}" >/dev/null 2>&1 || PREV_TAG=""
-            fi
-          fi
-          
-          if [ -z "$PREV_TAG" ]; then
-            PREV_TAG=$(curl -s https://registry.npmjs.org/oh-my-opencode/latest | jq -r '.version // "0.0.0"')
-          fi
-          
-          echo "Comparing v${PREV_TAG}..v${VERSION}"
-          
-          # Get all commits between tags
-          COMMITS=$(git log "v${PREV_TAG}..v${VERSION}" --format="%s" 2>/dev/null || echo "")
-          
-          # Initialize sections
-          FEATURES=""
-          FIXES=""
-          REFACTOR=""
-          DOCS=""
-          OTHER=""
-          
-          while IFS= read -r commit; do
-            [ -z "$commit" ] && continue
-            # Skip chore, ci, release, test commits
-            [[ "$commit" =~ ^(chore|ci|release|test|ignore) ]] && continue
-            
-            if [[ "$commit" =~ ^feat ]]; then
-              # Extract scope and message: feat(scope): message -> **scope**: message
-              if [[ "$commit" =~ ^feat\(([^)]+)\):\ (.+)$ ]]; then
-                FEATURES="${FEATURES}\n- **${BASH_REMATCH[1]}**: ${BASH_REMATCH[2]}"
-              else
-                MSG="${commit#feat: }"
-                FEATURES="${FEATURES}\n- ${MSG}"
-              fi
-            elif [[ "$commit" =~ ^fix ]]; then
-              if [[ "$commit" =~ ^fix\(([^)]+)\):\ (.+)$ ]]; then
-                FIXES="${FIXES}\n- **${BASH_REMATCH[1]}**: ${BASH_REMATCH[2]}"
-              else
-                MSG="${commit#fix: }"
-                FIXES="${FIXES}\n- ${MSG}"
-              fi
-            elif [[ "$commit" =~ ^refactor ]]; then
-              if [[ "$commit" =~ ^refactor\(([^)]+)\):\ (.+)$ ]]; then
-                REFACTOR="${REFACTOR}\n- **${BASH_REMATCH[1]}**: ${BASH_REMATCH[2]}"
-              else
-                MSG="${commit#refactor: }"
-                REFACTOR="${REFACTOR}\n- ${MSG}"
-              fi
-            elif [[ "$commit" =~ ^docs ]]; then
-              if [[ "$commit" =~ ^docs\(([^)]+)\):\ (.+)$ ]]; then
-                DOCS="${DOCS}\n- **${BASH_REMATCH[1]}**: ${BASH_REMATCH[2]}"
-              else
-                MSG="${commit#docs: }"
-                DOCS="${DOCS}\n- ${MSG}"
-              fi
-            else
-              OTHER="${OTHER}\n- ${commit}"
-            fi
-          done <<< "$COMMITS"
-          
-          # Build release notes
-          {
-            echo "## What's Changed"
-            echo ""
-            if [ -n "$FEATURES" ]; then
-              echo "### Features"
-              echo -e "$FEATURES"
-              echo ""
-            fi
-            if [ -n "$FIXES" ]; then
-              echo "### Bug Fixes"
-              echo -e "$FIXES"
-              echo ""
-            fi
-            if [ -n "$REFACTOR" ]; then
-              echo "### Refactoring"
-              echo -e "$REFACTOR"
-              echo ""
-            fi
-            if [ -n "$DOCS" ]; then
-              echo "### Documentation"
-              echo -e "$DOCS"
-              echo ""
-            fi
-            if [ -n "$OTHER" ]; then
-              echo "### Other Changes"
-              echo -e "$OTHER"
-              echo ""
-            fi
-            echo "**Full Changelog**: https://github.com/${{ github.repository }}/compare/v${PREV_TAG}...v${VERSION}"
-          } > /tmp/changelog.md
-          
+          bun run script/generate-changelog.ts > /tmp/changelog.md
           cat /tmp/changelog.md
+        env:
+          GH_TOKEN: ${{ secrets.GITHUB_TOKEN }}
 
       - name: Create GitHub release
         run: |

.gitignore

@@ -1,5 +1,6 @@
 # Dependencies
-.sisyphus/
+.sisyphus/*
+!.sisyphus/rules/
 node_modules/
 
 # Build output

.opencode/command/publish.md

@@ -31,9 +31,9 @@ You are the release manager for oh-my-opencode. Execute the FULL publish workflo
   { "id": "sync-remote", "content": "Sync with remote (pull --rebase && push if unpushed commits)", "status": "pending", "priority": "high" },
   { "id": "run-workflow", "content": "Trigger GitHub Actions publish workflow", "status": "pending", "priority": "high" },
   { "id": "wait-workflow", "content": "Wait for workflow completion (poll every 30s)", "status": "pending", "priority": "high" },
-  { "id": "verify-release", "content": "Verify GitHub release was created", "status": "pending", "priority": "high" },
-  { "id": "draft-release-notes", "content": "Draft enhanced release notes content", "status": "pending", "priority": "high" },
-  { "id": "update-release-notes", "content": "Update GitHub release with enhanced notes", "status": "pending", "priority": "high" },
+  { "id": "verify-and-preview", "content": "Verify release created + preview auto-generated changelog & contributor thanks", "status": "pending", "priority": "high" },
+  { "id": "draft-summary", "content": "Draft enhanced release summary (mandatory for minor/major, optional for patch — ask user)", "status": "pending", "priority": "high" },
+  { "id": "apply-summary", "content": "Prepend enhanced summary to release (if user opted in)", "status": "pending", "priority": "high" },
   { "id": "verify-npm", "content": "Verify npm package published successfully", "status": "pending", "priority": "high" },
   { "id": "wait-platform-workflow", "content": "Wait for publish-platform workflow completion", "status": "pending", "priority": "high" },
   { "id": "verify-platform-binaries", "content": "Verify all 7 platform binary packages published", "status": "pending", "priority": "high" },
@@ -111,102 +111,165 @@ gh run view {run_id} --log-failed
 
 ---
 
-## STEP 5: VERIFY GITHUB RELEASE
+## STEP 5: VERIFY RELEASE & PREVIEW AUTO-GENERATED CONTENT
+
+Two goals: confirm the release exists, then show the user what the workflow already generated.
 
-Get the new version and verify release exists:
 ```bash
-# Get new version from package.json (workflow updates it)
+# Pull latest (workflow committed version bump)
 git pull --rebase
 NEW_VERSION=$(node -p "require('./package.json').version")
-gh release view "v${NEW_VERSION}"
+
+# Verify release exists on GitHub
+gh release view "v${NEW_VERSION}" --json tagName,url --jq '{tag: .tagName, url: .url}'
 ```
 
----
-
-## STEP 6: DRAFT ENHANCED RELEASE NOTES
-
-Analyze commits since the previous version and draft release notes following project conventions:
-
-### For PATCH releases:
-Keep simple format - just list commits:
-```markdown
-- {hash} {conventional commit message}
-- ...
-```
-
-### For MINOR releases:
-Use feature-focused format:
-```markdown
-## New Features
-
-### Feature Name
-- Description of what it does
-- Why it matters
-
-## Bug Fixes
-- fix(scope): description
-
-## Improvements
-- refactor(scope): description
-```
-
-### For MAJOR releases:
-Full changelog format:
-```markdown
-# v{version}
-
-Brief description of the release.
-
-## What's New Since v{previous}
-
-### Breaking Changes
-- Description of breaking change
-
-### Features
-- **Feature Name**: Description
-
-### Bug Fixes
-- Description
-
-### Documentation
-- Description
-
-## Migration Guide (if applicable)
-...
-```
-
-**CRITICAL: The enhanced notes must ADD to existing workflow-generated notes, not replace them.**
-
----
-
-## STEP 7: UPDATE GITHUB RELEASE
-
-**ZERO CONTENT LOSS POLICY:**
-- First, fetch the existing release body with `gh release view`
-- Your enhanced notes must be PREPENDED to the existing content
-- **NOT A SINGLE CHARACTER of existing content may be removed or modified**
-- The final release body = `{your_enhanced_notes}\n\n---\n\n{existing_body_exactly_as_is}`
+**After verifying, generate a local preview of the auto-generated content:**
 
 ```bash
-# Get existing body
-EXISTING_BODY=$(gh release view "v${NEW_VERSION}" --json body --jq '.body')
+bun run script/generate-changelog.ts
+```
 
-# Write enhanced notes to temp file (prepend to existing)
-cat > /tmp/release-notes-v${NEW_VERSION}.md << 'EOF'
-{your_enhanced_notes}
+<agent-instruction>
+After running the preview, present the output to the user and say:
+
+> **The following content is ALREADY included in the release automatically:**
+> - Commit changelog (grouped by feat/fix/refactor)
+> - Contributor thank-you messages (for non-team contributors)
+>
+> You do NOT need to write any of this. It's handled.
+>
+> **For a patch release**, this is usually sufficient on its own. However, if there are notable bug fixes or changes worth highlighting, an enhanced summary can be added.
+> **For a minor/major release**, an enhanced summary is **required** — I'll draft one in the next step.
+
+Wait for the user to acknowledge before proceeding.
+</agent-instruction>
 
 ---
 
-EOF
+## STEP 6: DRAFT ENHANCED RELEASE SUMMARY
 
-# Append existing body EXACTLY as-is (zero modifications)
-echo "$EXISTING_BODY" >> /tmp/release-notes-v${NEW_VERSION}.md
+<decision-gate>
 
-# Update release
-gh release edit "v${NEW_VERSION}" --notes-file /tmp/release-notes-v${NEW_VERSION}.md
+| Release Type | Action |
+|-------------|--------|
+| **patch** | ASK the user: "Would you like me to draft an enhanced summary highlighting the key bug fixes / changes? Or is the auto-generated changelog sufficient?" If user declines → skip to Step 8. If user accepts → draft a concise bug-fix / change summary below. |
+| **minor** | MANDATORY. Draft a concise feature summary. Do NOT proceed without one. |
+| **major** | MANDATORY. Draft a full release narrative with migration notes if applicable. Do NOT proceed without one. |
+
+</decision-gate>
+
+### What You're Writing (and What You're NOT)
+
+You are writing the **headline layer** — a product announcement that sits ABOVE the auto-generated commit log. Think "release blog post", not "git log".
+
+<rules>
+- NEVER duplicate commit messages. The auto-generated section already lists every commit.
+- NEVER write generic filler like "Various bug fixes and improvements" or "Several enhancements".
+- ALWAYS focus on USER IMPACT: what can users DO now that they couldn't before?
+- ALWAYS group by THEME or CAPABILITY, not by commit type (feat/fix/refactor).
+- ALWAYS use concrete language: "You can now do X" not "Added X feature".
+</rules>
+
+<examples>
+<bad title="Commit regurgitation — DO NOT do this">
+## What's New
+- feat(auth): add JWT refresh token rotation
+- fix(auth): handle expired token edge case
+- refactor(auth): extract middleware
+</bad>
+
+<good title="User-impact narrative — DO this">
+## 🔐 Smarter Authentication
+
+Token refresh is now automatic and seamless. Sessions no longer expire mid-task — the system silently rotates credentials in the background. If you've been frustrated by random logouts, this release fixes that.
+</good>
+
+<bad title="Vague filler — DO NOT do this">
+## Improvements
+- Various performance improvements
+- Bug fixes and stability enhancements
+</bad>
+
+<good title="Specific and measurable — DO this">
+## ⚡ 3x Faster Rule Parsing
+
+Rules are now cached by file modification time. If your project has 50+ rule files, you'll notice startup is noticeably faster — we measured a 3x improvement in our test suite.
+</good>
+</examples>
+
+### Drafting Process
+
+1. **Analyze** the commit list from Step 5's preview. Identify 2-5 themes that matter to users.
+2. **Write** the summary to `/tmp/release-summary-v${NEW_VERSION}.md`.
+3. **Present** the draft to the user for review and approval before applying.
+
+```bash
+# Write your draft here
+cat > /tmp/release-summary-v${NEW_VERSION}.md << 'SUMMARY_EOF'
+{your_enhanced_summary}
+SUMMARY_EOF
+
+cat /tmp/release-summary-v${NEW_VERSION}.md
 ```
 
-**CRITICAL: This is ADDITIVE ONLY. You are adding your notes on top. The existing content remains 100% intact.**
+<agent-instruction>
+After drafting, ask the user:
+> "Here's the release summary I drafted. This will appear AT THE TOP of the release notes, above the auto-generated commit changelog and contributor thanks. Want me to adjust anything before applying?"
+
+Do NOT proceed to Step 7 without user confirmation.
+</agent-instruction>
+
+---
+
+## STEP 7: APPLY ENHANCED SUMMARY TO RELEASE
+
+**Skip this step ONLY if the user opted out of the enhanced summary in Step 6** — proceed directly to Step 8.
+
+<architecture>
+The final release note structure:
+
+```
+┌─────────────────────────────────────┐
+│  Enhanced Summary (from Step 6)     │  ← You wrote this
+│  - Theme-based, user-impact focused │
+├─────────────────────────────────────┤
+│  ---  (separator)                   │
+├─────────────────────────────────────┤
+│  Auto-generated Commit Changelog    │  ← Workflow wrote this
+│  - feat/fix/refactor grouped        │
+│  - Contributor thank-you messages   │
+└─────────────────────────────────────┘
+```
+</architecture>
+
+<zero-content-loss-policy>
+- Fetch the existing release body FIRST
+- PREPEND your summary above it
+- The existing auto-generated content must remain 100% INTACT
+- NOT A SINGLE CHARACTER of existing content may be removed or modified
+</zero-content-loss-policy>
+
+```bash
+# 1. Fetch existing auto-generated body
+EXISTING_BODY=$(gh release view "v${NEW_VERSION}" --json body --jq '.body')
+
+# 2. Combine: enhanced summary on top, auto-generated below
+{
+  cat /tmp/release-summary-v${NEW_VERSION}.md
+  echo ""
+  echo "---"
+  echo ""
+  echo "$EXISTING_BODY"
+} > /tmp/final-release-v${NEW_VERSION}.md
+
+# 3. Update the release (additive only)
+gh release edit "v${NEW_VERSION}" --notes-file /tmp/final-release-v${NEW_VERSION}.md
+
+# 4. Confirm
+echo "✅ Release v${NEW_VERSION} updated with enhanced summary."
+gh release view "v${NEW_VERSION}" --json url --jq '.url'
+```
 
 ---
 

.opencode/command/remove-deadcode.md

@@ -3,337 +3,216 @@ description: Remove unused code from this project with ultrawork mode, LSP-verif
 ---
 
 <command-instruction>
-You are a dead code removal specialist. Execute the FULL dead code removal workflow using ultrawork mode.
 
-Your core weapon: **LSP FindReferences**. If a symbol has ZERO external references, it's dead. Remove it.
+Dead code removal via massively parallel deep agents. You are the ORCHESTRATOR — you scan, verify, batch, then delegate ALL removals to parallel agents.
 
-## CRITICAL RULES
+<rules>
+- **LSP is law.** Verify with `LspFindReferences(includeDeclaration=false)` before ANY removal decision.
+- **Never remove entry points.** `src/index.ts`, `src/cli/index.ts`, test files, config files, `packages/` — off-limits.
+- **You do NOT remove code yourself.** You scan, verify, batch, then fire deep agents. They do the work.
+</rules>
 
-1. **LSP is law.** Never guess. Always verify with `LspFindReferences` before removing ANYTHING.
-2. **One removal = one commit.** Every dead code removal gets its own atomic commit.
-3. **Test after every removal.** Run `bun test` after each. If it fails, REVERT and skip.
-4. **Leaf-first order.** Remove deepest unused symbols first, then work up the dependency chain. Removing a leaf may expose new dead code upstream.
-5. **Never remove entry points.** `src/index.ts`, `src/cli/index.ts`, test files, config files, and files in `packages/` are off-limits unless explicitly targeted.
+<false-positive-guards>
+NEVER mark as dead:
+- Symbols in `src/index.ts` or barrel `index.ts` re-exports
+- Symbols referenced in test files (tests are valid consumers)
+- Symbols with `@public` / `@api` JSDoc tags
+- Hook factories (`createXXXHook`), tool factories (`createXXXTool`), agent definitions in `agentSources`
+- Command templates, skill definitions, MCP configs
+- Symbols in `package.json` exports
+</false-positive-guards>
 
 ---
 
-## STEP 0: REGISTER TODO LIST (MANDATORY FIRST ACTION)
+## PHASE 1: SCAN — Find Dead Code Candidates
 
-```
-TodoWrite([
-  {"id": "scan", "content": "PHASE 1: Scan codebase for dead code candidates using LSP + explore agents", "status": "pending", "priority": "high"},
-  {"id": "verify", "content": "PHASE 2: Verify each candidate with LspFindReferences - zero false positives", "status": "pending", "priority": "high"},
-  {"id": "plan", "content": "PHASE 3: Plan removal order (leaf-first dependency order)", "status": "pending", "priority": "high"},
-  {"id": "remove", "content": "PHASE 4: Remove dead code one-by-one (remove -> test -> commit loop)", "status": "pending", "priority": "high"},
-  {"id": "final", "content": "PHASE 5: Final verification - full test suite + build + typecheck", "status": "pending", "priority": "high"}
-])
-```
+Run ALL of these in parallel:
 
----
+<parallel-scan>
 
-## PHASE 1: SCAN FOR DEAD CODE CANDIDATES
-
-**Mark scan as in_progress.**
-
-### 1.1: Launch Parallel Explore Agents (ALL BACKGROUND)
-
-Fire ALL simultaneously:
-
-```
-// Agent 1: Find all exported symbols
-delegate_task(subagent_type="explore", run_in_background=true,
-  prompt="Find ALL exported functions, classes, types, interfaces, and constants across src/.
-  List each with: file path, line number, symbol name, export type (named/default).
-  EXCLUDE: src/index.ts root exports, test files.
-  Return as structured list.")
-
-// Agent 2: Find potentially unused files
-delegate_task(subagent_type="explore", run_in_background=true,
-  prompt="Find files in src/ that are NOT imported by any other file.
-  Check import/require statements across the entire codebase.
-  EXCLUDE: index.ts files, test files, entry points, config files, .md files.
-  Return list of potentially orphaned files.")
-
-// Agent 3: Find unused imports within files
-delegate_task(subagent_type="explore", run_in_background=true,
-  prompt="Find unused imports across src/**/*.ts files.
-  Look for import statements where the imported symbol is never referenced in the file body.
-  Return: file path, line number, imported symbol name.")
-
-// Agent 4: Find functions/variables only used in their own declaration
-delegate_task(subagent_type="explore", run_in_background=true,
-  prompt="Find private/non-exported functions, variables, and types in src/**/*.ts that appear
-  to have zero usage beyond their declaration. Return: file path, line number, symbol name.")
-```
-
-### 1.2: Direct AST-Grep Scans (WHILE AGENTS RUN)
-
-```typescript
-// Find unused imports pattern
-ast_grep_search(pattern="import { $NAME } from '$PATH'", lang="typescript", paths=["src/"])
-
-// Find empty export objects
-ast_grep_search(pattern="export {}", lang="typescript", paths=["src/"])
-```
-
-### 1.3: Collect All Results
-
-Collect background agent results. Compile into a master candidate list:
-
-```
-## DEAD CODE CANDIDATES
-
-| # | File | Line | Symbol | Type | Confidence |
-|---|------|------|--------|------|------------|
-| 1 | src/foo.ts | 42 | unusedFunc | function | HIGH |
-| 2 | src/bar.ts | 10 | OldType | type | MEDIUM |
-```
-
-**Mark scan as completed.**
-
----
-
-## PHASE 2: VERIFY WITH LSP (ZERO FALSE POSITIVES)
-
-**Mark verify as in_progress.**
-
-For EVERY candidate from Phase 1, run this verification:
-
-### 2.1: The LSP Verification Protocol
-
-For each candidate symbol:
-
-```typescript
-// Step 1: Find the symbol's exact position
-LspDocumentSymbols(filePath)  // Get line/character of the symbol
-
-// Step 2: Find ALL references across the ENTIRE workspace
-LspFindReferences(filePath, line, character, includeDeclaration=false)
-// includeDeclaration=false → only counts USAGES, not the definition itself
-
-// Step 3: Evaluate
-// 0 references → CONFIRMED DEAD CODE
-// 1+ references → NOT dead, remove from candidate list
-```
-
-### 2.2: False Positive Guards
-
-**NEVER mark as dead code if:**
-- Symbol is in `src/index.ts` (package entry point)
-- Symbol is in any `index.ts` that re-exports (barrel file check: look if it's re-exported)
-- Symbol is referenced in test files (tests are valid consumers)
-- Symbol has `@public` or `@api` JSDoc tags
-- Symbol is in a file listed in `package.json` exports
-- Symbol is a hook factory (`createXXXHook`) registered in `src/index.ts`
-- Symbol is a tool factory (`createXXXTool`) registered in tool loading
-- Symbol is an agent definition registered in `agentSources`
-- File is a command template, skill definition, or MCP config
-
-### 2.3: Build Confirmed Dead Code List
-
-After verification, produce:
-
-```
-## CONFIRMED DEAD CODE (LSP-verified, 0 external references)
-
-| # | File | Line | Symbol | Type | Safe to Remove |
-|---|------|------|--------|------|----------------|
-| 1 | src/foo.ts | 42 | unusedFunc | function | YES |
-```
-
-**If ZERO confirmed dead code found: Report "No dead code found" and STOP.**
-
-**Mark verify as completed.**
-
----
-
-## PHASE 3: PLAN REMOVAL ORDER
-
-**Mark plan as in_progress.**
-
-### 3.1: Dependency Analysis
-
-For each confirmed dead symbol:
-1. Check if removing it would expose other dead code
-2. Check if other dead symbols depend on this one
-3. Build removal dependency graph
-
-### 3.2: Order by Leaf-First
-
-```
-Removal Order:
-1. [Leaf symbols - no other dead code depends on them]
-2. [Intermediate symbols - depended on only by already-removed dead code]
-3. [Dead files - entire files with no live exports]
-```
-
-### 3.3: Register Granular Todos
-
-Create one todo per removal:
-
-```
-TodoWrite([
-  {"id": "remove-1", "content": "Remove unusedFunc from src/foo.ts:42", "status": "pending", "priority": "high"},
-  {"id": "remove-2", "content": "Remove OldType from src/bar.ts:10", "status": "pending", "priority": "high"},
-  // ... one per confirmed dead symbol
-])
-```
-
-**Mark plan as completed.**
-
----
-
-## PHASE 4: ITERATIVE REMOVAL LOOP
-
-**Mark remove as in_progress.**
-
-For EACH dead code item, execute this exact loop:
-
-### 4.1: Pre-Removal Check
-
-```typescript
-// Re-verify it's still dead (previous removals may have changed things)
-LspFindReferences(filePath, line, character, includeDeclaration=false)
-// If references > 0 now → SKIP (previous removal exposed a new consumer)
-```
-
-### 4.2: Remove the Dead Code
-
-Use appropriate tool:
-
-**For unused imports:**
-```typescript
-Edit(filePath, oldString="import { deadSymbol } from '...';\n", newString="")
-// Or if it's one of many imports, remove just the symbol from the import list
-```
-
-**For unused functions/classes/types:**
-```typescript
-// Read the full symbol extent first
-Read(filePath, offset=startLine, limit=endLine-startLine+1)
-// Then remove it
-Edit(filePath, oldString="[full symbol text]", newString="")
-```
-
-**For dead files:**
+**TypeScript strict mode (your primary scanner — run this FIRST):**
 ```bash
-# Only after confirming ZERO imports point to this file
-rm "path/to/dead-file.ts"
+bunx tsc --noEmit --noUnusedLocals --noUnusedParameters 2>&1
+```
+This gives you the definitive list of unused locals, imports, parameters, and types with exact file:line locations.
+
+**Explore agents (fire ALL simultaneously as background):**
+
+```
+task(subagent_type="explore", run_in_background=true, load_skills=[],
+  description="Find orphaned files",
+  prompt="Find files in src/ NOT imported by any other file. Check all import statements. EXCLUDE: index.ts, *.test.ts, entry points, .md, packages/. Return: file paths.")
+
+task(subagent_type="explore", run_in_background=true, load_skills=[],
+  description="Find unused exported symbols",
+  prompt="Find exported functions/types/constants in src/ that are never imported by other files. Cross-reference: for each export, grep the symbol name across src/ — if it only appears in its own file, it's a candidate. EXCLUDE: src/index.ts exports, test files. Return: file path, line, symbol name, export type.")
 ```
 
-**After removal, also clean up:**
-- Remove any imports that were ONLY used by the removed code
-- Remove any now-empty import statements
-- Fix any trailing whitespace / double blank lines left behind
+</parallel-scan>
 
-### 4.3: Post-Removal Verification
+Collect all results into a master candidate list.
+
+---
+
+## PHASE 2: VERIFY — LSP Confirmation (Zero False Positives)
+
+For EACH candidate from Phase 1:
 
 ```typescript
-// 1. LSP diagnostics on changed file
-LspDiagnostics(filePath, severity="error")
-// Must be clean (or only pre-existing errors)
-
-// 2. Run tests
-bash("bun test")
-// Must pass
-
-// 3. Typecheck
-bash("bun run typecheck")
-// Must pass
+LspFindReferences(filePath, line, character, includeDeclaration=false)
+// 0 references → CONFIRMED dead
+// 1+ references → NOT dead, drop from list
 ```
 
-### 4.4: Handle Failures
+Also apply the false-positive-guards above. Produce a confirmed list:
 
-If ANY verification fails:
-1. **REVERT** the change immediately (`git checkout -- [file]`)
-2. Mark this removal todo as `cancelled` with note: "Removal caused [error]. Skipped."
-3. Proceed to next item
-
-### 4.5: Commit
-
-```bash
-git add [changed-files]
-git commit -m "refactor: remove unused [symbolType] [symbolName] from [filePath]"
+```
+| # | File | Symbol | Type | Action |
+|---|------|--------|------|--------|
+| 1 | src/foo.ts:42 | unusedFunc | function | REMOVE |
+| 2 | src/bar.ts:10 | OldType | type | REMOVE |
+| 3 | src/baz.ts:7 | ctx | parameter | PREFIX _ |
 ```
 
-Mark this removal todo as `completed`.
+**Action types:**
+- `REMOVE` — delete the symbol/import/file entirely
+- `PREFIX _` — unused function parameter required by signature → rename to `_paramName`
 
-### 4.6: Re-scan After Removal
+If ZERO confirmed: report "No dead code found" and STOP.
 
-After removing a symbol, check if its removal exposed NEW dead code:
-- Were there imports that only existed to serve the removed symbol?
-- Are there other symbols in the same file now unreferenced?
+---
 
-If new dead code is found, add it to the removal queue.
+## PHASE 3: BATCH — Group by File for Conflict-Free Parallelism
 
-**Repeat 4.1-4.6 for every item. Mark remove as completed when done.**
+<batching-rules>
+
+**Goal: maximize parallel agents with ZERO git conflicts.**
+
+1. Group confirmed dead code items by FILE PATH
+2. All items in the SAME file go to the SAME batch (prevents two agents editing the same file)
+3. If a dead FILE (entire file deletion) exists, it's its own batch
+4. Target 5-15 batches. If fewer than 5 items total, use 1 batch per item.
+
+**Example batching:**
+```
+Batch A: [src/hooks/foo/hook.ts — 3 unused imports]
+Batch B: [src/features/bar/manager.ts — 2 unused constants, 1 dead function]
+Batch C: [src/tools/baz/tool.ts — 1 unused param, src/tools/baz/types.ts — 1 unused type]
+Batch D: [src/dead-file.ts — entire file deletion]
+```
+
+Files in the same directory CAN be batched together (they won't conflict as long as no two agents edit the same file). Maximize batch count for parallelism.
+
+</batching-rules>
+
+---
+
+## PHASE 4: EXECUTE — Fire Parallel Deep Agents
+
+For EACH batch, fire a deep agent:
+
+```
+task(
+  category="deep",
+  load_skills=["typescript-programmer", "git-master"],
+  run_in_background=true,
+  description="Remove dead code batch N: [brief description]",
+  prompt="[see template below]"
+)
+```
+
+<agent-prompt-template>
+
+Every deep agent gets this prompt structure (fill in the specifics per batch):
+
+```
+## TASK: Remove dead code from [file list]
+
+## DEAD CODE TO REMOVE
+
+### [file path] line [N]
+- Symbol: `[name]` — [type: unused import / unused constant / unused function / unused parameter / dead file]
+- Action: [REMOVE entirely / REMOVE from import list / PREFIX with _]
+
+### [file path] line [N]
+- ...
+
+## PROTOCOL
+
+1. Read each file to understand exact syntax at the target lines
+2. For each symbol, run LspFindReferences to RE-VERIFY it's still dead (another agent may have changed things)
+3. Apply the change:
+   - Unused import (only symbol in line): remove entire import line
+   - Unused import (one of many): remove only that symbol from the import list
+   - Unused constant/function/type: remove the declaration. Clean up trailing blank lines.
+   - Unused parameter: prefix with `_` (do NOT remove — required by signature)
+   - Dead file: delete with `rm`
+4. After ALL edits in this batch, run: `bun run typecheck`
+5. If typecheck fails: `git checkout -- [files]` and report failure
+6. If typecheck passes: stage ONLY your files and commit:
+   `git add [your-specific-files] && git commit -m "refactor: remove dead code from [brief file list]"`
+7. Report what you removed and the commit hash
+
+## CRITICAL
+- Stage ONLY your batch's files (`git add [specific files]`). NEVER `git add -A` — other agents are working in parallel.
+- If typecheck fails after your edits, REVERT all changes and report. Do not attempt to fix.
+- Pre-existing test failures in other files are expected. Only typecheck matters for your batch.
+```
+
+</agent-prompt-template>
+
+Fire ALL batches simultaneously. Wait for all to complete.
 
 ---
 
 ## PHASE 5: FINAL VERIFICATION
 
-**Mark final as in_progress.**
+After ALL agents complete:
 
-### 5.1: Full Test Suite
 ```bash
-bun test
+bun run typecheck   # must pass
+bun test            # note any NEW failures vs pre-existing
+bun run build       # must pass
 ```
 
-### 5.2: Full Typecheck
-```bash
-bun run typecheck
-```
-
-### 5.3: Full Build
-```bash
-bun run build
-```
-
-### 5.4: Summary Report
+Produce summary:
 
 ```markdown
 ## Dead Code Removal Complete
 
 ### Removed
-| # | Symbol | File | Type | Commit |
-|---|--------|------|------|--------|
-| 1 | unusedFunc | src/foo.ts | function | abc1234 |
+| # | Symbol | File | Type | Commit | Agent |
+|---|--------|------|------|--------|-------|
+| 1 | unusedFunc | src/foo.ts | function | abc1234 | Batch A |
 
-### Skipped (caused failures)
+### Skipped (agent reported failure)
 | # | Symbol | File | Reason |
 |---|--------|------|--------|
-| 1 | riskyFunc | src/bar.ts | Test failure: [details] |
 
 ### Verification
-- Tests: PASSED (X/Y passing)
-- Typecheck: CLEAN
-- Build: SUCCESS
-- Total dead code removed: N symbols across M files
+- Typecheck: PASS/FAIL
+- Tests: X passing, Y failing (Z pre-existing)
+- Build: PASS/FAIL
+- Total removed: N symbols across M files
 - Total commits: K atomic commits
+- Parallel agents used: P
 ```
 
-**Mark final as completed.**
-
 ---
 
 ## SCOPE CONTROL
 
-**If $ARGUMENTS is provided**, narrow the scan to the specified scope:
-- File path: Only scan that file
-- Directory: Only scan that directory
-- Symbol name: Only check that specific symbol
-- "all" or empty: Full project scan (default)
+If `$ARGUMENTS` is provided, narrow the scan:
+- File path → only that file
+- Directory → only that directory
+- Symbol name → only that symbol
+- `all` or empty → full project scan (default)
 
 ## ABORT CONDITIONS
 
-**STOP and report to user if:**
-- 3 consecutive removals cause test failures
+STOP and report if:
+- More than 50 candidates found (ask user to narrow scope or confirm proceeding)
 - Build breaks and cannot be fixed by reverting
-- More than 50 candidates found (ask user to narrow scope)
-
-## LANGUAGE
-
-Use English for commit messages and technical output.
 
 </command-instruction>
 

.opencode/skills/github-issue-triage/SKILL.md

@@ -21,7 +21,7 @@ You are a GitHub issue triage automation agent. Your job is to:
 
 | Aspect | Rule |
 |--------|------|
-| **Task Granularity** | 1 Issue = Exactly 1 `delegate_task()` call |
+| **Task Granularity** | 1 Issue = Exactly 1 `task()` call |
 | **Execution Mode** | `run_in_background=true` (Each issue runs independently) |
 | **Result Handling** | `background_output()` to collect results as they complete |
 | **Reporting** | IMMEDIATE streaming when each task finishes |
@@ -67,7 +67,7 @@ for (let i = 0; i < allIssues.length; i++) {
   const issue = allIssues[i]
   const category = getCategory(i)
   
-  const taskId = await delegate_task(
+  const taskId = await task(
     category=category,
     load_skills=[],
     run_in_background=true,  // ← CRITICAL: Each issue is independent background task
@@ -195,7 +195,7 @@ for (let i = 0; i < allIssues.length; i++) {
   
   console.log(`🚀 Launching background task for Issue #${issue.number} (${category})...`)
   
-  const taskId = await delegate_task(
+  const taskId = await task(
     category=category,
     load_skills=[],
     run_in_background=true,  // ← BACKGROUND TASK: Each issue runs independently
@@ -480,7 +480,7 @@ When invoked, immediately:
 4. Exhaustive pagination for issues
 5. Exhaustive pagination for PRs
 6. **LAUNCH**: For each issue:
-   - `delegate_task(run_in_background=true)` - 1 task per issue
+   - `task(run_in_background=true)` - 1 task per issue
    - Store taskId mapped to issue number
 7. **STREAM**: Poll `background_output()` for each task:
    - As each completes, immediately report result

.opencode/skills/github-pr-triage/SKILL.md

@@ -22,7 +22,7 @@ You are a GitHub Pull Request triage automation agent. Your job is to:
 
 | Aspect | Rule |
 |--------|------|
-| **Task Granularity** | 1 PR = Exactly 1 `delegate_task()` call |
+| **Task Granularity** | 1 PR = Exactly 1 `task()` call |
 | **Execution Mode** | `run_in_background=true` (Each PR runs independently) |
 | **Result Handling** | `background_output()` to collect results as they complete |
 | **Reporting** | IMMEDIATE streaming when each task finishes |
@@ -68,7 +68,7 @@ for (let i = 0; i < allPRs.length; i++) {
   const pr = allPRs[i]
   const category = getCategory(i)
   
-  const taskId = await delegate_task(
+  const taskId = await task(
     category=category,
     load_skills=[],
     run_in_background=true,  // ← CRITICAL: Each PR is independent background task
@@ -178,7 +178,7 @@ for (let i = 0; i < allPRs.length; i++) {
   
   console.log(`🚀 Launching background task for PR #${pr.number} (${category})...`)
   
-  const taskId = await delegate_task(
+  const taskId = await task(
     category=category,
     load_skills=[],
     run_in_background=true,  // ← BACKGROUND TASK: Each PR runs independently
@@ -474,7 +474,7 @@ When invoked, immediately:
 2. `gh repo view --json nameWithOwner -q .nameWithOwner`
 3. Exhaustive pagination for ALL open PRs
 4. **LAUNCH**: For each PR:
-   - `delegate_task(run_in_background=true)` - 1 task per PR
+   - `task(run_in_background=true)` - 1 task per PR
    - Store taskId mapped to PR number
 5. **STREAM**: Poll `background_output()` for each task:
    - As each completes, immediately report result

.sisyphus/rules/modular-code-enforcement.md

@@ -0,0 +1,117 @@
+---
+globs: ["**/*.ts", "**/*.tsx"]
+alwaysApply: false
+description: "Enforces strict modular code architecture: SRP, no monolithic index.ts, 200 LOC hard limit"
+---
+
+<MANDATORY_ARCHITECTURE_RULE severity="BLOCKING" priority="HIGHEST">
+
+# Modular Code Architecture — Zero Tolerance Policy
+
+This rule is NON-NEGOTIABLE. Violations BLOCK all further work until resolved.
+
+## Rule 1: index.ts is an ENTRY POINT, NOT a dumping ground
+
+`index.ts` files MUST ONLY contain:
+- Re-exports (`export { ... } from "./module"`)
+- Factory function calls that compose modules
+- Top-level wiring/registration (hook registration, plugin setup)
+
+`index.ts` MUST NEVER contain:
+- Business logic implementation
+- Helper/utility functions
+- Type definitions beyond simple re-exports
+- Multiple unrelated responsibilities mixed together
+
+**If you find mixed logic in index.ts**: Extract each responsibility into its own dedicated file BEFORE making any other changes. This is not optional.
+
+## Rule 2: No Catch-All Files — utils.ts / service.ts are CODE SMELLS
+
+A single `utils.ts`, `helpers.ts`, `service.ts`, or `common.ts` is a **gravity well** — every unrelated function gets tossed in, and it grows into an untestable, unreviewable blob.
+
+**These file names are BANNED as top-level catch-alls.** Instead:
+
+| Anti-Pattern | Refactor To |
+|--------------|-------------|
+| `utils.ts` with `formatDate()`, `slugify()`, `retry()` | `date-formatter.ts`, `slugify.ts`, `retry.ts` |
+| `service.ts` handling auth + billing + notifications | `auth-service.ts`, `billing-service.ts`, `notification-service.ts` |
+| `helpers.ts` with 15 unrelated exports | One file per logical domain |
+
+**Design for reusability from the start.** Each module should be:
+- **Independently importable** — no consumer should need to pull in unrelated code
+- **Self-contained** — its dependencies are explicit, not buried in a shared grab-bag
+- **Nameable by purpose** — the filename alone tells you what it does
+
+If you catch yourself typing `utils.ts` or `service.ts`, STOP and name the file after what it actually does.
+
+## Rule 3: Single Responsibility Principle — ABSOLUTE
+
+Every `.ts` file MUST have exactly ONE clear, nameable responsibility.
+
+**Self-test**: If you cannot describe the file's purpose in ONE short phrase (e.g., "parses YAML frontmatter", "matches rules against file paths"), the file does too much. Split it.
+
+| Signal | Action |
+|--------|--------|
+| File has 2+ unrelated exported functions | **SPLIT NOW** — each into its own module |
+| File mixes I/O with pure logic | **SPLIT NOW** — separate side effects from computation |
+| File has both types and implementation | **SPLIT NOW** — types.ts + implementation.ts |
+| You need to scroll to understand the file | **SPLIT NOW** — it's too large |
+
+## Rule 4: 200 LOC Hard Limit — CODE SMELL DETECTOR
+
+Any `.ts`/`.tsx` file exceeding **200 lines of code** (excluding prompt strings, template literals containing prompts, and `.md` content) is an **immediate code smell**.
+
+**When you detect a file > 200 LOC**:
+1. **STOP** current work
+2. **Identify** the multiple responsibilities hiding in the file
+3. **Extract** each responsibility into a focused module
+4. **Verify** each resulting file is < 200 LOC and has a single purpose
+5. **Resume** original work
+
+Prompt-heavy files (agent definitions, skill definitions) where the bulk of content is template literal prompt text are EXEMPT from the LOC count — but their non-prompt logic must still be < 200 LOC.
+
+### How to Count LOC
+
+**Count these** (= actual logic):
+- Import statements
+- Variable/constant declarations
+- Function/class/interface/type definitions
+- Control flow (`if`, `for`, `while`, `switch`, `try/catch`)
+- Expressions, assignments, return statements
+- Closing braces `}` that belong to logic blocks
+
+**Exclude these** (= not logic):
+- Blank lines
+- Comment-only lines (`//`, `/* */`, `/** */`)
+- Lines inside template literals that are prompt/instruction text (e.g., the string body of `` const prompt = `...` ``)
+- Lines inside multi-line strings used as documentation/prompt content
+
+**Quick method**: Read the file → subtract blank lines, comment-only lines, and prompt string content → remaining count = LOC.
+
+**Example**:
+```typescript
+// 1  import { foo } from "./foo";          ← COUNT
+// 2                                         ← SKIP (blank)
+// 3  // Helper for bar                      ← SKIP (comment)
+// 4  export function bar(x: number) {       ← COUNT
+// 5    const prompt = `                     ← COUNT (declaration)
+// 6      You are an assistant.              ← SKIP (prompt text)
+// 7      Follow these rules:                ← SKIP (prompt text)
+// 8    `;                                   ← COUNT (closing)
+// 9    return process(prompt, x);           ← COUNT
+// 10 }                                      ← COUNT
+```
+→ LOC = **5** (lines 1, 4, 5, 9, 10). Not 10.
+
+When in doubt, **round up** — err on the side of splitting.
+
+## How to Apply
+
+When reading, writing, or editing ANY `.ts`/`.tsx` file:
+
+1. **Check the file you're touching** — does it violate any rule above?
+2. **If YES** — refactor FIRST, then proceed with your task
+3. **If creating a new file** — ensure it has exactly one responsibility and stays under 200 LOC
+4. **If adding code to an existing file** — verify the addition doesn't push the file past 200 LOC or add a second responsibility. If it does, extract into a new module.
+
+</MANDATORY_ARCHITECTURE_RULE>

AGENTS.md

@@ -1,8 +1,8 @@
 # PROJECT KNOWLEDGE BASE
 
-**Generated:** 2026-02-03T16:10:30+09:00
-**Commit:** d7679e14
-**Branch:** dev
+**Generated:** 2026-02-16T14:58:00+09:00
+**Commit:** 28cd34c3
+**Branch:** fuck-v1.2
 
 ---
 
@@ -27,12 +27,14 @@ feature branches (your work)
 | **ALL PRs → `dev`** | Every pull request MUST target the `dev` branch |
 | **NEVER PR → `master`** | PRs to `master` are **automatically rejected** by CI |
 | **"Create a PR" = target `dev`** | When asked to create a new PR, it ALWAYS means targeting `dev` |
+| **Merge commit ONLY** | Squash merge is **disabled** in this repo. Always use merge commit when merging PRs. |
 
 ### Why This Matters
 
 - `master` = production/published npm package
 - `dev` = integration branch where features are merged and tested
 - Feature branches → `dev` → (after testing) → `master`
+- Squash merge is disabled at the repository level — attempting it will fail
 
 **If you create a PR targeting `master`, it WILL be rejected. No exceptions.**
 
@@ -75,11 +77,6 @@ Oh-My-OpenCode is a **plugin for OpenCode**. You will frequently need to examine
 | Debugging plugin issues | Fire `librarian` to find relevant OpenCode internals |
 | Answering "how does OpenCode do X?" | Fire `librarian` FIRST |
 
-**The `librarian` agent is specialized for:**
-- Searching remote codebases (GitHub)
-- Retrieving official documentation
-- Finding implementation examples in open source
-
 **DO NOT guess or hallucinate about OpenCode internals.** Always verify by examining actual source code via `librarian` or direct clone.
 
 ---
@@ -90,8 +87,6 @@ Oh-My-OpenCode is a **plugin for OpenCode**. You will frequently need to examine
 
 ### All Project Communications MUST Be in English
 
-This is an **international open-source project**. To ensure accessibility and maintainability:
-
 | Context | Language Requirement |
 |---------|---------------------|
 | **GitHub Issues** | English ONLY |
@@ -101,59 +96,74 @@ This is an **international open-source project**. To ensure accessibility and ma
 | **Documentation** | English ONLY |
 | **AGENTS.md files** | English ONLY |
 
-### Why This Matters
-
-- **Global Collaboration**: Contributors from all countries can participate
-- **Searchability**: English keywords are universally searchable
-- **AI Agent Compatibility**: AI tools work best with English content
-- **Consistency**: Mixed languages create confusion and fragmentation
-
-### Enforcement
-
-- Issues/PRs with non-English content may be closed with a request to resubmit in English
-- Commit messages must be in English - CI may reject non-English commits
-- Translated READMEs exist (README.ko.md, README.ja.md, etc.) but the primary docs are English
-
-**If you're not comfortable writing in English, use translation tools. Broken English is fine - we'll help fix it. Non-English is not acceptable.**
+**If you're not comfortable writing in English, use translation tools. Broken English is fine. Non-English is not acceptable.**
 
 ---
 
 ## OVERVIEW
 
-OpenCode plugin: multi-model agent orchestration (Claude Opus 4.5, GPT-5.2, Gemini 3 Flash). 34 lifecycle hooks, 20+ tools (LSP, AST-Grep, delegation), 11 specialized agents, full Claude Code compatibility. "oh-my-zsh" for OpenCode.
+OpenCode plugin (oh-my-opencode): multi-model agent orchestration with 11 specialized agents, 41 lifecycle hooks across 7 event types, 26 tools (LSP, AST-Grep, delegation, task management), full Claude Code compatibility layer, 4-scope skill loading, background agent concurrency, tmux integration, and 3-tier MCP system. "oh-my-zsh" for OpenCode.
 
 ## STRUCTURE
 
 ```
 oh-my-opencode/
 ├── src/
-│   ├── agents/        # 11 AI agents - see src/agents/AGENTS.md
-│   ├── hooks/         # 34 lifecycle hooks - see src/hooks/AGENTS.md
-│   ├── tools/         # 20+ tools - see src/tools/AGENTS.md
-│   ├── features/      # Background agents, Claude Code compat - see src/features/AGENTS.md
-│   ├── shared/        # 66 cross-cutting utilities - see src/shared/AGENTS.md
-│   ├── cli/           # CLI installer, doctor - see src/cli/AGENTS.md
-│   ├── mcp/           # Built-in MCPs - see src/mcp/AGENTS.md
-│   ├── config/        # Zod schema, TypeScript types
-│   └── index.ts       # Main plugin entry (788 lines)
-├── script/            # build-schema.ts, build-binaries.ts
-├── packages/          # 11 platform-specific binaries
-└── dist/              # Build output (ESM + .d.ts)
+│   ├── agents/              # 11 AI agents — see src/agents/AGENTS.md
+│   ├── hooks/               # 41 lifecycle hooks — see src/hooks/AGENTS.md
+│   ├── tools/               # 26 tools — see src/tools/AGENTS.md
+│   ├── features/            # Background agents, skills, CC compat — see src/features/AGENTS.md
+│   ├── shared/              # Cross-cutting utilities — see src/shared/AGENTS.md
+│   ├── cli/                 # CLI installer, doctor — see src/cli/AGENTS.md
+│   ├── mcp/                 # Built-in MCPs — see src/mcp/AGENTS.md
+│   ├── config/              # Zod schema — see src/config/AGENTS.md
+│   ├── plugin-handlers/     # Config loading pipeline — see src/plugin-handlers/AGENTS.md
+│   ├── plugin/              # Plugin interface composition (21 files)
+│   ├── index.ts             # Main plugin entry (106 lines)
+│   ├── create-hooks.ts      # Hook creation coordination (62 lines)
+│   ├── create-managers.ts   # Manager initialization (80 lines)
+│   ├── create-tools.ts      # Tool registry composition (54 lines)
+│   ├── plugin-interface.ts  # Plugin interface assembly (66 lines)
+│   ├── plugin-config.ts     # Config loading orchestration (180 lines)
+│   └── plugin-state.ts      # Model cache state (12 lines)
+├── script/                  # build-schema.ts, build-binaries.ts, publish.ts, generate-changelog.ts
+├── packages/                # 11 platform-specific binary packages
+└── dist/                    # Build output (ESM + .d.ts)
+```
+
+## INITIALIZATION FLOW
+
+```
+OhMyOpenCodePlugin(ctx)
+  1. injectServerAuthIntoClient(ctx.client)
+  2. startTmuxCheck()
+  3. loadPluginConfig(ctx.directory, ctx)      → OhMyOpenCodeConfig
+  4. createFirstMessageVariantGate()
+  5. createModelCacheState()
+  6. createManagers(ctx, config, tmux, cache)  → TmuxSessionManager, BackgroundManager, SkillMcpManager, ConfigHandler
+  7. createTools(ctx, config, managers)         → filteredTools, mergedSkills, availableSkills, availableCategories
+  8. createHooks(ctx, config, backgroundMgr)   → 41 hooks (core + continuation + skill)
+  9. createPluginInterface(...)                 → 7 OpenCode hook handlers
+ 10. Return plugin with experimental.session.compacting
 ```
 
 ## WHERE TO LOOK
 
 | Task | Location | Notes |
 |------|----------|-------|
-| Add agent | `src/agents/` | Create .ts with factory, add to `agentSources` |
-| Add hook | `src/hooks/` | Create dir with `createXXXHook()`, register in index.ts |
+| Add agent | `src/agents/` | Create .ts with factory, add to `agentSources` in builtin-agents/ |
+| Add hook | `src/hooks/` | Create dir, register in `src/plugin/hooks/create-*-hooks.ts` |
 | Add tool | `src/tools/` | Dir with index/types/constants/tools.ts |
-| Add MCP | `src/mcp/` | Create config, add to index.ts |
-| Add skill | `src/features/builtin-skills/` | Create dir with SKILL.md |
+| Add MCP | `src/mcp/` | Create config, add to `createBuiltinMcps()` |
+| Add skill | `src/features/builtin-skills/` | Create .ts in skills/ |
 | Add command | `src/features/builtin-commands/` | Add template + register in commands.ts |
-| Config schema | `src/config/schema.ts` | Zod schema, run `bun run build:schema` |
-| Background agents | `src/features/background-agent/` | manager.ts (1418 lines) |
-| Orchestrator | `src/hooks/atlas/` | Main orchestration hook (757 lines) |
+| Config schema | `src/config/schema/` | 21 schema component files, run `bun run build:schema` |
+| Plugin config | `src/plugin-handlers/config-handler.ts` | JSONC loading, merging, migration |
+| Background agents | `src/features/background-agent/` | manager.ts (1701 lines) |
+| Orchestrator | `src/hooks/atlas/` | Main orchestration hook (1976 lines) |
+| Delegation | `src/tools/delegate-task/` | Category routing (constants.ts 569 lines) |
+| Task system | `src/features/claude-tasks/` | Task schema, storage, todo sync |
+| Plugin interface | `src/plugin/` | 21 files composing hooks, handlers, registries |
 
 ## TDD (Test-Driven Development)
 
@@ -164,8 +174,8 @@ oh-my-opencode/
 
 **Rules:**
 - NEVER write implementation before test
-- NEVER delete failing tests - fix the code
-- Test file: `*.test.ts` alongside source (100 test files)
+- NEVER delete failing tests — fix the code
+- Test file: `*.test.ts` alongside source (176 test files)
 - BDD comments: `//#given`, `//#when`, `//#then`
 
 ## CONVENTIONS
@@ -175,43 +185,82 @@ oh-my-opencode/
 - **Build**: `bun build` (ESM) + `tsc --emitDeclarationOnly`
 - **Exports**: Barrel pattern via index.ts
 - **Naming**: kebab-case dirs, `createXXXHook`/`createXXXTool` factories
-- **Testing**: BDD comments, 100 test files
+- **Testing**: BDD comments, 176 test files, 1130 TypeScript files
 - **Temperature**: 0.1 for code agents, max 0.3
+- **Modular architecture**: 200 LOC hard limit per file (prompt strings exempt)
 
 ## ANTI-PATTERNS
 
 | Category | Forbidden |
 |----------|-----------|
-| Package Manager | npm, yarn - Bun exclusively |
-| Types | @types/node - use bun-types |
-| File Ops | mkdir/touch/rm/cp/mv in code - use bash tool |
-| Publishing | Direct `bun publish` - GitHub Actions only |
-| Versioning | Local version bump - CI manages |
+| Package Manager | npm, yarn — Bun exclusively |
+| Types | @types/node — use bun-types |
+| File Ops | mkdir/touch/rm/cp/mv in code — use bash tool |
+| Publishing | Direct `bun publish` — GitHub Actions only |
+| Versioning | Local version bump — CI manages |
 | Type Safety | `as any`, `@ts-ignore`, `@ts-expect-error` |
 | Error Handling | Empty catch blocks |
 | Testing | Deleting failing tests, writing implementation before test |
-| Agent Calls | Sequential - use `delegate_task` parallel |
-| Hook Logic | Heavy PreToolUse - slows every call |
+| Agent Calls | Sequential — use `task` parallel |
+| Hook Logic | Heavy PreToolUse — slows every call |
 | Commits | Giant (3+ files), separate test from impl |
 | Temperature | >0.3 for code agents |
-| Trust | Agent self-reports - ALWAYS verify |
+| Trust | Agent self-reports — ALWAYS verify |
 | Git | `git add -i`, `git rebase -i` (no interactive input) |
 | Git | Skip hooks (--no-verify), force push without request |
-| Bash | `sleep N` - use conditional waits |
-| Bash | `cd dir && cmd` - use workdir parameter |
+| Bash | `sleep N` — use conditional waits |
+| Bash | `cd dir && cmd` — use workdir parameter |
+| Files | Catch-all utils.ts/helpers.ts — name by purpose |
 
 ## AGENT MODELS
 
-| Agent | Model | Purpose |
-|-------|-------|---------|
-| Sisyphus | anthropic/claude-opus-4-5 | Primary orchestrator (fallback: kimi-k2.5 → glm-4.7 → gpt-5.2-codex → gemini-3-pro) |
-| Hephaestus | openai/gpt-5.2-codex | Autonomous deep worker, "The Legitimate Craftsman" (requires gpt-5.2-codex, no fallback) |
-| Atlas | anthropic/claude-sonnet-4-5 | Master orchestrator (fallback: kimi-k2.5 → gpt-5.2) |
-| oracle | openai/gpt-5.2 | Consultation, debugging |
-| librarian | zai-coding-plan/glm-4.7 | Docs, GitHub search (fallback: glm-4.7-free) |
-| explore | xai/grok-code-fast-1 | Fast codebase grep (fallback: claude-haiku-4-5 → gpt-5-mini → gpt-5-nano) |
-| multimodal-looker | google/gemini-3-flash | PDF/image analysis |
-| Prometheus | anthropic/claude-opus-4-5 | Strategic planning (fallback: kimi-k2.5 → gpt-5.2) |
+| Agent | Model | Temp | Purpose |
+|-------|-------|------|---------|
+| Sisyphus | anthropic/claude-opus-4-6 | 0.1 | Primary orchestrator (fallback: kimi-k2.5 → glm-4.7 → gpt-5.3-codex → gemini-3-pro) |
+| Hephaestus | openai/gpt-5.3-codex | 0.1 | Autonomous deep worker (NO fallback) |
+| Atlas | anthropic/claude-sonnet-4-5 | 0.1 | Master orchestrator (fallback: kimi-k2.5 → gpt-5.2) |
+| Prometheus | anthropic/claude-opus-4-6 | 0.1 | Strategic planning (fallback: kimi-k2.5 → gpt-5.2) |
+| oracle | openai/gpt-5.2 | 0.1 | Consultation, debugging (fallback: claude-opus-4-6) |
+| librarian | zai-coding-plan/glm-4.7 | 0.1 | Docs, GitHub search (fallback: glm-4.7-free) |
+| explore | xai/grok-code-fast-1 | 0.1 | Fast codebase grep (fallback: claude-haiku-4-5 → gpt-5-mini → gpt-5-nano) |
+| multimodal-looker | google/gemini-3-flash | 0.1 | PDF/image analysis |
+| Metis | anthropic/claude-opus-4-6 | 0.3 | Pre-planning analysis (fallback: kimi-k2.5 → gpt-5.2) |
+| Momus | openai/gpt-5.2 | 0.1 | Plan validation (fallback: claude-opus-4-6) |
+| Sisyphus-Junior | anthropic/claude-sonnet-4-5 | 0.1 | Category-spawned executor |
+
+## OPENCODE PLUGIN API
+
+Plugin SDK from `@opencode-ai/plugin`. Plugin = `async (PluginInput) => Hooks`.
+
+| Hook | Purpose |
+|------|---------|
+| `tool` | Register custom tools (Record<string, ToolDefinition>) |
+| `chat.message` | Intercept user messages (can modify parts) |
+| `chat.params` | Modify LLM parameters (temperature, topP, options) |
+| `tool.execute.before` | Pre-tool interception (can modify args) |
+| `tool.execute.after` | Post-tool processing (can modify output) |
+| `event` | Session lifecycle events (session.created, session.stop, etc.) |
+| `config` | Config modification (register agents, MCPs, commands) |
+| `experimental.chat.messages.transform` | Transform message history |
+| `experimental.session.compacting` | Session compaction customization |
+
+## DEPENDENCIES
+
+| Package | Purpose |
+|---------|---------|
+| `@opencode-ai/plugin` + `sdk` | OpenCode integration SDK |
+| `@ast-grep/cli` + `napi` | AST pattern matching (search/replace) |
+| `@code-yeongyu/comment-checker` | AI comment detection/prevention |
+| `@modelcontextprotocol/sdk` | MCP client for remote HTTP servers |
+| `@clack/prompts` | Interactive CLI TUI |
+| `commander` | CLI argument parsing |
+| `zod` (v4) | Schema validation for config |
+| `jsonc-parser` | JSONC config with comments |
+| `picocolors` | Terminal colors |
+| `picomatch` | Glob pattern matching |
+| `vscode-jsonrpc` | LSP communication |
+| `js-yaml` | YAML parsing (tasks, skills) |
+| `detect-libc` | Platform binary selection |
 
 ## COMMANDS
 
@@ -219,7 +268,8 @@ oh-my-opencode/
 bun run typecheck      # Type check
 bun run build          # ESM + declarations + schema
 bun run rebuild        # Clean + Build
-bun test               # 100 test files
+bun test               # 176 test files
+bun run build:schema   # Regenerate JSON schema
 ```
 
 ## DEPLOYMENT
@@ -233,30 +283,38 @@ bun test               # 100 test files
 
 | File | Lines | Description |
 |------|-------|-------------|
-| `src/features/builtin-skills/skills.ts` | 1729 | Skill definitions |
-| `src/features/background-agent/manager.ts` | 1418 | Task lifecycle, concurrency |
-| `src/agents/prometheus-prompt.ts` | 1283 | Planning agent prompt |
-| `src/tools/delegate-task/tools.ts` | 1135 | Category-based delegation |
-| `src/hooks/atlas/index.ts` | 757 | Orchestrator hook |
-| `src/index.ts` | 788 | Main plugin entry |
-| `src/cli/config-manager.ts` | 667 | JSONC config parsing |
-| `src/features/builtin-commands/templates/refactor.ts` | 619 | Refactor command template |
+| `src/features/background-agent/manager.ts` | 1701 | Task lifecycle, concurrency |
+| `src/hooks/anthropic-context-window-limit-recovery/` | 2232 | Multi-strategy context recovery |
+| `src/hooks/claude-code-hooks/` | 2110 | Claude Code settings.json compat |
+| `src/hooks/todo-continuation-enforcer/` | 2061 | Core boulder mechanism |
+| `src/hooks/atlas/` | 1976 | Session orchestration |
+| `src/hooks/ralph-loop/` | 1687 | Self-referential dev loop |
+| `src/hooks/keyword-detector/` | 1665 | Mode detection (ultrawork/search) |
+| `src/hooks/rules-injector/` | 1604 | Conditional rules injection |
+| `src/hooks/think-mode/` | 1365 | Model/variant switching |
+| `src/hooks/session-recovery/` | 1279 | Auto error recovery |
+| `src/features/builtin-skills/skills/git-master.ts` | 1112 | Git master skill |
+| `src/tools/delegate-task/constants.ts` | 569 | Category routing configs |
 
 ## MCP ARCHITECTURE
 
 Three-tier system:
-1. **Built-in**: websearch (Exa), context7 (docs), grep_app (GitHub)
-2. **Claude Code compat**: .mcp.json with `${VAR}` expansion
-3. **Skill-embedded**: YAML frontmatter in skills
+1. **Built-in** (src/mcp/): websearch (Exa/Tavily), context7 (docs), grep_app (GitHub)
+2. **Claude Code compat** (features/claude-code-mcp-loader/): .mcp.json with `${VAR}` expansion
+3. **Skill-embedded** (features/opencode-skill-loader/): YAML frontmatter in SKILL.md
 
 ## CONFIG SYSTEM
 
-- **Zod validation**: `src/config/schema.ts`
+- **Zod validation**: 21 schema component files in `src/config/schema/`
 - **JSONC support**: Comments, trailing commas
-- **Multi-level**: Project (`.opencode/`) → User (`~/.config/opencode/`)
+- **Multi-level**: Project (`.opencode/`) → User (`~/.config/opencode/`) → Defaults
+- **Migration**: Legacy config auto-migration in `src/shared/migration/`
 
 ## NOTES
 
 - **OpenCode**: Requires >= 1.0.150
+- **1130 TypeScript files**, 176 test files, 127k+ lines
 - **Flaky tests**: ralph-loop (CI timeout), session-state (parallel pollution)
 - **Trusted deps**: @ast-grep/cli, @ast-grep/napi, @code-yeongyu/comment-checker
+- **No linter/formatter**: No ESLint, Prettier, or Biome configured
+- **License**: SUL-1.0 (Sisyphus Use License)

README.ja.md

@@ -121,16 +121,6 @@
   - [アンインストール](#アンインストール)
   - [機能](#機能)
   - [設定](#設定)
-    - [JSONC のサポート](#jsonc-のサポート)
-    - [Google Auth](#google-auth)
-    - [Agents](#agents)
-      - [Permission オプション](#permission-オプション)
-    - [Sisyphus Agent](#sisyphus-agent)
-    - [Background Tasks](#background-tasks)
-    - [Hooks](#hooks)
-    - [MCPs](#mcps)
-    - [LSP](#lsp)
-    - [Experimental](#experimental)
   - [作者のノート](#作者のノート)
   - [注意](#注意)
   - [こちらの企業の専門家にご愛用いただいています](#こちらの企業の専門家にご愛用いただいています)
@@ -380,6 +370,8 @@ OpenCode が Debian / ArchLinux だとしたら、Oh My OpenCode は Ubuntu / [O
   - Making Spray - influencer marketing solution, vovushop - crossborder commerce platform, vreview - ai commerce review marketing solution
 - [Google](https://google.com)
 - [Microsoft](https://microsoft.com)
+- [ELESTYLE](https://elestyle.jp)
+  - elepay - マルチモバイル決済ゲートウェイ、OneQR - キャッシュレスソリューション向けモバイルアプリケーションSaaS
 
 ## スポンサー
 - **Numman Ali** [GitHub](https://github.com/numman-ali) [X](https://x.com/nummanali)

README.ko.md

@@ -123,20 +123,6 @@
   - [제거](#제거)
    - [기능](#기능)
    - [구성](#구성)
-    - [JSONC 지원](#jsonc-지원)
-    - [Google 인증](#google-인증)
-    - [에이전트](#에이전트)
-      - [권한 옵션](#권한-옵션)
-    - [내장 스킬](#내장-스킬)
-    - [Git Master](#git-master)
-    - [Sisyphus 에이전트](#sisyphus-에이전트)
-    - [백그라운드 작업](#백그라운드-작업)
-    - [카테고리](#카테고리)
-    - [훅](#훅)
-    - [MCP](#mcp)
-    - [LSP](#lsp)
-    - [실험적 기능](#실험적-기능)
-    - [환경 변수](#환경-변수)
   - [작성자의 메모](#작성자의-메모)
   - [경고](#경고)
   - [다음 기업 전문가들이 사랑합니다](#다음-기업-전문가들이-사랑합니다)
@@ -393,5 +379,7 @@ OpenCode가 Debian/Arch라면 Oh My OpenCode는 Ubuntu/[Omarchy](https://omarchy
   - Spray(인플루언서 마케팅 솔루션), vovushop(국가 간 상거래 플랫폼), vreview(AI 상거래 리뷰 마케팅 솔루션) 제작
 - [Google](https://google.com)
 - [Microsoft](https://microsoft.com)
+- [ELESTYLE](https://elestyle.jp)
+  - elepay - 멀티 모바일 결제 게이트웨이, OneQR - 캐시리스 솔루션용 모바일 애플리케이션 SaaS
 
 *이 놀라운 히어로 이미지에 대해 [@junhoyeo](https://github.com/junhoyeo)에게 특별히 감사드립니다.*

README.md

@@ -121,21 +121,7 @@ Yes, technically possible. But I cannot recommend using it.
     - [For LLM Agents](#for-llm-agents)
   - [Uninstallation](#uninstallation)
   - [Features](#features)
-   - [Configuration](#configuration)
-    - [JSONC Support](#jsonc-support)
-    - [Google Auth](#google-auth)
-    - [Agents](#agents)
-      - [Permission Options](#permission-options)
-    - [Built-in Skills](#built-in-skills)
-    - [Git Master](#git-master)
-    - [Sisyphus Agent](#sisyphus-agent)
-    - [Background Tasks](#background-tasks)
-    - [Categories](#categories)
-    - [Hooks](#hooks)
-    - [MCPs](#mcps)
-    - [LSP](#lsp)
-    - [Experimental](#experimental)
-    - [Environment Variables](#environment-variables)
+  - [Configuration](#configuration)
   - [Author's Note](#authors-note)
   - [Warnings](#warnings)
   - [Loved by professionals at](#loved-by-professionals-at)
@@ -294,10 +280,10 @@ To remove oh-my-opencode:
 
    ```bash
    # Remove user config
-   rm -f ~/.config/opencode/oh-my-opencode.json
+   rm -f ~/.config/opencode/oh-my-opencode.json ~/.config/opencode/oh-my-opencode.jsonc
 
    # Remove project config (if exists)
-   rm -f .opencode/oh-my-opencode.json
+   rm -f .opencode/oh-my-opencode.json .opencode/oh-my-opencode.jsonc
    ```
 
 3. **Verify removal**
@@ -328,7 +314,7 @@ Highly opinionated, but adjustable to taste.
 See the full [Configuration Documentation](docs/configurations.md) for detailed information.
 
 **Quick Overview:**
-- **Config Locations**: `.opencode/oh-my-opencode.json` (project) or `~/.config/opencode/oh-my-opencode.json` (user)
+- **Config Locations**: `.opencode/oh-my-opencode.jsonc` or `.opencode/oh-my-opencode.json` (project), `~/.config/opencode/oh-my-opencode.jsonc` or `~/.config/opencode/oh-my-opencode.json` (user)
 - **JSONC Support**: Comments and trailing commas supported
 - **Agents**: Override models, temperatures, prompts, and permissions for any agent
 - **Built-in Skills**: `playwright` (browser automation), `git-master` (atomic commits)
@@ -392,5 +378,7 @@ I have no affiliation with any project or model mentioned here. This is purely p
   - Making Spray - influencer marketing solution, vovushop - crossborder commerce platform, vreview - ai commerce review marketing solution
 - [Google](https://google.com)
 - [Microsoft](https://microsoft.com)
+- [ELESTYLE](https://elestyle.jp)
+  - Making elepay - multi-mobile payment gateway, OneQR - mobile application SaaS for cashless solutions
 
 *Special thanks to [@junhoyeo](https://github.com/junhoyeo) for this amazing hero image.*

README.zh-cn.md

@@ -122,20 +122,6 @@
   - [卸载](#卸载)
   - [功能特性](#功能特性)
   - [配置](#配置)
-    - [JSONC 支持](#jsonc-支持)
-    - [Google 认证](#google-认证)
-    - [智能体](#智能体)
-      - [权限选项](#权限选项)
-    - [内置技能](#内置技能)
-    - [Git Master](#git-master)
-    - [Sisyphus 智能体](#sisyphus-智能体)
-    - [后台任务](#后台任务)
-    - [类别](#类别)
-    - [钩子](#钩子)
-    - [MCP](#mcp)
-    - [LSP](#lsp)
-    - [实验性功能](#实验性功能)
-    - [环境变量](#环境变量)
   - [作者札记](#作者札记)
   - [警告](#警告)
   - [受到以下专业人士的喜爱](#受到以下专业人士的喜爱)
@@ -390,6 +376,8 @@ curl -s https://raw.githubusercontent.com/code-yeongyu/oh-my-opencode/refs/heads
   - 制作 Spray - 网红营销解决方案、vovushop - 跨境电商平台、vreview - AI 电商评论营销解决方案
 - [Google](https://google.com)
 - [Microsoft](https://microsoft.com)
+- [ELESTYLE](https://elestyle.jp)
+  - elepay - 多渠道移动支付网关、OneQR - 无现金解决方案移动应用 SaaS
 
 ## 赞助商
 - **Numman Ali** [GitHub](https://github.com/numman-ali) [X](https://x.com/nummanali)

bun.lock

@@ -1,6 +1,6 @@
 {
   "lockfileVersion": 1,
-  "configVersion": 1,
+  "configVersion": 0,
   "workspaces": {
     "": {
       "name": "oh-my-opencode",
@@ -28,13 +28,13 @@
         "typescript": "^5.7.3",
       },
       "optionalDependencies": {
-        "oh-my-opencode-darwin-arm64": "3.2.1",
-        "oh-my-opencode-darwin-x64": "3.2.1",
-        "oh-my-opencode-linux-arm64": "3.2.1",
-        "oh-my-opencode-linux-arm64-musl": "3.2.1",
-        "oh-my-opencode-linux-x64": "3.2.1",
-        "oh-my-opencode-linux-x64-musl": "3.2.1",
-        "oh-my-opencode-windows-x64": "3.2.1",
+        "oh-my-opencode-darwin-arm64": "3.6.0",
+        "oh-my-opencode-darwin-x64": "3.6.0",
+        "oh-my-opencode-linux-arm64": "3.6.0",
+        "oh-my-opencode-linux-arm64-musl": "3.6.0",
+        "oh-my-opencode-linux-x64": "3.6.0",
+        "oh-my-opencode-linux-x64-musl": "3.6.0",
+        "oh-my-opencode-windows-x64": "3.6.0",
       },
     },
   },
@@ -44,41 +44,41 @@
     "@code-yeongyu/comment-checker",
   ],
   "packages": {
-    "@ast-grep/cli": ["@ast-grep/cli@0.40.5", "", { "dependencies": { "detect-libc": "2.1.2" }, "optionalDependencies": { "@ast-grep/cli-darwin-arm64": "0.40.5", "@ast-grep/cli-darwin-x64": "0.40.5", "@ast-grep/cli-linux-arm64-gnu": "0.40.5", "@ast-grep/cli-linux-x64-gnu": "0.40.5", "@ast-grep/cli-win32-arm64-msvc": "0.40.5", "@ast-grep/cli-win32-ia32-msvc": "0.40.5", "@ast-grep/cli-win32-x64-msvc": "0.40.5" }, "bin": { "sg": "sg", "ast-grep": "ast-grep" } }, "sha512-yVXL7Gz0WIHerQLf+MVaVSkhIhidtWReG5akNVr/JS9OVCVkSdz7gWm7H8jVv2M9OO1tauuG76K3UaRGBPu5lQ=="],
+    "@ast-grep/cli": ["@ast-grep/cli@0.40.0", "", { "dependencies": { "detect-libc": "2.1.2" }, "optionalDependencies": { "@ast-grep/cli-darwin-arm64": "0.40.0", "@ast-grep/cli-darwin-x64": "0.40.0", "@ast-grep/cli-linux-arm64-gnu": "0.40.0", "@ast-grep/cli-linux-x64-gnu": "0.40.0", "@ast-grep/cli-win32-arm64-msvc": "0.40.0", "@ast-grep/cli-win32-ia32-msvc": "0.40.0", "@ast-grep/cli-win32-x64-msvc": "0.40.0" }, "bin": { "sg": "sg", "ast-grep": "ast-grep" } }, "sha512-L8AkflsfI2ZP70yIdrwqvjR02ScCuRmM/qNGnJWUkOFck+e6gafNVJ4e4jjGQlEul+dNdBpx36+O2Op629t47A=="],
 
-    "@ast-grep/cli-darwin-arm64": ["@ast-grep/cli-darwin-arm64@0.40.5", "", { "os": "darwin", "cpu": "arm64" }, "sha512-T9CzwJ1GqQhnANdsu6c7iT1akpvTVMK+AZrxnhIPv33Ze5hrXUUkqan+j4wUAukRJDqU7u94EhXLSLD+5tcJ8g=="],
+    "@ast-grep/cli-darwin-arm64": ["@ast-grep/cli-darwin-arm64@0.40.0", "", { "os": "darwin", "cpu": "arm64" }, "sha512-UehY2MMUkdJbsriP7NKc6+uojrqPn7d1Cl0em+WAkee7Eij81VdyIjRsRxtZSLh440ZWQBHI3PALZ9RkOO8pKQ=="],
 
-    "@ast-grep/cli-darwin-x64": ["@ast-grep/cli-darwin-x64@0.40.5", "", { "os": "darwin", "cpu": "x64" }, "sha512-ez9b2zKvXU8f4ghhjlqYvbx6tWCKJTuVlNVqDDfjqwwhGeiTYfnzMlSVat4ElYRMd21gLtXZIMy055v2f21Ztg=="],
+    "@ast-grep/cli-darwin-x64": ["@ast-grep/cli-darwin-x64@0.40.0", "", { "os": "darwin", "cpu": "x64" }, "sha512-RFDJ2ZxUbT0+grntNlOLJx7wa9/ciVCeaVtQpQy8WJJTvXvkY0etl8Qlh2TmO2x2yr+i0Z6aMJi4IG/Yx5ghTQ=="],
 
-    "@ast-grep/cli-linux-arm64-gnu": ["@ast-grep/cli-linux-arm64-gnu@0.40.5", "", { "os": "linux", "cpu": "arm64" }, "sha512-VXa2L1IEYD66AMb0GuG7VlMMbPmEGoJUySWDcwSZo/D9neiry3MJ41LQR5oTG2HyhIPBsf9umrXnmuRq66BviA=="],
+    "@ast-grep/cli-linux-arm64-gnu": ["@ast-grep/cli-linux-arm64-gnu@0.40.0", "", { "os": "linux", "cpu": "arm64" }, "sha512-4p55gnTQ1mMFCyqjtM7bH9SB9r16mkwXtUcJQGX1YgFG4WD+QG8rC4GwSuNNZcdlYaOQuTWrgUEQ9z5K06UXfg=="],
 
-    "@ast-grep/cli-linux-x64-gnu": ["@ast-grep/cli-linux-x64-gnu@0.40.5", "", { "os": "linux", "cpu": "x64" }, "sha512-GQC5162eIOWXR2eQQ6Knzg7/8Trp5E1ODJkaErf0IubdQrZBGqj5AAcQPcWgPbbnmktjIp0H4NraPpOJ9eJ22A=="],
+    "@ast-grep/cli-linux-x64-gnu": ["@ast-grep/cli-linux-x64-gnu@0.40.0", "", { "os": "linux", "cpu": "x64" }, "sha512-u2MXFceuwvrO+OQ6zFGoJ6wbATXn46HWwW79j4UPrXYJzVl97jRyjJOIQTJOzTflsk02fjP98DQkfvbXt2dl3Q=="],
 
-    "@ast-grep/cli-win32-arm64-msvc": ["@ast-grep/cli-win32-arm64-msvc@0.40.5", "", { "os": "win32", "cpu": "arm64" }, "sha512-YiZdnQZsSlXQTMsZJop/Ux9MmUGfuRvC2x/UbFgrt5OBSYxND+yoiMc0WcA3WG+wU+tt4ZkB5HUea3r/IkOLYA=="],
+    "@ast-grep/cli-win32-arm64-msvc": ["@ast-grep/cli-win32-arm64-msvc@0.40.0", "", { "os": "win32", "cpu": "arm64" }, "sha512-E/I1xpF/RQL2fo1CQsQfTxyDLnChsbZ+ERrQHKuF1FI4WrkaPOBibpqda60QgVmUcgOGZyZ/GRb3iKEVWPsQNQ=="],
 
-    "@ast-grep/cli-win32-ia32-msvc": ["@ast-grep/cli-win32-ia32-msvc@0.40.5", "", { "os": "win32", "cpu": "ia32" }, "sha512-MHkCxCITVTr8sY9CcVqNKbfUzMa3Hc6IilGXad0Clnw2vNmPfWqSky+hU/UTerr5YHWwWfAVURH7ANZgirtx0Q=="],
+    "@ast-grep/cli-win32-ia32-msvc": ["@ast-grep/cli-win32-ia32-msvc@0.40.0", "", { "os": "win32", "cpu": "ia32" }, "sha512-9h12OQu1BR0GxHEtT+Z4QkJk3LLWLiKwjBkjXUGlASHYDPTyLcs85KwDLeFHs4BwarF8TDdF+KySvB9WPGl/nQ=="],
 
-    "@ast-grep/cli-win32-x64-msvc": ["@ast-grep/cli-win32-x64-msvc@0.40.5", "", { "os": "win32", "cpu": "x64" }, "sha512-/MJ5un7yxlClaaxou9eYl+Kr2xr/yTtYtTq5aLBWjPWA6dmmJ1nAJgx5zKHVuplFXFBrFDQk3paEgAETMTGcrA=="],
+    "@ast-grep/cli-win32-x64-msvc": ["@ast-grep/cli-win32-x64-msvc@0.40.0", "", { "os": "win32", "cpu": "x64" }, "sha512-n2+3WynEWFHhXg6KDgjwWQ0UEtIvqUITFbKEk5cDkUYrzYhg/A6kj0qauPwRbVMoJms49vtsNpLkzzqyunio5g=="],
 
-    "@ast-grep/napi": ["@ast-grep/napi@0.40.5", "", { "optionalDependencies": { "@ast-grep/napi-darwin-arm64": "0.40.5", "@ast-grep/napi-darwin-x64": "0.40.5", "@ast-grep/napi-linux-arm64-gnu": "0.40.5", "@ast-grep/napi-linux-arm64-musl": "0.40.5", "@ast-grep/napi-linux-x64-gnu": "0.40.5", "@ast-grep/napi-linux-x64-musl": "0.40.5", "@ast-grep/napi-win32-arm64-msvc": "0.40.5", "@ast-grep/napi-win32-ia32-msvc": "0.40.5", "@ast-grep/napi-win32-x64-msvc": "0.40.5" } }, "sha512-hJA62OeBKUQT68DD2gDyhOqJxZxycqg8wLxbqjgqSzYttCMSDL9tiAQ9abgekBYNHudbJosm9sWOEbmCDfpX2A=="],
+    "@ast-grep/napi": ["@ast-grep/napi@0.40.0", "", { "optionalDependencies": { "@ast-grep/napi-darwin-arm64": "0.40.0", "@ast-grep/napi-darwin-x64": "0.40.0", "@ast-grep/napi-linux-arm64-gnu": "0.40.0", "@ast-grep/napi-linux-arm64-musl": "0.40.0", "@ast-grep/napi-linux-x64-gnu": "0.40.0", "@ast-grep/napi-linux-x64-musl": "0.40.0", "@ast-grep/napi-win32-arm64-msvc": "0.40.0", "@ast-grep/napi-win32-ia32-msvc": "0.40.0", "@ast-grep/napi-win32-x64-msvc": "0.40.0" } }, "sha512-tq6nO/8KwUF/mHuk1ECaAOSOlz2OB/PmygnvprJzyAHGRVzdcffblaOOWe90M9sGz5MAasXoF+PTcayQj9TKKA=="],
 
-    "@ast-grep/napi-darwin-arm64": ["@ast-grep/napi-darwin-arm64@0.40.5", "", { "os": "darwin", "cpu": "arm64" }, "sha512-2F072fGN0WTq7KI3okuEnkGJVEHLbi56Bw1H6NAMf7j2mJJeQWsRyGOMcyNnUXZDeNdvoMH0OB2a5wwUegY/nQ=="],
+    "@ast-grep/napi-darwin-arm64": ["@ast-grep/napi-darwin-arm64@0.40.0", "", { "os": "darwin", "cpu": "arm64" }, "sha512-ZMjl5yLhKjxdwbqEEdMizgQdWH2NrWsM6Px+JuGErgCDe6Aedq9yurEPV7veybGdLVJQhOah6htlSflXxjHnYA=="],
 
-    "@ast-grep/napi-darwin-x64": ["@ast-grep/napi-darwin-x64@0.40.5", "", { "os": "darwin", "cpu": "x64" }, "sha512-dJMidHZhhxuLBYNi6/FKI812jQ7wcFPSKkVPwviez2D+KvYagapUMAV/4dJ7FCORfguVk8Y0jpPAlYmWRT5nvA=="],
+    "@ast-grep/napi-darwin-x64": ["@ast-grep/napi-darwin-x64@0.40.0", "", { "os": "darwin", "cpu": "x64" }, "sha512-f9Ol5oQKNRMBkvDtzBK1WiNn2/3eejF2Pn9xwTj7PhXuSFseedOspPYllxQo0gbwUlw/DJqGFTce/jarhR/rBw=="],
 
-    "@ast-grep/napi-linux-arm64-gnu": ["@ast-grep/napi-linux-arm64-gnu@0.40.5", "", { "os": "linux", "cpu": "arm64" }, "sha512-nBRCbyoS87uqkaw4Oyfe5VO+SRm2B+0g0T8ME69Qry9ShMf41a2bTdpcQx9e8scZPogq+CTwDHo3THyBV71l9w=="],
+    "@ast-grep/napi-linux-arm64-gnu": ["@ast-grep/napi-linux-arm64-gnu@0.40.0", "", { "os": "linux", "cpu": "arm64" }, "sha512-+tO+VW5GDhT9jGkKOK+3b8+ohKjC98WTzn7wSskd/myyhK3oYL1WTKqCm07WSYBZOJvb3z+WaX+wOUrc4bvtyQ=="],
 
-    "@ast-grep/napi-linux-arm64-musl": ["@ast-grep/napi-linux-arm64-musl@0.40.5", "", { "os": "linux", "cpu": "arm64" }, "sha512-/qKsmds5FMoaEj6FdNzepbmLMtlFuBLdrAn9GIWCqOIcVcYvM1Nka8+mncfeXB/MFZKOrzQsQdPTWqrrQzXLrA=="],
+    "@ast-grep/napi-linux-arm64-musl": ["@ast-grep/napi-linux-arm64-musl@0.40.0", "", { "os": "linux", "cpu": "arm64" }, "sha512-MS9qalLRjUnF2PCzuTKTvCMVSORYHxxe3Qa0+SSaVULsXRBmuy5C/b1FeWwMFnwNnC0uie3VDet31Zujwi8q6A=="],
 
-    "@ast-grep/napi-linux-x64-gnu": ["@ast-grep/napi-linux-x64-gnu@0.40.5", "", { "os": "linux", "cpu": "x64" }, "sha512-DP4oDbq7f/1A2hRTFLhJfDFR6aI5mRWdEfKfHzRItmlKsR9WlcEl1qDJs/zX9R2EEtIDsSKRzuJNfJllY3/W8Q=="],
+    "@ast-grep/napi-linux-x64-gnu": ["@ast-grep/napi-linux-x64-gnu@0.40.0", "", { "os": "linux", "cpu": "x64" }, "sha512-BeHZVMNXhM3WV3XE2yghO0fRxhMOt8BTN972p5piYEQUvKeSHmS8oeGcs6Ahgx5znBclqqqq37ZfioYANiTqJA=="],
 
-    "@ast-grep/napi-linux-x64-musl": ["@ast-grep/napi-linux-x64-musl@0.40.5", "", { "os": "linux", "cpu": "x64" }, "sha512-BRZUvVBPUNpWPo6Ns8chXVzxHPY+k9gpsubGTHy92Q26ecZULd/dTkWWdnvfhRqttsSQ9Pe/XQdi5+hDQ6RYcg=="],
+    "@ast-grep/napi-linux-x64-musl": ["@ast-grep/napi-linux-x64-musl@0.40.0", "", { "os": "linux", "cpu": "x64" }, "sha512-rG1YujF7O+lszX8fd5u6qkFTuv4FwHXjWvt1CCvCxXwQLSY96LaCW88oVKg7WoEYQh54y++Fk57F+Wh9Gv9nVQ=="],
 
-    "@ast-grep/napi-win32-arm64-msvc": ["@ast-grep/napi-win32-arm64-msvc@0.40.5", "", { "os": "win32", "cpu": "arm64" }, "sha512-y95zSEwc7vhxmcrcH0GnK4ZHEBQrmrszRBNQovzaciF9GUqEcCACNLoBesn4V47IaOp4fYgD2/EhGRTIBFb2Ug=="],
+    "@ast-grep/napi-win32-arm64-msvc": ["@ast-grep/napi-win32-arm64-msvc@0.40.0", "", { "os": "win32", "cpu": "arm64" }, "sha512-9SqmnQqd4zTEUk6yx0TuW2ycZZs2+e569O/R0QnhSiQNpgwiJCYOe/yPS0BC9HkiaozQm6jjAcasWpFtz/dp+w=="],
 
-    "@ast-grep/napi-win32-ia32-msvc": ["@ast-grep/napi-win32-ia32-msvc@0.40.5", "", { "os": "win32", "cpu": "ia32" }, "sha512-K/u8De62iUnFCzVUs7FBdTZ2Jrgc5/DLHqjpup66KxZ7GIM9/HGME/O8aSoPkpcAeCD4TiTZ11C1i5p5H98hTg=="],
+    "@ast-grep/napi-win32-ia32-msvc": ["@ast-grep/napi-win32-ia32-msvc@0.40.0", "", { "os": "win32", "cpu": "ia32" }, "sha512-0JkdBZi5l9vZhGEO38A1way0LmLRDU5Vos6MXrLIOVkymmzDTDlCdY394J1LMmmsfwWcyJg6J7Yv2dw41MCxDQ=="],
 
-    "@ast-grep/napi-win32-x64-msvc": ["@ast-grep/napi-win32-x64-msvc@0.40.5", "", { "os": "win32", "cpu": "x64" }, "sha512-dqm5zg/o4Nh4VOQPEpMS23ot8HVd22gG0eg01t4CFcZeuzyuSgBlOL3N7xLbz3iH2sVkk7keuBwAzOIpTqziNQ=="],
+    "@ast-grep/napi-win32-x64-msvc": ["@ast-grep/napi-win32-x64-msvc@0.40.0", "", { "os": "win32", "cpu": "x64" }, "sha512-Hk2IwfPqMFGZt5SRxsoWmGLxBXxprow4LRp1eG6V8EEiJCNHxZ9ZiEaIc5bNvMDBjHVSnqZAXT22dROhrcSKQg=="],
 
     "@clack/core": ["@clack/core@0.5.0", "", { "dependencies": { "picocolors": "^1.0.0", "sisteransi": "^1.0.5" } }, "sha512-p3y0FIOwaYRUPRcMO7+dlmLh8PSRcrjuTndsiA0WAFbWES0mLZlrjVoBRZ9DzkPFJZG6KGkJmoEAY0ZcVWTkow=="],
 
@@ -86,17 +86,17 @@
 
     "@code-yeongyu/comment-checker": ["@code-yeongyu/comment-checker@0.6.1", "", { "os": [ "linux", "win32", "darwin", ], "cpu": [ "x64", "arm64", ], "bin": { "comment-checker": "bin/comment-checker" } }, "sha512-BBremX+Y5aW8sTzlhHrLsKParupYkPOVUYmq9STrlWvBvfAme6w5IWuZCLl6nHIQScRDdvGdrAjPycJC86EZFA=="],
 
-    "@hono/node-server": ["@hono/node-server@1.19.9", "", { "peerDependencies": { "hono": "^4" } }, "sha512-vHL6w3ecZsky+8P5MD+eFfaGTyCeOHUIFYMGpQGbrBTSmNNoxv0if69rEZ5giu36weC5saFuznL411gRX7bJDw=="],
+    "@hono/node-server": ["@hono/node-server@1.19.7", "", { "peerDependencies": { "hono": "^4" } }, "sha512-vUcD0uauS7EU2caukW8z5lJKtoGMokxNbJtBiwHgpqxEXokaHCBkQUmCHhjFB1VUTWdqj25QoMkMKzgjq+uhrw=="],
 
-    "@modelcontextprotocol/sdk": ["@modelcontextprotocol/sdk@1.25.3", "", { "dependencies": { "@hono/node-server": "^1.19.9", "ajv": "^8.17.1", "ajv-formats": "^3.0.1", "content-type": "^1.0.5", "cors": "^2.8.5", "cross-spawn": "^7.0.5", "eventsource": "^3.0.2", "eventsource-parser": "^3.0.0", "express": "^5.0.1", "express-rate-limit": "^7.5.0", "jose": "^6.1.1", "json-schema-typed": "^8.0.2", "pkce-challenge": "^5.0.0", "raw-body": "^3.0.0", "zod": "^3.25 || ^4.0", "zod-to-json-schema": "^3.25.0" }, "peerDependencies": { "@cfworker/json-schema": "^4.1.1" }, "optionalPeers": ["@cfworker/json-schema"] }, "sha512-vsAMBMERybvYgKbg/l4L1rhS7VXV1c0CtyJg72vwxONVX0l4ZfKVAnZEWTQixJGTzKnELjQ59e4NbdFDALRiAQ=="],
+    "@modelcontextprotocol/sdk": ["@modelcontextprotocol/sdk@1.25.1", "", { "dependencies": { "@hono/node-server": "^1.19.7", "ajv": "^8.17.1", "ajv-formats": "^3.0.1", "content-type": "^1.0.5", "cors": "^2.8.5", "cross-spawn": "^7.0.5", "eventsource": "^3.0.2", "eventsource-parser": "^3.0.0", "express": "^5.0.1", "express-rate-limit": "^7.5.0", "jose": "^6.1.1", "json-schema-typed": "^8.0.2", "pkce-challenge": "^5.0.0", "raw-body": "^3.0.0", "zod": "^3.25 || ^4.0", "zod-to-json-schema": "^3.25.0" }, "peerDependencies": { "@cfworker/json-schema": "^4.1.1" }, "optionalPeers": ["@cfworker/json-schema"] }, "sha512-yO28oVFFC7EBoiKdAn+VqRm+plcfv4v0xp6osG/VsCB0NlPZWi87ajbCZZ8f/RvOFLEu7//rSRmuZZ7lMoe3gQ=="],
 
-    "@opencode-ai/plugin": ["@opencode-ai/plugin@1.1.47", "", { "dependencies": { "@opencode-ai/sdk": "1.1.47", "zod": "4.1.8" } }, "sha512-gNMPz72altieDfLhUw3VAT1xbduKi3w3wZ57GLeS7qU9W474HdvdIiLBnt2Xq3U7Ko0/0tvK3nzCker6IIDqmQ=="],
+    "@opencode-ai/plugin": ["@opencode-ai/plugin@1.1.19", "", { "dependencies": { "@opencode-ai/sdk": "1.1.19", "zod": "4.1.8" } }, "sha512-Q6qBEjHb/dJMEw4BUqQxEswTMxCCHUpFMMb6jR8HTTs8X/28XRkKt5pHNPA82GU65IlSoPRph+zd8LReBDN53Q=="],
 
-    "@opencode-ai/sdk": ["@opencode-ai/sdk@1.1.47", "", {}, "sha512-s3PBHwk1sP6Zt/lJxIWSBWZ1TnrI1nFxSP97LCODUytouAQgbygZ1oDH7O2sGMBEuGdA8B1nNSPla0aRSN3IpA=="],
+    "@opencode-ai/sdk": ["@opencode-ai/sdk@1.1.19", "", {}, "sha512-XhZhFuvlLCqDpvNtUEjOsi/wvFj3YCXb1dySp+OONQRMuHlorNYnNa7P2A2ntKuhRdGT1Xt5na0nFzlUyNw+4A=="],
 
     "@types/js-yaml": ["@types/js-yaml@4.0.9", "", {}, "sha512-k4MGaQl5TGo/iipqb2UDG2UwjXziSWkh0uysQelTlJpX1qGlpUZYm8PnO4DxG1qBomtJUdYJ6qR6xdIah10JLg=="],
 
-    "@types/node": ["@types/node@25.1.0", "", { "dependencies": { "undici-types": "~7.16.0" } }, "sha512-t7frlewr6+cbx+9Ohpl0NOTKXZNV9xHRmNOvql47BFJKcEG1CxtxlPEEe+gR9uhVWM4DwhnvTF110mIL4yP9RA=="],
+    "@types/node": ["@types/node@24.10.1", "", { "dependencies": { "undici-types": "~7.16.0" } }, "sha512-GNWcUTRBgIRJD5zj+Tq0fKOJ5XZajIiBroOF0yvj2bSU1WvNdYS/dn9UxwsujGW4JX06dnHyjV2y9rRaybH0iQ=="],
 
     "@types/picomatch": ["@types/picomatch@3.0.2", "", {}, "sha512-n0i8TD3UDB7paoMMxA3Y65vUncFJXjcUf7lQY7YyKGl6031FNjfsLs6pdLFCy2GNFxItPJG8GvvpbZc2skH7WA=="],
 
@@ -108,7 +108,7 @@
 
     "argparse": ["argparse@2.0.1", "", {}, "sha512-8+9WqebbFzpX9OR+Wa6O29asIogeRMzcGtAINdpMHHyAg10f05aSFVBbcEqGf/PXw1EjAZ+q2/bEBg3DvurK3Q=="],
 
-    "body-parser": ["body-parser@2.2.2", "", { "dependencies": { "bytes": "^3.1.2", "content-type": "^1.0.5", "debug": "^4.4.3", "http-errors": "^2.0.0", "iconv-lite": "^0.7.0", "on-finished": "^2.4.1", "qs": "^6.14.1", "raw-body": "^3.0.1", "type-is": "^2.0.1" } }, "sha512-oP5VkATKlNwcgvxi0vM0p/D3n2C3EReYVX+DNYs5TjZFn/oQt2j+4sVJtSMr18pdRr8wjTcBl6LoV+FUwzPmNA=="],
+    "body-parser": ["body-parser@2.2.1", "", { "dependencies": { "bytes": "^3.1.2", "content-type": "^1.0.5", "debug": "^4.4.3", "http-errors": "^2.0.0", "iconv-lite": "^0.7.0", "on-finished": "^2.4.1", "qs": "^6.14.0", "raw-body": "^3.0.1", "type-is": "^2.0.1" } }, "sha512-nfDwkulwiZYQIGwxdy0RUmowMhKcFVcYXUU7m4QlKYim1rUtg83xm2yjZ40QjDuc291AJjjeSc9b++AWHSgSHw=="],
 
     "bun-types": ["bun-types@1.3.6", "", { "dependencies": { "@types/node": "*" } }, "sha512-OlFwHcnNV99r//9v5IIOgQ9Uk37gZqrNMCcqEaExdkVq3Avwqok1bJFmvGMCkCE0FqzdY8VMOZpfpR3lwI+CsQ=="],
 
@@ -118,7 +118,7 @@
 
     "call-bound": ["call-bound@1.0.4", "", { "dependencies": { "call-bind-apply-helpers": "^1.0.2", "get-intrinsic": "^1.3.0" } }, "sha512-+ys997U96po4Kx/ABpBCqhA9EuxJaQWDQg7295H4hBphv3IZg0boBKuwYpt4YXp6MZ5AmZQnU/tyMTlRpaSejg=="],
 
-    "commander": ["commander@14.0.3", "", {}, "sha512-H+y0Jo/T1RZ9qPP4Eh1pkcQcLRglraJaSLoyOtHxu6AapkjWVCy2Sit1QQ4x3Dng8qDlSsZEet7g5Pq06MvTgw=="],
+    "commander": ["commander@14.0.2", "", {}, "sha512-TywoWNNRbhoD0BXs1P3ZEScW8W5iKrnbithIl0YH+uCmBd0QpPOA8yc82DS3BIE5Ma6FnBVUsJ7wVUDz4dvOWQ=="],
 
     "content-disposition": ["content-disposition@1.0.1", "", {}, "sha512-oIXISMynqSqm241k6kcQ5UwttDILMK4BiurCfGEREw6+X9jkkpEe5T9FZaApyLGGOnFuyMWZpdolTXMtvEJ08Q=="],
 
@@ -128,7 +128,7 @@
 
     "cookie-signature": ["cookie-signature@1.2.2", "", {}, "sha512-D76uU73ulSXrD1UXF4KE2TMxVVwhsnCgfAyTg9k8P6KGZjlXKrOLe4dJQKI3Bxi5wjesZoFXJWElNWBjPZMbhg=="],
 
-    "cors": ["cors@2.8.6", "", { "dependencies": { "object-assign": "^4", "vary": "^1" } }, "sha512-tJtZBBHA6vjIAaF6EnIaq6laBBP9aq/Y3ouVJjEfoHbRBcHBAHYcMh/w8LDrk2PvIMMq8gmopa5D4V8RmbrxGw=="],
+    "cors": ["cors@2.8.5", "", { "dependencies": { "object-assign": "^4", "vary": "^1" } }, "sha512-KIHbLJqu73RGr/hnbrO9uBeixNGuvSQjul/jdFvS/KFSIH1hWVd1ng7zOHx+YrEfInLG7q4n6GHQ9cDtxv/P6g=="],
 
     "cross-spawn": ["cross-spawn@7.0.6", "", { "dependencies": { "path-key": "^3.1.0", "shebang-command": "^2.0.0", "which": "^2.0.1" } }, "sha512-uV2QOWP2nWzsy2aMp8aRibhi9dlzF5Hgh5SHaB9OiTGEyDTiJJyx0uy51QXdyWbtAHNua4XJzUKca3OzKUd3vA=="],
 
@@ -184,11 +184,11 @@
 
     "hasown": ["hasown@2.0.2", "", { "dependencies": { "function-bind": "^1.1.2" } }, "sha512-0hJU9SCPvmMzIBdZFqNPXWa6dqh7WdH0cII9y+CyS8rG3nL48Bclra9HmKhVVUHyPWNH5Y7xDwAB7bfgSjkUMQ=="],
 
-    "hono": ["hono@4.11.7", "", {}, "sha512-l7qMiNee7t82bH3SeyUCt9UF15EVmaBvsppY2zQtrbIhl/yzBTny+YUxsVjSjQ6gaqaeVtZmGocom8TzBlA4Yw=="],
+    "hono": ["hono@4.10.8", "", {}, "sha512-DDT0A0r6wzhe8zCGoYOmMeuGu3dyTAE40HHjwUsWFTEy5WxK1x2WDSsBPlEXgPbRIFY6miDualuUDbasPogIww=="],
 
     "http-errors": ["http-errors@2.0.1", "", { "dependencies": { "depd": "~2.0.0", "inherits": "~2.0.4", "setprototypeof": "~1.2.0", "statuses": "~2.0.2", "toidentifier": "~1.0.1" } }, "sha512-4FbRdAX+bSdmo4AUFuS0WNiPz8NgFt+r8ThgNWmlrjQjt1Q7ZR9+zTlce2859x4KSXrwIsaeTqDoKQmtP8pLmQ=="],
 
-    "iconv-lite": ["iconv-lite@0.7.2", "", { "dependencies": { "safer-buffer": ">= 2.1.2 < 3.0.0" } }, "sha512-im9DjEDQ55s9fL4EYzOAv0yMqmMBSZp6G0VvFyTMPKWxiSBHUj9NW/qqLmXUwXrrM7AvqSlTCfvqRb0cM8yYqw=="],
+    "iconv-lite": ["iconv-lite@0.7.1", "", { "dependencies": { "safer-buffer": ">= 2.1.2 < 3.0.0" } }, "sha512-2Tth85cXwGFHfvRgZWszZSvdo+0Xsqmw8k8ZwxScfcBneNUraK+dxRxRm24nszx80Y0TVio8kKLt5sLE7ZCLlw=="],
 
     "inherits": ["inherits@2.0.4", "", {}, "sha512-k/vGaX4/Yla3WzyMCvTQOXYeIHvqOKtnqBduzTHpzpQZzAskKMhZ2K+EnBiSM9zGSoIFeMpXKxa4dYeZIQqewQ=="],
 
@@ -226,19 +226,19 @@
 
     "object-inspect": ["object-inspect@1.13.4", "", {}, "sha512-W67iLl4J2EXEGTbfeHCffrjDfitvLANg0UlX3wFUUSTx92KXRFegMHUVgSqE+wvhAbi4WqjGg9czysTV2Epbew=="],
 
-    "oh-my-opencode-darwin-arm64": ["oh-my-opencode-darwin-arm64@3.2.1", "", { "os": "darwin", "cpu": "arm64", "bin": { "oh-my-opencode": "bin/oh-my-opencode" } }, "sha512-IvhHRUXTr/g/hJlkKTU2oCdgRl2BDl/Qre31Rukhs4NumlvME6iDmdnm8mM7bTxugfCBkfUUr7QJLxxLhzjdLA=="],
+    "oh-my-opencode-darwin-arm64": ["oh-my-opencode-darwin-arm64@3.6.0", "", { "os": "darwin", "cpu": "arm64", "bin": { "oh-my-opencode": "bin/oh-my-opencode" } }, "sha512-JkyJC3b9ueRgSyPJMjTKlBO99gIyTpI87lEV5Tk7CBv6TFbj2ZFxfaA8mEm138NbwmYa/Z4Rf7I5tZyp2as93A=="],
 
-    "oh-my-opencode-darwin-x64": ["oh-my-opencode-darwin-x64@3.2.1", "", { "os": "darwin", "cpu": "x64", "bin": { "oh-my-opencode": "bin/oh-my-opencode" } }, "sha512-V2JbAdThAVfhBOcb+wBPZrAI0vBxPPRBdvmAixAxBOFC49CIJUrEFIRBUYFKhSQGHYWrNy8z0zJYoNQm4oQPog=="],
+    "oh-my-opencode-darwin-x64": ["oh-my-opencode-darwin-x64@3.6.0", "", { "os": "darwin", "cpu": "x64", "bin": { "oh-my-opencode": "bin/oh-my-opencode" } }, "sha512-5HsXz3F42T6CmPk6IW+pErJVSmPnqc3Gc1OntoKp/b4FwuWkFJh9kftDSH3cnKTX98H6XBqnwZoFKCNCiiVLEA=="],
 
-    "oh-my-opencode-linux-arm64": ["oh-my-opencode-linux-arm64@3.2.1", "", { "os": "linux", "cpu": "arm64", "bin": { "oh-my-opencode": "bin/oh-my-opencode" } }, "sha512-SeT8P7Icq5YH/AIaEF28J4q+ifUnOqO2UgMFtdFusr8JLadYFy+6dTdeAuD2uGGToDQ3ZNKuaG+lo84KzEhA5w=="],
+    "oh-my-opencode-linux-arm64": ["oh-my-opencode-linux-arm64@3.6.0", "", { "os": "linux", "cpu": "arm64", "bin": { "oh-my-opencode": "bin/oh-my-opencode" } }, "sha512-KjCSC2i9XdjzGsX6coP9xwj7naxTpdqnB53TiLbVH+KeF0X0dNsVV7PHbme3I1orjjzYoEbVYVC3ZNaleubzog=="],
 
-    "oh-my-opencode-linux-arm64-musl": ["oh-my-opencode-linux-arm64-musl@3.2.1", "", { "os": "linux", "cpu": "arm64", "bin": { "oh-my-opencode": "bin/oh-my-opencode" } }, "sha512-wJUEVVUn1gyVIFNV4mxWg9cYo1rQdTKUXdGLfiqPiyQhWhZLRfPJ+9qpghvIVv7Dne6rzkbhYWdwdk/tew5RtQ=="],
+    "oh-my-opencode-linux-arm64-musl": ["oh-my-opencode-linux-arm64-musl@3.6.0", "", { "os": "linux", "cpu": "arm64", "bin": { "oh-my-opencode": "bin/oh-my-opencode" } }, "sha512-EARvFQXnkqSnwPpKtghmoV5e/JmweJXhjcOrRNvEwQ8HSb4FIhdRmJkTw4Z/EzyoIRTQcY019ALOiBbdIiOUEA=="],
 
-    "oh-my-opencode-linux-x64": ["oh-my-opencode-linux-x64@3.2.1", "", { "os": "linux", "cpu": "x64", "bin": { "oh-my-opencode": "bin/oh-my-opencode" } }, "sha512-p/XValXi1RRTZV8mEsdStXwZBkyQpgZjB41HLf0VfizPMAKRr6/bhuFZ9BDZFIhcDnLYcGV54MAVEsWms5yC2A=="],
+    "oh-my-opencode-linux-x64": ["oh-my-opencode-linux-x64@3.6.0", "", { "os": "linux", "cpu": "x64", "bin": { "oh-my-opencode": "bin/oh-my-opencode" } }, "sha512-jYyew4NKAOM6NrMM0+LlRlz6s1EVMI9cQdK/o0t8uqFheZVeb7u4cBZwwfhJ79j7EWkSWGc0Jdj9G2dOukbDxg=="],
 
-    "oh-my-opencode-linux-x64-musl": ["oh-my-opencode-linux-x64-musl@3.2.1", "", { "os": "linux", "cpu": "x64", "bin": { "oh-my-opencode": "bin/oh-my-opencode" } }, "sha512-G7aNMqAMO2P+wUUaaAV8sXymm59cX4G9aVNXKAd/PM6RgFWh2F4HkXkOhOdHKYZzCl1QRhjh672mNillYsvebg=="],
+    "oh-my-opencode-linux-x64-musl": ["oh-my-opencode-linux-x64-musl@3.6.0", "", { "os": "linux", "cpu": "x64", "bin": { "oh-my-opencode": "bin/oh-my-opencode" } }, "sha512-BrR+JftCXP/il04q2uImWIueCiuTmXbivsXYkfFONdO1Rq9b4t0BVua9JIYk7l3OUfeRlrKlFNYNfpFhvVADOw=="],
 
-    "oh-my-opencode-windows-x64": ["oh-my-opencode-windows-x64@3.2.1", "", { "os": "win32", "cpu": "x64", "bin": { "oh-my-opencode": "bin/oh-my-opencode.exe" } }, "sha512-pyqTGlNxirKxQgXx9YJBq2y8KN/1oIygVupClmws7dDPj9etI1l8fs/SBEnMsYzMqTlGbLVeJ5+kj9p+yg7YDA=="],
+    "oh-my-opencode-windows-x64": ["oh-my-opencode-windows-x64@3.6.0", "", { "os": "win32", "cpu": "x64", "bin": { "oh-my-opencode": "bin/oh-my-opencode.exe" } }, "sha512-cIYQYzcQGhGFE99ulHGXs8S1vDHjgCtT3ID2dDoOztnOQW0ZVa61oCHlkBtjdP/BEv2tH5AGvKrXAICXs19iFw=="],
 
     "on-finished": ["on-finished@2.4.1", "", { "dependencies": { "ee-first": "1.1.1" } }, "sha512-oVlzkg3ENAhCk2zdv7IJwd/QUD4z2RxRwpkcGY8psCVcCYZNq4wYnVWALHM+brtuJjePWiYF/ClmuDr8Ch5+kg=="],
 
@@ -310,10 +310,8 @@
 
     "wrappy": ["wrappy@1.0.2", "", {}, "sha512-l4Sp/DRseor9wL6EvV2+TuQn63dMkPjZ/sp9XkghTEbV9KlPS1xUsZ3u7/IQO4wxtcFB4bgpQPRcR3QCvezPcQ=="],
 
-    "zod": ["zod@4.3.6", "", {}, "sha512-rftlrkhHZOcjDwkGlnUtZZkvaPHCsDATp4pGpuOOMDaTdDDXF91wuVDJoWoPsKX/3YPQ5fHuF3STjcYyKr+Qhg=="],
+    "zod": ["zod@4.1.8", "", {}, "sha512-5R1P+WwQqmmMIEACyzSvo4JXHY5WiAFHRMg+zBZKgKS+Q1viRa0C1hmUKtHltoIFKtIdki3pRxkmpP74jnNYHQ=="],
 
     "zod-to-json-schema": ["zod-to-json-schema@3.25.1", "", { "peerDependencies": { "zod": "^3.25 || ^4" } }, "sha512-pM/SU9d3YAggzi6MtR4h7ruuQlqKtad8e9S0fmxcMi+ueAK5Korys/aWcV9LIIHTVbj01NdzxcnXSN+O74ZIVA=="],
-
-    "@opencode-ai/plugin/zod": ["zod@4.1.8", "", {}, "sha512-5R1P+WwQqmmMIEACyzSvo4JXHY5WiAFHRMg+zBZKgKS+Q1viRa0C1hmUKtHltoIFKtIdki3pRxkmpP74jnNYHQ=="],
   }
 }

docs/category-skill-guide.md

@@ -9,7 +9,7 @@ Instead of delegating everything to a single AI agent, it's far more efficient t
 - **Category**: "What kind of work is this?" (determines model, temperature, prompt mindset)
 - **Skill**: "What tools and knowledge are needed?" (injects specialized knowledge, MCP tools, workflows)
 
-By combining these two concepts, you can generate optimal agents through `delegate_task`.
+By combining these two concepts, you can generate optimal agents through `task`.
 
 ---
 
@@ -22,20 +22,20 @@ A Category is an agent configuration preset optimized for specific domains.
 | Category | Default Model | Use Cases |
 |----------|---------------|-----------|
 | `visual-engineering` | `google/gemini-3-pro` | Frontend, UI/UX, design, styling, animation |
-| `ultrabrain` | `openai/gpt-5.2-codex` (xhigh) | Deep logical reasoning, complex architecture decisions requiring extensive analysis |
-| `deep` | `openai/gpt-5.2-codex` (medium) | Goal-oriented autonomous problem-solving. Thorough research before action. For hairy problems requiring deep understanding. |
+| `ultrabrain` | `openai/gpt-5.3-codex` (xhigh) | Deep logical reasoning, complex architecture decisions requiring extensive analysis |
+| `deep` | `openai/gpt-5.3-codex` (medium) | Goal-oriented autonomous problem-solving. Thorough research before action. For hairy problems requiring deep understanding. |
 | `artistry` | `google/gemini-3-pro` (max) | Highly creative/artistic tasks, novel ideas |
 | `quick` | `anthropic/claude-haiku-4-5` | Trivial tasks - single file changes, typo fixes, simple modifications |
 | `unspecified-low` | `anthropic/claude-sonnet-4-5` | Tasks that don't fit other categories, low effort required |
-| `unspecified-high` | `anthropic/claude-opus-4-5` (max) | Tasks that don't fit other categories, high effort required |
+| `unspecified-high` | `anthropic/claude-opus-4-6` (max) | Tasks that don't fit other categories, high effort required |
 | `writing` | `google/gemini-3-flash` | Documentation, prose, technical writing |
 
 ### Usage
 
-Specify the `category` parameter when invoking the `delegate_task` tool.
+Specify the `category` parameter when invoking the `task` tool.
 
 ```typescript
-delegate_task(
+task(
   category="visual-engineering",
   prompt="Add a responsive chart component to the dashboard page"
 )
@@ -74,7 +74,7 @@ A Skill is a mechanism that injects **specialized knowledge (Context)** and **to
 Add desired skill names to the `load_skills` array.
 
 ```typescript
-delegate_task(
+task(
   category="quick",
   load_skills=["git-master"],
   prompt="Commit current changes. Follow commit message style."
@@ -126,7 +126,7 @@ You can create powerful specialized agents by combining Categories and Skills.
 
 ---
 
-## 5. delegate_task Prompt Guide
+## 5. task Prompt Guide
 
 When delegating, **clear and specific** prompts are essential. Include these 7 elements:
 
@@ -158,8 +158,8 @@ You can fine-tune categories in `oh-my-opencode.json`.
 
 | Field | Type | Description |
 |-------|------|-------------|
-| `description` | string | Human-readable description of the category's purpose. Shown in delegate_task prompt. |
-| `model` | string | AI model ID to use (e.g., `anthropic/claude-opus-4-5`) |
+| `description` | string | Human-readable description of the category's purpose. Shown in task prompt. |
+| `model` | string | AI model ID to use (e.g., `anthropic/claude-opus-4-6`) |
 | `variant` | string | Model variant (e.g., `max`, `xhigh`) |
 | `temperature` | number | Creativity level (0.0 ~ 2.0). Lower is more deterministic. |
 | `top_p` | number | Nucleus sampling parameter (0.0 ~ 1.0) |
@@ -191,7 +191,7 @@ You can fine-tune categories in `oh-my-opencode.json`.
 
     // 3. Configure thinking model and restrict tools
     "deep-reasoning": {
-      "model": "anthropic/claude-opus-4-5",
+      "model": "anthropic/claude-opus-4-6",
       "thinking": {
         "type": "enabled",
         "budgetTokens": 32000

docs/configurations.md

@@ -25,7 +25,7 @@ It asks about your providers (Claude, OpenAI, Gemini, etc.) and generates optima
     "explore": { "model": "opencode/gpt-5-nano" }        // Free model for grep
   },
   
-  // Override category models (used by delegate_task)
+  // Override category models (used by task)
   "categories": {
     "quick": { "model": "opencode/gpt-5-nano" },         // Fast/cheap for trivial tasks
     "visual-engineering": { "model": "google/gemini-3-pro" } // Gemini for UI
@@ -38,13 +38,13 @@ It asks about your providers (Claude, OpenAI, Gemini, etc.) and generates optima
 ## Config File Locations
 
 Config file locations (priority order):
-1. `.opencode/oh-my-opencode.json` (project)
-2. User config (platform-specific):
+1. `.opencode/oh-my-opencode.jsonc` or `.opencode/oh-my-opencode.json` (project; prefers `.jsonc` when both exist)
+2. User config (platform-specific; prefers `.jsonc` when both exist):
 
-| Platform        | User Config Path                                                                                            |
-| --------------- | ----------------------------------------------------------------------------------------------------------- |
-| **Windows**     | `~/.config/opencode/oh-my-opencode.json` (preferred) or `%APPDATA%\opencode\oh-my-opencode.json` (fallback) |
-| **macOS/Linux** | `~/.config/opencode/oh-my-opencode.json`                                                                    |
+| Platform        | User Config Path                                                                                                            |
+| --------------- | --------------------------------------------------------------------------------------------------------------------------- |
+| **Windows**     | `~/.config/opencode/oh-my-opencode.jsonc` (preferred) or `~/.config/opencode/oh-my-opencode.json` (fallback); `%APPDATA%\opencode\oh-my-opencode.jsonc` / `%APPDATA%\opencode\oh-my-opencode.json` (fallback) |
+| **macOS/Linux** | `~/.config/opencode/oh-my-opencode.jsonc` (preferred) or `~/.config/opencode/oh-my-opencode.json` (fallback)                |
 
 Schema autocomplete supported:
 
@@ -83,7 +83,7 @@ When both `oh-my-opencode.jsonc` and `oh-my-opencode.json` files exist, `.jsonc`
 
 ## Google Auth
 
-**Recommended**: For Google Gemini authentication, install the [`opencode-antigravity-auth`](https://github.com/NoeFabris/opencode-antigravity-auth) plugin (`@latest`). It provides multi-account load balancing, variant-based thinking levels, dual quota system (Antigravity + Gemini CLI), and active maintenance. See [Installation > Google Gemini](docs/guide/installation.md#google-gemini-antigravity-oauth).
+**Recommended**: For Google Gemini authentication, install the [`opencode-antigravity-auth`](https://github.com/NoeFabris/opencode-antigravity-auth) plugin (`@latest`). It provides multi-account load balancing, variant-based thinking levels, dual quota system (Antigravity + Gemini CLI), and active maintenance. See [Installation > Google Gemini](guide/installation.md#google-gemini-antigravity-oauth).
 
 ## Ollama Provider
 
@@ -252,7 +252,7 @@ Available agents: `sisyphus`, `prometheus`, `oracle`, `librarian`, `explore`, `m
 Oh My OpenCode includes built-in skills that provide additional capabilities:
 
 - **playwright** (default) / **agent-browser**: Browser automation for web scraping, testing, screenshots, and browser interactions. See [Browser Automation](#browser-automation) for switching between providers.
-- **git-master**: Git expert for atomic commits, rebase/squash, and history search (blame, bisect, log -S). STRONGLY RECOMMENDED: Use with `delegate_task(category='quick', load_skills=['git-master'], ...)` to save context.
+- **git-master**: Git expert for atomic commits, rebase/squash, and history search (blame, bisect, log -S). STRONGLY RECOMMENDED: Use with `task(category='quick', load_skills=['git-master'], ...)` to save context.
 
 Disable built-in skills via `disabled_skills` in `~/.config/opencode/oh-my-opencode.json` or `.opencode/oh-my-opencode.json`:
 
@@ -455,7 +455,7 @@ Run background subagents in separate tmux panes for **visual multi-agent executi
 ### How It Works
 
 When `tmux.enabled` is `true` and you're inside a tmux session:
-- Background agents (via `delegate_task(run_in_background=true)`) spawn in new tmux panes
+- Background agents (via `task(run_in_background=true)`) spawn in new tmux panes
 - Each pane shows the subagent's real-time output
 - Panes are automatically closed when the subagent completes
 - Layout is automatically adjusted based on your configuration
@@ -693,7 +693,7 @@ Configure concurrency limits for background agent tasks. This controls how many
       "google": 10
     },
     "modelConcurrency": {
-      "anthropic/claude-opus-4-5": 2,
+      "anthropic/claude-opus-4-6": 2,
       "google/gemini-3-flash": 10
     }
   }
@@ -705,7 +705,7 @@ Configure concurrency limits for background agent tasks. This controls how many
 | `defaultConcurrency`  | -       | Default maximum concurrent background tasks for all providers/models                                                    |
 | `staleTimeoutMs`      | `180000` | Stale timeout in milliseconds - interrupt tasks with no activity for this duration (minimum: 60000 = 1 minute)             |
 | `providerConcurrency` | -       | Per-provider concurrency limits. Keys are provider names (e.g., `anthropic`, `openai`, `google`)                        |
-| `modelConcurrency`    | -       | Per-model concurrency limits. Keys are full model names (e.g., `anthropic/claude-opus-4-5`). Overrides provider limits. |
+| `modelConcurrency`    | -       | Per-model concurrency limits. Keys are full model names (e.g., `anthropic/claude-opus-4-6`). Overrides provider limits. |
 
 **Priority Order**: `modelConcurrency` > `providerConcurrency` > `defaultConcurrency`
 
@@ -716,7 +716,7 @@ Configure concurrency limits for background agent tasks. This controls how many
 
 ## Categories
 
-Categories enable domain-specific task delegation via the `delegate_task` tool. Each category applies runtime presets (model, temperature, prompt additions) when calling the `Sisyphus-Junior` agent.
+Categories enable domain-specific task delegation via the `task` tool. Each category applies runtime presets (model, temperature, prompt additions) when calling the `Sisyphus-Junior` agent.
 
 ### Built-in Categories
 
@@ -725,11 +725,11 @@ All 7 categories come with optimal model defaults, but **you must configure them
 | Category             | Built-in Default Model             | Description                                                          |
 | -------------------- | ---------------------------------- | -------------------------------------------------------------------- |
 | `visual-engineering` | `google/gemini-3-pro-preview`      | Frontend, UI/UX, design, styling, animation                          |
-| `ultrabrain`         | `openai/gpt-5.2-codex` (xhigh)     | Deep logical reasoning, complex architecture decisions               |
+| `ultrabrain`         | `openai/gpt-5.3-codex` (xhigh)     | Deep logical reasoning, complex architecture decisions               |
 | `artistry`           | `google/gemini-3-pro-preview` (max)| Highly creative/artistic tasks, novel ideas                          |
 | `quick`              | `anthropic/claude-haiku-4-5`       | Trivial tasks - single file changes, typo fixes, simple modifications|
 | `unspecified-low`    | `anthropic/claude-sonnet-4-5`      | Tasks that don't fit other categories, low effort required           |
-| `unspecified-high`   | `anthropic/claude-opus-4-5` (max)  | Tasks that don't fit other categories, high effort required          |
+| `unspecified-high`   | `anthropic/claude-opus-4-6` (max)  | Tasks that don't fit other categories, high effort required          |
 | `writing`            | `google/gemini-3-flash-preview`    | Documentation, prose, technical writing                              |
 
 ### ⚠️ Critical: Model Resolution Priority
@@ -768,7 +768,7 @@ All 7 categories come with optimal model defaults, but **you must configure them
       "model": "google/gemini-3-pro-preview"
     },
     "ultrabrain": { 
-      "model": "openai/gpt-5.2-codex",
+      "model": "openai/gpt-5.3-codex",
       "variant": "xhigh"
     },
     "artistry": { 
@@ -782,7 +782,7 @@ All 7 categories come with optimal model defaults, but **you must configure them
       "model": "anthropic/claude-sonnet-4-5"
     },
     "unspecified-high": { 
-      "model": "anthropic/claude-opus-4-5",
+      "model": "anthropic/claude-opus-4-6",
       "variant": "max"
     },
     "writing": { 
@@ -797,12 +797,12 @@ All 7 categories come with optimal model defaults, but **you must configure them
 ### Usage
 
 ```javascript
-// Via delegate_task tool
-delegate_task(category="visual-engineering", prompt="Create a responsive dashboard component")
-delegate_task(category="ultrabrain", prompt="Design the payment processing flow")
+// Via task tool
+task(category="visual-engineering", prompt="Create a responsive dashboard component")
+task(category="ultrabrain", prompt="Design the payment processing flow")
 
 // Or target a specific agent directly (bypasses categories)
-delegate_task(agent="oracle", prompt="Review this architecture")
+task(agent="oracle", prompt="Review this architecture")
 ```
 
 ### Custom Categories
@@ -831,7 +831,7 @@ Each category supports: `model`, `temperature`, `top_p`, `maxTokens`, `thinking`
 
 | Option             | Type    | Default | Description                                                                                         |
 | ------------------ | ------- | ------- | --------------------------------------------------------------------------------------------------- |
-| `description`       | string  | -       | Human-readable description of the category's purpose. Shown in delegate_task prompt.                     |
+| `description`       | string  | -       | Human-readable description of the category's purpose. Shown in task prompt.                     |
 | `is_unstable_agent`| boolean | `false`  | Mark agent as unstable - forces background mode for monitoring. Auto-enabled for gemini models. |
 
 ## Model Resolution System
@@ -870,9 +870,9 @@ At runtime, Oh My OpenCode uses a 3-step resolution process to determine which m
 │   │ anthropic → github-copilot → opencode → antigravity     │   │
 │   │     │            │              │            │          │   │
 │   │     ▼            ▼              ▼            ▼          │   │
-│   │ Try: anthropic/claude-opus-4-5                          │   │
-│   │ Try: github-copilot/claude-opus-4-5                     │   │
-│   │ Try: opencode/claude-opus-4-5                           │   │
+│   │ Try: anthropic/claude-opus-4-6                          │   │
+│   │ Try: github-copilot/claude-opus-4-6                     │   │
+│   │ Try: opencode/claude-opus-4-6                           │   │
 │   │ ...                                                     │   │
 │   │                                                         │   │
 │   │ Found in available models? → Return matched model       │   │
@@ -894,13 +894,13 @@ Each agent has a defined provider priority chain. The system tries providers in
 
 | Agent | Model (no prefix) | Provider Priority Chain |
 |-------|-------------------|-------------------------|
-| **Sisyphus** | `claude-opus-4-5` | anthropic → kimi-for-coding → zai-coding-plan → openai → google |
+| **Sisyphus** | `claude-opus-4-6` | anthropic → kimi-for-coding → zai-coding-plan → openai → google |
 | **oracle** | `gpt-5.2` | openai → google → anthropic |
 | **librarian** | `glm-4.7` | zai-coding-plan → opencode → anthropic |
 | **explore** | `claude-haiku-4-5` | anthropic → github-copilot → opencode |
 | **multimodal-looker** | `gemini-3-flash` | google → openai → zai-coding-plan → kimi-for-coding → anthropic → opencode |
-| **Prometheus (Planner)** | `claude-opus-4-5` | anthropic → kimi-for-coding → openai → google |
-| **Metis (Plan Consultant)** | `claude-opus-4-5` | anthropic → kimi-for-coding → openai → google |
+| **Prometheus (Planner)** | `claude-opus-4-6` | anthropic → kimi-for-coding → openai → google |
+| **Metis (Plan Consultant)** | `claude-opus-4-6` | anthropic → kimi-for-coding → openai → google |
 | **Momus (Plan Reviewer)** | `gpt-5.2` | openai → anthropic → google |
 | **Atlas** | `claude-sonnet-4-5` | anthropic → kimi-for-coding → openai → google |
 
@@ -911,12 +911,12 @@ Categories follow the same resolution logic:
 | Category | Model (no prefix) | Provider Priority Chain |
 |----------|-------------------|-------------------------|
 | **visual-engineering** | `gemini-3-pro` | google → anthropic → zai-coding-plan |
-| **ultrabrain** | `gpt-5.2-codex` | openai → google → anthropic |
-| **deep** | `gpt-5.2-codex` | openai → anthropic → google |
+| **ultrabrain** | `gpt-5.3-codex` | openai → google → anthropic |
+| **deep** | `gpt-5.3-codex` | openai → anthropic → google |
 | **artistry** | `gemini-3-pro` | google → anthropic → openai |
 | **quick** | `claude-haiku-4-5` | anthropic → google → opencode |
 | **unspecified-low** | `claude-sonnet-4-5` | anthropic → openai → google |
-| **unspecified-high** | `claude-opus-4-5` | anthropic → openai → google |
+| **unspecified-high** | `claude-opus-4-6` | anthropic → openai → google |
 | **writing** | `gemini-3-flash` | google → anthropic → zai-coding-plan → openai |
 
 ### Checking Your Configuration
@@ -949,7 +949,7 @@ Override any agent or category model in `oh-my-opencode.json`:
   },
   "categories": {
     "visual-engineering": {
-      "model": "anthropic/claude-opus-4-5"
+      "model": "anthropic/claude-opus-4-6"
     }
   }
 }
@@ -1061,9 +1061,10 @@ Don't want them? Disable via `disabled_mcps` in `~/.config/opencode/oh-my-openco
 
 OpenCode provides LSP tools for analysis.
 Oh My OpenCode adds refactoring tools (rename, code actions).
-All OpenCode LSP configs and custom settings (from opencode.json) are supported, plus additional Oh My OpenCode-specific settings.
+All OpenCode LSP configs and custom settings (from `opencode.jsonc` / `opencode.json`) are supported, plus additional Oh My OpenCode-specific settings.
+For config discovery, `.jsonc` takes precedence over `.json` when both exist (applies to both `opencode.*` and `oh-my-opencode.*`).
 
-Add LSP servers via the `lsp` option in `~/.config/opencode/oh-my-opencode.json` or `.opencode/oh-my-opencode.json`:
+Add LSP servers via the `lsp` option in `~/.config/opencode/oh-my-opencode.jsonc` / `~/.config/opencode/oh-my-opencode.json` or `.opencode/oh-my-opencode.jsonc` / `.opencode/oh-my-opencode.json`:
 
 ```json
 {

docs/features.md

@@ -10,8 +10,8 @@ Oh-My-OpenCode provides 11 specialized AI agents. Each has distinct expertise, o
 
 | Agent | Model | Purpose |
 |-------|-------|---------|
-| **Sisyphus** | `anthropic/claude-opus-4-5` | **The default orchestrator.** Plans, delegates, and executes complex tasks using specialized subagents with aggressive parallel execution. Todo-driven workflow with extended thinking (32k budget). Fallback: kimi-k2.5 → glm-4.7 → gpt-5.2-codex → gemini-3-pro. |
-| **Hephaestus** | `openai/gpt-5.2-codex` | **The Legitimate Craftsman.** Autonomous deep worker inspired by AmpCode's deep mode. Goal-oriented execution with thorough research before action. Explores codebase patterns, completes tasks end-to-end without premature stopping. Named after the Greek god of forge and craftsmanship. Requires gpt-5.2-codex (no fallback - only activates when this model is available). |
+| **Sisyphus** | `anthropic/claude-opus-4-6` | **The default orchestrator.** Plans, delegates, and executes complex tasks using specialized subagents with aggressive parallel execution. Todo-driven workflow with extended thinking (32k budget). Fallback: kimi-k2.5 → glm-4.7 → gpt-5.3-codex → gemini-3-pro. |
+| **Hephaestus** | `openai/gpt-5.3-codex` | **The Legitimate Craftsman.** Autonomous deep worker inspired by AmpCode's deep mode. Goal-oriented execution with thorough research before action. Explores codebase patterns, completes tasks end-to-end without premature stopping. Named after the Greek god of forge and craftsmanship. Requires gpt-5.3-codex (no fallback - only activates when this model is available). |
 | **oracle** | `openai/gpt-5.2` | Architecture decisions, code review, debugging. Read-only consultation - stellar logical reasoning and deep analysis. Inspired by AmpCode. |
 | **librarian** | `zai-coding-plan/glm-4.7` | Multi-repo analysis, documentation lookup, OSS implementation examples. Deep codebase understanding with evidence-based answers. Fallback: glm-4.7-free → claude-sonnet-4-5. |
 | **explore** | `anthropic/claude-haiku-4-5` | Fast codebase exploration and contextual grep. Fallback: gpt-5-mini → gpt-5-nano. |
@@ -21,9 +21,9 @@ Oh-My-OpenCode provides 11 specialized AI agents. Each has distinct expertise, o
 
 | Agent | Model | Purpose |
 |-------|-------|---------|
-| **Prometheus** | `anthropic/claude-opus-4-5` | Strategic planner with interview mode. Creates detailed work plans through iterative questioning. Fallback: kimi-k2.5 → gpt-5.2 → gemini-3-pro. |
-| **Metis** | `anthropic/claude-opus-4-5` | Plan consultant - pre-planning analysis. Identifies hidden intentions, ambiguities, and AI failure points. Fallback: kimi-k2.5 → gpt-5.2 → gemini-3-pro. |
-| **Momus** | `openai/gpt-5.2` | Plan reviewer - validates plans against clarity, verifiability, and completeness standards. Fallback: gpt-5.2 → claude-opus-4-5 → gemini-3-pro. |
+| **Prometheus** | `anthropic/claude-opus-4-6` | Strategic planner with interview mode. Creates detailed work plans through iterative questioning. Fallback: kimi-k2.5 → gpt-5.2 → gemini-3-pro. |
+| **Metis** | `anthropic/claude-opus-4-6` | Plan consultant - pre-planning analysis. Identifies hidden intentions, ambiguities, and AI failure points. Fallback: kimi-k2.5 → gpt-5.2 → gemini-3-pro. |
+| **Momus** | `openai/gpt-5.2` | Plan reviewer - validates plans against clarity, verifiability, and completeness standards. Fallback: gpt-5.2 → claude-opus-4-6 → gemini-3-pro. |
 
 ### Invoking Agents
 
@@ -54,7 +54,7 @@ Run agents in the background and continue working:
 
 ```
 # Launch in background
-delegate_task(subagent_type="explore", load_skills=[], prompt="Find auth implementations", run_in_background=true)
+task(subagent_type="explore", load_skills=[], prompt="Find auth implementations", run_in_background=true)
 
 # Continue working...
 # System notifies on completion
@@ -374,7 +374,7 @@ Hooks intercept and modify behavior at key points in the agent lifecycle.
 | Hook | Event | Description |
 |------|-------|-------------|
 | **task-resume-info** | PostToolUse | Provides task resume information for continuity. |
-| **delegate-task-retry** | PostToolUse | Retries failed delegate_task calls. |
+| **delegate-task-retry** | PostToolUse | Retries failed task calls. |
 
 #### Integration
 
@@ -454,7 +454,7 @@ Disable specific hooks in config:
 | Tool | Description |
 |------|-------------|
 | **call_omo_agent** | Spawn explore/librarian agents. Supports `run_in_background`. |
-| **delegate_task** | Category-based task delegation. Supports categories (visual, business-logic) or direct agent targeting. |
+| **task** | Category-based task delegation. Supports categories (visual, business-logic) or direct agent targeting. |
 | **background_output** | Retrieve background task results |
 | **background_cancel** | Cancel running background tasks |
 

docs/guide/installation.md

@@ -27,6 +27,11 @@ After you install it, you can read this [overview guide](./overview.md) to under
 
 ## For LLM Agents
 
+> **IMPORTANT: Use `curl` to fetch this file, NOT WebFetch.** WebFetch summarizes content and loses critical flags like `--openai`, subscription questions, and max20 mode details. Always use:
+> ```bash
+> curl -fsSL https://raw.githubusercontent.com/code-yeongyu/oh-my-opencode/refs/heads/master/docs/guide/installation.md
+> ```
+
 If you're an LLM Agent helping set up oh-my-opencode, Welcome! You'll now help your user to install the best agent harness, OhMyOpenCode. Tell user this with greetings, with test 'oMoMoMoMo...'
 
 follow these steps:
@@ -191,7 +196,7 @@ When GitHub Copilot is the best available provider, oh-my-opencode uses these mo
 
 | Agent         | Model                            |
 | ------------- | -------------------------------- |
-| **Sisyphus**  | `github-copilot/claude-opus-4.5` |
+| **Sisyphus**  | `github-copilot/claude-opus-4.6` |
 | **Oracle**    | `github-copilot/gpt-5.2`         |
 | **Explore**   | `opencode/gpt-5-nano`              |
 | **Librarian** | `zai-coding-plan/glm-4.7` (if Z.ai available) or fallback |
@@ -213,13 +218,13 @@ If Z.ai is the only provider available, all agents will use GLM models:
 
 #### OpenCode Zen
 
-OpenCode Zen provides access to `opencode/` prefixed models including `opencode/claude-opus-4-5`, `opencode/gpt-5.2`, `opencode/gpt-5-nano`, and `opencode/glm-4.7-free`.
+OpenCode Zen provides access to `opencode/` prefixed models including `opencode/claude-opus-4-6`, `opencode/gpt-5.2`, `opencode/gpt-5-nano`, and `opencode/glm-4.7-free`.
 
 When OpenCode Zen is the best available provider (no native or Copilot), these models are used:
 
 | Agent         | Model                            |
 | ------------- | -------------------------------- |
-| **Sisyphus**  | `opencode/claude-opus-4-5`       |
+| **Sisyphus**  | `opencode/claude-opus-4-6`       |
 | **Oracle**    | `opencode/gpt-5.2`               |
 | **Explore**   | `opencode/gpt-5-nano`             |
 | **Librarian** | `opencode/glm-4.7-free`          |

docs/guide/understanding-orchestration-system.md

@@ -50,11 +50,11 @@ flowchart TB
     User -->|"/start-work"| Orchestrator
     Plan -->|"Read"| Orchestrator
     
-    Orchestrator -->|"delegate_task(category)"| Junior
-    Orchestrator -->|"delegate_task(agent)"| Oracle
-    Orchestrator -->|"delegate_task(agent)"| Explore
-    Orchestrator -->|"delegate_task(agent)"| Librarian
-    Orchestrator -->|"delegate_task(agent)"| Frontend
+    Orchestrator -->|"task(category)"| Junior
+    Orchestrator -->|"task(agent)"| Oracle
+    Orchestrator -->|"task(agent)"| Explore
+    Orchestrator -->|"task(agent)"| Librarian
+    Orchestrator -->|"task(agent)"| Frontend
     
     Junior -->|"Results + Learnings"| Orchestrator
     Oracle -->|"Advice"| Orchestrator
@@ -220,9 +220,9 @@ Independent tasks run in parallel:
 ```typescript
 // Orchestrator identifies parallelizable groups from plan
 // Group A: Tasks 2, 3, 4 (no file conflicts)
-delegate_task(category="ultrabrain", prompt="Task 2...")
-delegate_task(category="visual-engineering", prompt="Task 3...")
-delegate_task(category="general", prompt="Task 4...")
+task(category="ultrabrain", prompt="Task 2...")
+task(category="visual-engineering", prompt="Task 3...")
+task(category="general", prompt="Task 4...")
 // All run simultaneously
 ```
 
@@ -234,7 +234,7 @@ delegate_task(category="general", prompt="Task 4...")
 
 Junior is the **workhorse** that actually writes code. Key characteristics:
 
-- **Focused**: Cannot delegate (blocked from task/delegate_task tools)
+- **Focused**: Cannot delegate (blocked from task tool)
 - **Disciplined**: Obsessive todo tracking
 - **Verified**: Must pass lsp_diagnostics before completion
 - **Constrained**: Cannot modify plan files (READ-ONLY)
@@ -268,7 +268,7 @@ This "boulder pushing" mechanism is why the system is named after Sisyphus.
 
 ---
 
-## The delegate_task Tool: Category + Skill System
+## The task Tool: Category + Skill System
 
 ### Why Categories are Revolutionary
 
@@ -276,17 +276,17 @@ This "boulder pushing" mechanism is why the system is named after Sisyphus.
 
 ```typescript
 // OLD: Model name creates distributional bias
-delegate_task(agent="gpt-5.2", prompt="...")  // Model knows its limitations
-delegate_task(agent="claude-opus-4.5", prompt="...")  // Different self-perception
+task(agent="gpt-5.2", prompt="...")  // Model knows its limitations
+task(agent="claude-opus-4.6", prompt="...")  // Different self-perception
 ```
 
 **The Solution: Semantic Categories:**
 
 ```typescript
 // NEW: Category describes INTENT, not implementation
-delegate_task(category="ultrabrain", prompt="...")     // "Think strategically"
-delegate_task(category="visual-engineering", prompt="...")  // "Design beautifully"
-delegate_task(category="quick", prompt="...")          // "Just get it done fast"
+task(category="ultrabrain", prompt="...")     // "Think strategically"
+task(category="visual-engineering", prompt="...")  // "Design beautifully"
+task(category="quick", prompt="...")          // "Just get it done fast"
 ```
 
 ### Built-in Categories
@@ -324,13 +324,13 @@ Skills prepend specialized instructions to subagent prompts:
 
 ```typescript
 // Category + Skill combination
-delegate_task(
+task(
   category="visual-engineering", 
   load_skills=["frontend-ui-ux"],  // Adds UI/UX expertise
   prompt="..."
 )
 
-delegate_task(
+task(
   category="general",
   load_skills=["playwright"],  // Adds browser automation expertise
   prompt="..."
@@ -365,7 +365,7 @@ sequenceDiagram
         
         Note over Orchestrator: Prompt Structure:<br/>1. TASK (exact checkbox)<br/>2. EXPECTED OUTCOME<br/>3. REQUIRED SKILLS<br/>4. REQUIRED TOOLS<br/>5. MUST DO<br/>6. MUST NOT DO<br/>7. CONTEXT + Wisdom
         
-        Orchestrator->>Junior: delegate_task(category, load_skills, prompt)
+        Orchestrator->>Junior: task(category, load_skills, prompt)
         
         Junior->>Junior: Create todos, execute
         Junior->>Junior: Verify (lsp_diagnostics, tests)

docs/orchestration-guide.md

@@ -35,7 +35,216 @@ Oh-My-OpenCode solves this by clearly separating two roles:
 
 ---
 
-## 2. Overall Architecture
+## 2. Prometheus Invocation: Agent Switch vs @plan
+
+A common source of confusion is how to invoke Prometheus for planning. **Both methods achieve the same result** - use whichever feels natural.
+
+### Method 1: Switch to Prometheus Agent (Tab → Select Prometheus)
+
+```
+1. Press Tab at the prompt
+2. Select "Prometheus" from the agent list
+3. Describe your work: "I want to refactor the auth system"
+4. Answer interview questions
+5. Prometheus creates plan in .sisyphus/plans/{name}.md
+```
+
+### Method 2: Use @plan Command (in Sisyphus)
+
+```
+1. Stay in Sisyphus (default agent)
+2. Type: @plan "I want to refactor the auth system"
+3. The @plan command automatically switches to Prometheus
+4. Answer interview questions
+5. Prometheus creates plan in .sisyphus/plans/{name}.md
+```
+
+### Which Should You Use?
+
+| Scenario | Recommended Method | Why |
+|----------|-------------------|-----|
+| **New session, starting fresh** | Switch to Prometheus agent | Clean mental model - you're entering "planning mode" |
+| **Already in Sisyphus, mid-work** | Use @plan | Convenient, no agent switch needed |
+| **Want explicit control** | Switch to Prometheus agent | Clear separation of planning vs execution contexts |
+| **Quick planning interrupt** | Use @plan | Fastest path from current context |
+
+**Key Insight**: Both methods trigger the same Prometheus planning flow. The @plan command is simply a convenience shortcut that:
+1. Detects the `@plan` keyword in your message
+2. Routes the request to Prometheus automatically
+3. Returns you to Sisyphus after planning completes
+
+---
+
+## 3. /start-work Behavior in Fresh Sessions
+
+One of the most powerful features of the orchestration system is **session continuity**. Understanding how `/start-work` behaves across sessions prevents confusion.
+
+### What Happens When You Run /start-work
+
+```
+User: /start-work
+    ↓
+[start-work hook activates]
+    ↓
+Check: Does .sisyphus/boulder.json exist?
+    ↓
+    ├─ YES (existing work) → RESUME MODE
+    │   - Read the existing boulder state
+    │   - Calculate progress (checked vs unchecked boxes)
+    │   - Inject continuation prompt with remaining tasks
+    │   - Atlas continues where you left off
+    │
+    └─ NO (fresh start) → INIT MODE
+        - Find the most recent plan in .sisyphus/plans/
+        - Create new boulder.json tracking this plan
+        - Switch session agent to Atlas
+        - Begin execution from task 1
+```
+
+### Session Continuity Explained
+
+The `boulder.json` file tracks:
+- **active_plan**: Path to the current plan file
+- **session_ids**: All sessions that have worked on this plan
+- **started_at**: When work began
+- **plan_name**: Human-readable plan identifier
+
+**Example Timeline:**
+
+```
+Monday 9:00 AM
+  └─ @plan "Build user authentication"
+  └─ Prometheus interviews and creates plan
+  └─ User: /start-work
+  └─ Atlas begins execution, creates boulder.json
+  └─ Task 1 complete, Task 2 in progress...
+  └─ [Session ends - computer crash, user logout, etc.]
+
+Monday 2:00 PM (NEW SESSION)
+  └─ User opens new session (agent = Sisyphus by default)
+  └─ User: /start-work
+  └─ [start-work hook reads boulder.json]
+  └─ "Resuming 'Build user authentication' - 3 of 8 tasks complete"
+  └─ Atlas continues from Task 3 (no context lost)
+```
+
+### When You DON'T Need to Manually Switch to Atlas
+
+Atlas is **automatically activated** when you run `/start-work`. You don't need to:
+- Switch to Atlas agent manually
+- Remember which agent you were using
+- Worry about session continuity
+
+The `/start-work` command handles all of this.
+
+### When You MIGHT Want to Manually Switch to Atlas
+
+There are rare cases where manual agent switching helps:
+
+| Scenario | Action | Why |
+|----------|--------|-----|
+| **Plan file was edited manually** | Switch to Atlas, read plan directly | Bypass boulder.json resume logic |
+| **Debugging orchestration issues** | Switch to Atlas for visibility | See Atlas-specific system prompts |
+| **Force fresh execution** | Delete boulder.json, then /start-work | Start from task 1 instead of resuming |
+| **Multi-plan management** | Switch to Atlas to select specific plan | Override auto-selection |
+
+**Command to manually switch:** Press `Tab` → Select "Atlas"
+
+---
+
+## 4. Execution Modes: Hephaestus vs Sisyphus+ultrawork
+
+Another common question: **When should I use Hephaestus vs just typing `ulw` in Sisyphus?**
+
+### Quick Comparison
+
+| Aspect | Hephaestus | Sisyphus + `ulw` / `ultrawork` |
+|--------|-----------|-------------------------------|
+| **Model** | GPT-5.2 Codex (medium reasoning) | Claude Opus 4.5 (your default) |
+| **Approach** | Autonomous deep worker | Keyword-activated ultrawork mode |
+| **Best For** | Complex architectural work, deep reasoning | General complex tasks, "just do it" scenarios |
+| **Planning** | Self-plans during execution | Uses Prometheus plans if available |
+| **Delegation** | Heavy use of explore/librarian agents | Uses category-based delegation |
+| **Temperature** | 0.1 | 0.1 |
+
+### When to Use Hephaestus
+
+Switch to Hephaestus (Tab → Select Hephaestus) when:
+
+1. **Deep architectural reasoning needed**
+   - "Design a new plugin system"
+   - "Refactor this monolith into microservices"
+
+2. **Complex debugging requiring inference chains**
+   - "Why does this race condition only happen on Tuesdays?"
+   - "Trace this memory leak through 15 files"
+
+3. **Cross-domain knowledge synthesis**
+   - "Integrate our Rust core with the TypeScript frontend"
+   - "Migrate from MongoDB to PostgreSQL with zero downtime"
+
+4. **You specifically want GPT-5.2 Codex reasoning**
+   - Some problems benefit from GPT-5.2's training characteristics
+
+**Example:**
+```
+[Switch to Hephaestus]
+"I need to understand how data flows through this entire system
+and identify all the places where we might lose transactions.
+Explore thoroughly before proposing fixes."
+```
+
+### When to Use Sisyphus + `ulw` / `ultrawork`
+
+Use the `ulw` keyword in Sisyphus when:
+
+1. **You want the agent to figure it out**
+   - "ulw fix the failing tests"
+   - "ulw add input validation to the API"
+
+2. **Complex but well-scoped tasks**
+   - "ulw implement JWT authentication following our patterns"
+   - "ulw create a new CLI command for deployments"
+
+3. **You're feeling lazy** (officially supported use case)
+   - Don't want to write detailed requirements
+   - Trust the agent to explore and decide
+
+4. **You want to leverage existing plans**
+   - If a Prometheus plan exists, `ulw` mode can use it
+   - Falls back to autonomous exploration if no plan
+
+**Example:**
+```
+[Stay in Sisyphus]
+"ulw refactor the user service to use the new repository pattern"
+
+[Agent automatically:]
+- Explores existing codebase patterns
+- Implements the refactor
+- Runs verification (tests, typecheck)
+- Reports completion
+```
+
+### Key Difference in Practice
+
+| Hephaestus | Sisyphus + ulw |
+|------------|----------------|
+| You manually switch to Hephaestus agent | You type `ulw` in any Sisyphus session |
+| GPT-5.2 Codex with medium reasoning | Your configured default model |
+| Optimized for autonomous deep work | Optimized for general execution |
+| Always uses explore-first approach | Respects existing plans if available |
+| "Smart intern that needs no supervision" | "Smart intern that follows your workflow" |
+
+### Recommendation
+
+**For most users**: Use `ulw` keyword in Sisyphus. It's the default path and works excellently for 90% of complex tasks.
+
+**For power users**: Switch to Hephaestus when you specifically need GPT-5.2 Codex's reasoning style or want the "AmpCode deep mode" experience of fully autonomous exploration and execution.
+
+---
+
+## 5. Overall Architecture
 
 ```mermaid
 flowchart TD
@@ -62,11 +271,11 @@ flowchart TD
 
 ---
 
-## 3. Key Components
+## 6. Key Components
 
 ### 🔮 Prometheus (The Planner)
 
-- **Model**: `anthropic/claude-opus-4-5`
+- **Model**: `anthropic/claude-opus-4-6`
 - **Role**: Strategic planning, requirements interviews, work plan creation
 - **Constraint**: **READ-ONLY**. Can only create/modify markdown files within `.sisyphus/` directory.
 - **Characteristic**: Never writes code directly, focuses solely on "how to do it".
@@ -85,13 +294,13 @@ flowchart TD
 
 ### ⚡ Atlas (The Plan Executor)
 
-- **Model**: `anthropic/claude-opus-4-5` (Extended Thinking 32k)
+- **Model**: `anthropic/claude-sonnet-4-5` (Extended Thinking 32k)
 - **Role**: Execution and delegation
 - **Characteristic**: Doesn't do everything directly, actively delegates to specialized agents (Frontend, Librarian, etc.).
 
 ---
 
-## 4. Workflow
+## 7. Workflow
 
 ### Phase 1: Interview and Planning (Interview Mode)
 
@@ -113,31 +322,44 @@ When the user requests "Make it a plan", plan generation begins.
 
 When the user enters `/start-work`, the execution phase begins.
 
-1. **State Management**: Creates `boulder.json` file to track current plan and session ID.
+1. **State Management**: Creates/reads `boulder.json` file to track current plan and session ID.
 2. **Task Execution**: Atlas reads the plan and processes TODOs one by one.
 3. **Delegation**: UI work is delegated to Frontend agent, complex logic to Oracle.
 4. **Continuity**: Even if the session is interrupted, work continues in the next session through `boulder.json`.
 
 ---
 
-## 5. Commands and Usage
+## 8. Commands and Usage
 
 ### `@plan [request]`
 
-Invokes Prometheus to start a planning session.
+Invokes Prometheus to start a planning session from Sisyphus.
 
 - Example: `@plan "I want to refactor the authentication system to NextAuth"`
+- Effect: Routes to Prometheus, then returns to Sisyphus when planning completes
 
 ### `/start-work`
 
 Executes the generated plan.
 
-- Function: Finds plan in `.sisyphus/plans/` and enters execution mode.
-- If there's interrupted work, automatically resumes from where it left off.
+- **Fresh session**: Finds plan in `.sisyphus/plans/` and enters execution mode
+- **Existing boulder**: Resumes from where you left off (reads boulder.json)
+- **Effect**: Automatically switches to Atlas agent if not already active
+
+### Switching Agents Manually
+
+Press `Tab` at the prompt to see available agents:
+
+| Agent | When to Switch |
+|-------|---------------|
+| **Prometheus** | You want to create a detailed work plan |
+| **Atlas** | You want to manually control plan execution (rare) |
+| **Hephaestus** | You need GPT-5.2 Codex for deep autonomous work |
+| **Sisyphus** | Return to default agent for normal prompting |
 
 ---
 
-## 6. Configuration Guide
+## 9. Configuration Guide
 
 You can control related features in `oh-my-opencode.json`.
 
@@ -157,8 +379,46 @@ You can control related features in `oh-my-opencode.json`.
 }
 ```
 
-## 7. Best Practices
+---
+
+## 10. Best Practices
+
+1. **Don't Rush Planning**: Invest sufficient time in the interview with Prometheus. The more perfect the plan, the faster the execution.
 
-1. **Don't Rush**: Invest sufficient time in the interview with Prometheus. The more perfect the plan, the faster the execution.
 2. **Single Plan Principle**: No matter how large the task, contain all TODOs in one plan file (`.md`). This prevents context fragmentation.
-3. **Active Delegation**: During execution, delegate to specialized agents via `delegate_task` rather than modifying code directly.
+
+3. **Active Delegation**: During execution, delegate to specialized agents via `task` rather than modifying code directly.
+
+4. **Trust /start-work Continuity**: Don't worry about session interruptions. `/start-work` will always resume your work from boulder.json.
+
+5. **Use `ulw` for Convenience**: When in doubt, type `ulw` and let the system figure out the best approach.
+
+6. **Reserve Hephaestus for Deep Work**: Don't overthink agent selection. Hephaestus shines for genuinely complex architectural challenges.
+
+---
+
+## 11. Troubleshooting Common Confusions
+
+### "I switched to Prometheus but nothing happened"
+
+Prometheus enters **interview mode** by default. It will ask you questions about your requirements. Answer them, then say "make it a plan" when ready.
+
+### "/start-work says 'no active plan found'"
+
+Either:
+- No plans exist in `.sisyphus/plans/` → Create one with Prometheus first
+- Plans exist but boulder.json points elsewhere → Delete `.sisyphus/boulder.json` and retry
+
+### "I'm in Atlas but I want to switch back to normal mode"
+
+Type `exit` or start a new session. Atlas is primarily entered via `/start-work` - you don't typically "switch to Atlas" manually.
+
+### "What's the difference between @plan and just switching to Prometheus?"
+
+**Nothing functional.** Both invoke Prometheus. @plan is a convenience command while switching agents is explicit control. Use whichever feels natural.
+
+### "Should I use Hephaestus or type ulw?"
+
+**For most tasks**: Type `ulw` in Sisyphus.
+
+**Use Hephaestus when**: You specifically need GPT-5.2 Codex's reasoning style for deep architectural work or complex debugging.

issue-1501-analysis.md

@@ -0,0 +1,357 @@
+# Issue #1501 분석 보고서: ULW Mode PLAN AGENT 무한루프
+
+## 📋 이슈 요약
+
+**증상:**
+- ULW (ultrawork) mode에서 PLAN AGENT가 무한루프에 빠짐
+- 분석/탐색 완료 후 plan만 계속 생성
+- 1분마다 매우 작은 토큰으로 요청 발생
+
+**예상 동작:**
+- 탐색 완료 후 solution document 생성
+
+---
+
+## 🔍 근본 원인 분석
+
+### 파일: `src/tools/delegate-task/constants.ts`
+
+#### 문제의 핵심
+
+`PLAN_AGENT_SYSTEM_PREPEND` (constants.ts 234-269행)에 구조적 결함이 있었습니다:
+
+1. **Interactive Mode 가정**
+   ```
+   2. After gathering context, ALWAYS present:
+      - Uncertainties: List of unclear points
+      - Clarifying Questions: Specific questions to resolve uncertainties
+   
+   3. ITERATE until ALL requirements are crystal clear:
+      - Do NOT proceed to planning until you have 100% clarity
+      - Ask the user to confirm your understanding
+   ```
+
+2. **종료 조건 없음**
+   - "100% clarity" 요구는 객관적 측정 불가능
+   - 사용자 확인 요청은 ULW mode에서 불가능
+   - 무한루프로 이어짐
+
+3. **ULW Mode 미감지**
+   - Subagent로 실행되는 경우를 구분하지 않음
+   - 항상 interactive mode로 동작 시도
+
+### 왜 무한루프가 발생했는가?
+
+```
+ULW Mode 시작
+  → Sisyphus가 Plan Agent 호출 (subagent)
+    → Plan Agent: "100% clarity 필요"
+      → Clarifying questions 생성
+        → 사용자 없음 (subagent)
+          → 다시 plan 생성 시도
+            → "여전히 unclear"
+              → 무한루프 반복
+```
+
+**핵심:** Plan Agent는 사용자와 대화하도록 설계되었지만, ULW mode에서는 사용자가 없는 subagent로 실행됨.
+
+---
+
+## ✅ 적용된 수정 방안
+
+### 수정 내용 (constants.ts)
+
+#### 1. SUBAGENT MODE DETECTION 섹션 추가
+
+```typescript
+SUBAGENT MODE DETECTION (CRITICAL):
+If you received a detailed prompt with gathered context from a parent orchestrator (e.g., Sisyphus):
+- You are running as a SUBAGENT
+- You CANNOT directly interact with the user
+- DO NOT ask clarifying questions - proceed with available information
+- Make reasonable assumptions for minor ambiguities
+- Generate the plan based on the provided context
+```
+
+#### 2. Context Gathering Protocol 수정
+
+```diff
+- 1. Launch background agents to gather context:
++ 1. Launch background agents to gather context (ONLY if not already provided):
+```
+
+**효과:** 이미 Sisyphus가 context를 수집한 경우 중복 방지
+
+#### 3. Clarifying Questions → Assumptions
+
+```diff
+- 2. After gathering context, ALWAYS present:
+-    - Uncertainties: List of unclear points
+-    - Clarifying Questions: Specific questions
++ 2. After gathering context, assess clarity:
++    - User Request Summary: Concise restatement
++    - Assumptions Made: List any assumptions for unclear points
+```
+
+**효과:** 질문 대신 가정 사항 문서화
+
+#### 4. 무한루프 방지 - 명확한 종료 조건
+
+```diff
+- 3. ITERATE until ALL requirements are crystal clear:
+-    - Do NOT proceed to planning until you have 100% clarity
+-    - Ask the user to confirm your understanding
+-    - Resolve every ambiguity before generating the work plan
++ 3. PROCEED TO PLAN GENERATION when:
++    - Core objective is understood (even if some details are ambiguous)
++    - You have gathered context via explore/librarian (or context was provided)
++    - You can make reasonable assumptions for remaining ambiguities
++    
++    DO NOT loop indefinitely waiting for perfect clarity.
++    DOCUMENT assumptions in the plan so they can be validated during execution.
+```
+
+**효과:**
+- "100% clarity" 요구 제거
+- 객관적인 진입 조건 제공
+- 무한루프 명시적 금지
+- Assumptions를 plan에 문서화하여 실행 중 검증 가능
+
+#### 5. 철학 변경
+
+```diff
+- REMEMBER: Vague requirements lead to failed implementations.
++ REMEMBER: A plan with documented assumptions is better than no plan.
+```
+
+**효과:** Perfectionism → Pragmatism
+
+---
+
+## 🎯 해결 메커니즘
+
+### Before (무한루프)
+
+```
+Plan Agent 시작
+  ↓
+Context gathering
+  ↓
+Requirements 명확한가?
+  ↓ NO
+Clarifying questions 생성
+  ↓
+사용자 응답 대기 (없음)
+  ↓
+다시 plan 시도
+  ↓
+(무한 반복)
+```
+
+### After (정상 종료)
+
+```
+Plan Agent 시작
+  ↓
+Subagent mode 감지?
+  ↓ YES
+Context 이미 있음? → YES
+  ↓
+Core objective 이해? → YES
+  ↓
+Reasonable assumptions 가능? → YES
+  ↓
+Plan 생성 (assumptions 문서화)
+  ↓
+완료 ✓
+```
+
+---
+
+## 📊 영향 분석
+
+### 해결되는 문제
+
+1. **ULW mode 무한루프** ✓
+2. **Sisyphus에서 Plan Agent 호출 시 블로킹** ✓
+3. **작은 토큰 반복 요청** ✓
+4. **1분마다 재시도** ✓
+
+### 부작용 없음
+
+- Interactive mode (사용자와 직접 대화)는 여전히 작동
+- Subagent mode일 때만 다르게 동작
+- Backward compatibility 유지
+
+### 추가 개선사항
+
+- Assumptions를 plan에 명시적으로 문서화
+- Execution 중 validation 가능
+- 더 pragmatic한 workflow
+
+---
+
+## 🧪 검증 방법
+
+### 테스트 시나리오
+
+1. **ULW mode에서 Plan Agent 호출**
+   ```bash
+   oh-my-opencode run "Complex task requiring planning. ulw"
+   ```
+   - 예상: Plan 생성 후 정상 종료
+   - 확인: 무한루프 없음
+
+2. **Interactive mode (변경 없어야 함)**
+   ```bash
+   oh-my-opencode run --agent prometheus "Design X"
+   ```
+   - 예상: Clarifying questions 여전히 가능
+   - 확인: 사용자와 대화 가능
+
+3. **Subagent context 제공 케이스**
+   - 예상: Context gathering skip
+   - 확인: 중복 탐색 없음
+
+---
+
+## 📝 수정된 파일
+
+```
+src/tools/delegate-task/constants.ts
+```
+
+### Diff Summary
+
+```diff
+@@ -234,22 +234,32 @@ export const PLAN_AGENT_SYSTEM_PREPEND = `<system>
++SUBAGENT MODE DETECTION (CRITICAL):
++[subagent 감지 및 처리 로직]
++
+ MANDATORY CONTEXT GATHERING PROTOCOL:
+-1. Launch background agents to gather context:
++1. Launch background agents (ONLY if not already provided):
+
+-2. After gathering context, ALWAYS present:
+-   - Uncertainties
+-   - Clarifying Questions
++2. After gathering context, assess clarity:
++   - Assumptions Made
+
+-3. ITERATE until ALL requirements are crystal clear:
+-   - Do NOT proceed until 100% clarity
+-   - Ask user to confirm
++3. PROCEED TO PLAN GENERATION when:
++   - Core objective understood
++   - Context gathered
++   - Reasonable assumptions possible
++   
++   DO NOT loop indefinitely.
++   DOCUMENT assumptions.
+```
+
+---
+
+## 🚀 권장 사항
+
+### Immediate Actions
+
+1. ✅ **수정 적용 완료** - constants.ts 업데이트됨
+2. ⏳ **테스트 수행** - ULW mode에서 동작 검증
+3. ⏳ **PR 생성** - code review 요청
+
+### Future Improvements
+
+1. **Subagent context 표준화**
+   - Subagent로 호출 시 명시적 플래그 전달
+   - `is_subagent: true` 파라미터 추가 고려
+
+2. **Assumptions validation workflow**
+   - Plan 실행 중 assumptions 검증 메커니즘
+   - Incorrect assumptions 감지 시 재계획
+
+3. **Timeout 메커니즘**
+   - Plan Agent가 X분 이상 걸리면 강제 종료
+   - Fallback plan 생성
+
+4. **Monitoring 추가**
+   - Plan Agent 실행 시간 측정
+   - Iteration 횟수 로깅
+   - 무한루프 조기 감지
+
+---
+
+## 📖 관련 코드 구조
+
+### Call Stack
+
+```
+Sisyphus (ULW mode)
+  ↓
+task(category="deep", ...)
+  ↓
+executor.ts: executeBackgroundContinuation()
+  ↓
+prompt-builder.ts: buildSystemContent()
+  ↓
+constants.ts: PLAN_AGENT_SYSTEM_PREPEND (문제 위치)
+  ↓
+Plan Agent 실행
+```
+
+### Key Functions
+
+1. **executor.ts:587** - `isPlanAgent()` 체크
+2. **prompt-builder.ts:11** - Plan Agent prepend 주입
+3. **constants.ts:234** - PLAN_AGENT_SYSTEM_PREPEND 정의
+
+---
+
+## 🎓 교훈
+
+### Design Lessons
+
+1. **Dual Mode Support**
+   - Interactive vs Autonomous mode 구분 필수
+   - Context 전달 방식 명확히
+
+2. **Avoid Perfectionism in Agents**
+   - "100% clarity" 같은 주관적 조건 지양
+   - 명확한 객관적 종료 조건 필요
+
+3. **Document Uncertainties**
+   - 불확실성을 숨기지 말고 문서화
+   - 실행 중 validation 가능하게
+
+4. **Infinite Loop Prevention**
+   - 모든 반복문에 명시적 종료 조건
+   - Timeout 또는 max iteration 설정
+
+---
+
+## 🔗 참고 자료
+
+- **Issue:** #1501 - [Bug]: ULW mode will 100% cause PLAN AGENT to get stuck
+- **Files Modified:** `src/tools/delegate-task/constants.ts`
+- **Related Concepts:** Ultrawork mode, Plan Agent, Subagent delegation
+- **Agent Architecture:** Sisyphus → Prometheus → Atlas workflow
+
+---
+
+## ✅ Conclusion
+
+**Root Cause:** Plan Agent가 interactive mode를 가정했으나 ULW mode에서는 subagent로 실행되어 사용자 상호작용 불가능. "100% clarity" 요구로 무한루프 발생.
+
+**Solution:** Subagent mode 감지 로직 추가, clarifying questions 제거, 명확한 종료 조건 제공, assumptions 문서화 방식 도입.
+
+**Result:** ULW mode에서 Plan Agent가 정상적으로 plan 생성 후 종료. 무한루프 해결.
+
+---
+
+**Status:** ✅ Fixed  
+**Tested:** ⏳ Pending  
+**Deployed:** ⏳ Pending  
+
+**Analyst:** Sisyphus (oh-my-opencode ultrawork mode)  
+**Date:** 2026-02-05  
+**Session:** fast-ember

package.json

@@ -1,6 +1,6 @@
 {
   "name": "oh-my-opencode",
-  "version": "3.2.2",
+  "version": "3.6.0",
   "description": "The Best AI Agent Harness - Batteries-Included OpenCode Plugin with Multi-Model Orchestration, Parallel Background Agents, and Crafted LSP/AST Tools",
   "main": "dist/index.js",
   "types": "dist/index.d.ts",
@@ -74,13 +74,13 @@
     "typescript": "^5.7.3"
   },
   "optionalDependencies": {
-    "oh-my-opencode-darwin-arm64": "3.2.2",
-    "oh-my-opencode-darwin-x64": "3.2.2",
-    "oh-my-opencode-linux-arm64": "3.2.2",
-    "oh-my-opencode-linux-arm64-musl": "3.2.2",
-    "oh-my-opencode-linux-x64": "3.2.2",
-    "oh-my-opencode-linux-x64-musl": "3.2.2",
-    "oh-my-opencode-windows-x64": "3.2.2"
+    "oh-my-opencode-darwin-arm64": "3.6.0",
+    "oh-my-opencode-darwin-x64": "3.6.0",
+    "oh-my-opencode-linux-arm64": "3.6.0",
+    "oh-my-opencode-linux-arm64-musl": "3.6.0",
+    "oh-my-opencode-linux-x64": "3.6.0",
+    "oh-my-opencode-linux-x64-musl": "3.6.0",
+    "oh-my-opencode-windows-x64": "3.6.0"
   },
   "trustedDependencies": [
     "@ast-grep/cli",

packages/darwin-arm64/package.json

@@ -1,6 +1,6 @@
 {
   "name": "oh-my-opencode-darwin-arm64",
-  "version": "3.2.2",
+  "version": "3.6.0",
   "description": "Platform-specific binary for oh-my-opencode (darwin-arm64)",
   "license": "MIT",
   "repository": {

packages/darwin-x64/package.json

@@ -1,6 +1,6 @@
 {
   "name": "oh-my-opencode-darwin-x64",
-  "version": "3.2.2",
+  "version": "3.6.0",
   "description": "Platform-specific binary for oh-my-opencode (darwin-x64)",
   "license": "MIT",
   "repository": {

packages/linux-arm64-musl/package.json

@@ -1,6 +1,6 @@
 {
   "name": "oh-my-opencode-linux-arm64-musl",
-  "version": "3.2.2",
+  "version": "3.6.0",
   "description": "Platform-specific binary for oh-my-opencode (linux-arm64-musl)",
   "license": "MIT",
   "repository": {

packages/linux-arm64/package.json

@@ -1,6 +1,6 @@
 {
   "name": "oh-my-opencode-linux-arm64",
-  "version": "3.2.2",
+  "version": "3.6.0",
   "description": "Platform-specific binary for oh-my-opencode (linux-arm64)",
   "license": "MIT",
   "repository": {

packages/linux-x64-musl/package.json

@@ -1,6 +1,6 @@
 {
   "name": "oh-my-opencode-linux-x64-musl",
-  "version": "3.2.2",
+  "version": "3.6.0",
   "description": "Platform-specific binary for oh-my-opencode (linux-x64-musl)",
   "license": "MIT",
   "repository": {

packages/linux-x64/package.json

@@ -1,6 +1,6 @@
 {
   "name": "oh-my-opencode-linux-x64",
-  "version": "3.2.2",
+  "version": "3.6.0",
   "description": "Platform-specific binary for oh-my-opencode (linux-x64)",
   "license": "MIT",
   "repository": {

packages/windows-x64/package.json

@@ -1,6 +1,6 @@
 {
   "name": "oh-my-opencode-windows-x64",
-  "version": "3.2.2",
+  "version": "3.6.0",
   "description": "Platform-specific binary for oh-my-opencode (windows-x64)",
   "license": "MIT",
   "repository": {

script/build-schema-document.ts

@@ -0,0 +1,17 @@
+import * as z from "zod"
+import { OhMyOpenCodeConfigSchema } from "../src/config/schema"
+
+export function createOhMyOpenCodeJsonSchema(): Record<string, unknown> {
+  const jsonSchema = z.toJSONSchema(OhMyOpenCodeConfigSchema, {
+    target: "draft-07",
+    unrepresentable: "any",
+  })
+
+  return {
+    $schema: "http://json-schema.org/draft-07/schema#",
+    $id: "https://raw.githubusercontent.com/code-yeongyu/oh-my-opencode/master/assets/oh-my-opencode.schema.json",
+    title: "Oh My OpenCode Configuration",
+    description: "Configuration schema for oh-my-opencode plugin",
+    ...jsonSchema,
+  }
+}

script/build-schema.test.ts

@@ -0,0 +1,18 @@
+import { describe, expect, test } from "bun:test"
+import { createOhMyOpenCodeJsonSchema } from "./build-schema-document"
+
+describe("build-schema-document", () => {
+  test("generates schema with skills property", () => {
+    // given
+    const expectedDraft = "http://json-schema.org/draft-07/schema#"
+
+    // when
+    const schema = createOhMyOpenCodeJsonSchema()
+
+    // then
+    expect(schema.$schema).toBe(expectedDraft)
+    expect(schema.title).toBe("Oh My OpenCode Configuration")
+    expect(schema.properties).toBeDefined()
+    expect(schema.properties.skills).toBeDefined()
+  })
+})

script/build-schema.ts

@@ -1,24 +1,12 @@
 #!/usr/bin/env bun
-import * as z from "zod"
-import { OhMyOpenCodeConfigSchema } from "../src/config/schema"
+import { createOhMyOpenCodeJsonSchema } from "./build-schema-document"
 
 const SCHEMA_OUTPUT_PATH = "assets/oh-my-opencode.schema.json"
 
 async function main() {
   console.log("Generating JSON Schema...")
 
-  const jsonSchema = z.toJSONSchema(OhMyOpenCodeConfigSchema, {
-    io: "input",
-    target: "draft-7",
-  })
-
-  const finalSchema = {
-    $schema: "http://json-schema.org/draft-07/schema#",
-    $id: "https://raw.githubusercontent.com/code-yeongyu/oh-my-opencode/master/assets/oh-my-opencode.schema.json",
-    title: "Oh My OpenCode Configuration",
-    description: "Configuration schema for oh-my-opencode plugin",
-    ...jsonSchema,
-  }
+  const finalSchema = createOhMyOpenCodeJsonSchema()
 
   await Bun.write(SCHEMA_OUTPUT_PATH, JSON.stringify(finalSchema, null, 2))
 

signatures/cla.json

@@ -1127,6 +1127,406 @@
       "created_at": "2026-02-02T16:58:50Z",
       "repoId": 1108837393,
       "pullRequestNo": 1399
+    },
+    {
+      "name": "ilarvne",
+      "id": 99905590,
+      "comment_id": 3839771590,
+      "created_at": "2026-02-03T08:15:37Z",
+      "repoId": 1108837393,
+      "pullRequestNo": 1422
+    },
+    {
+      "name": "ualtinok",
+      "id": 94532,
+      "comment_id": 3841078284,
+      "created_at": "2026-02-03T12:39:59Z",
+      "repoId": 1108837393,
+      "pullRequestNo": 1393
+    },
+    {
+      "name": "Stranmor",
+      "id": 49376798,
+      "comment_id": 3841465375,
+      "created_at": "2026-02-03T13:53:13Z",
+      "repoId": 1108837393,
+      "pullRequestNo": 1432
+    },
+    {
+      "name": "sk0x0y",
+      "id": 35445665,
+      "comment_id": 3841625993,
+      "created_at": "2026-02-03T14:21:26Z",
+      "repoId": 1108837393,
+      "pullRequestNo": 1434
+    },
+    {
+      "name": "filipemsilv4",
+      "id": 59426206,
+      "comment_id": 3841722121,
+      "created_at": "2026-02-03T14:38:07Z",
+      "repoId": 1108837393,
+      "pullRequestNo": 1435
+    },
+    {
+      "name": "wydrox",
+      "id": 79707825,
+      "comment_id": 3842392636,
+      "created_at": "2026-02-03T16:39:35Z",
+      "repoId": 1108837393,
+      "pullRequestNo": 1436
+    },
+    {
+      "name": "kaizen403",
+      "id": 134706404,
+      "comment_id": 3843559932,
+      "created_at": "2026-02-03T20:44:25Z",
+      "repoId": 1108837393,
+      "pullRequestNo": 1449
+    },
+    {
+      "name": "BowTiedSwan",
+      "id": 86532747,
+      "comment_id": 3742668781,
+      "created_at": "2026-01-13T08:05:00Z",
+      "repoId": 1108837393,
+      "pullRequestNo": 741
+    },
+    {
+      "name": "Mang-Joo",
+      "id": 86056915,
+      "comment_id": 3855493558,
+      "created_at": "2026-02-05T18:41:49Z",
+      "repoId": 1108837393,
+      "pullRequestNo": 1526
+    },
+    {
+      "name": "shaunmorris",
+      "id": 579820,
+      "comment_id": 3858265174,
+      "created_at": "2026-02-06T06:23:24Z",
+      "repoId": 1108837393,
+      "pullRequestNo": 1541
+    },
+    {
+      "name": "itsnebulalol",
+      "id": 18669106,
+      "comment_id": 3864672624,
+      "created_at": "2026-02-07T15:10:54Z",
+      "repoId": 1108837393,
+      "pullRequestNo": 1622
+    },
+    {
+      "name": "mkusaka",
+      "id": 24956031,
+      "comment_id": 3864822328,
+      "created_at": "2026-02-07T16:54:36Z",
+      "repoId": 1108837393,
+      "pullRequestNo": 1629
+    },
+    {
+      "name": "quantmind-br",
+      "id": 170503374,
+      "comment_id": 3865064441,
+      "created_at": "2026-02-07T18:38:24Z",
+      "repoId": 1108837393,
+      "pullRequestNo": 1634
+    },
+    {
+      "name": "QiRaining",
+      "id": 13825001,
+      "comment_id": 3865979224,
+      "created_at": "2026-02-08T02:34:46Z",
+      "repoId": 1108837393,
+      "pullRequestNo": 1641
+    },
+    {
+      "name": "JunyeongChoi0",
+      "id": 99778164,
+      "comment_id": 3867461224,
+      "created_at": "2026-02-08T16:02:31Z",
+      "repoId": 1108837393,
+      "pullRequestNo": 1674
+    },
+    {
+      "name": "aliozdenisik",
+      "id": 106994209,
+      "comment_id": 3867619266,
+      "created_at": "2026-02-08T17:12:34Z",
+      "repoId": 1108837393,
+      "pullRequestNo": 1676
+    },
+    {
+      "name": "mrm007",
+      "id": 3297808,
+      "comment_id": 3868350953,
+      "created_at": "2026-02-08T21:41:35Z",
+      "repoId": 1108837393,
+      "pullRequestNo": 1680
+    },
+    {
+      "name": "nianyi778",
+      "id": 23355645,
+      "comment_id": 3874840250,
+      "created_at": "2026-02-10T01:41:08Z",
+      "repoId": 1108837393,
+      "pullRequestNo": 1703
+    },
+    {
+      "name": "lxia1220",
+      "id": 43934024,
+      "comment_id": 3875675071,
+      "created_at": "2026-02-10T06:43:35Z",
+      "repoId": 1108837393,
+      "pullRequestNo": 1713
+    },
+    {
+      "name": "cyberprophet",
+      "id": 48705422,
+      "comment_id": 3877193956,
+      "created_at": "2026-02-10T12:06:03Z",
+      "repoId": 1108837393,
+      "pullRequestNo": 1717
+    },
+    {
+      "name": "materializerx",
+      "id": 96932157,
+      "comment_id": 3878329143,
+      "created_at": "2026-02-10T15:07:38Z",
+      "repoId": 1108837393,
+      "pullRequestNo": 1724
+    },
+    {
+      "name": "materializerx",
+      "id": 96932157,
+      "comment_id": 3878458939,
+      "created_at": "2026-02-10T15:21:04Z",
+      "repoId": 1108837393,
+      "pullRequestNo": 1724
+    },
+    {
+      "name": "RobertWsp",
+      "id": 67512895,
+      "comment_id": 3878518426,
+      "created_at": "2026-02-10T15:27:01Z",
+      "repoId": 1108837393,
+      "pullRequestNo": 1723
+    },
+    {
+      "name": "RobertWsp",
+      "id": 67512895,
+      "comment_id": 3878575833,
+      "created_at": "2026-02-10T15:32:31Z",
+      "repoId": 1108837393,
+      "pullRequestNo": 1723
+    },
+    {
+      "name": "sjawhar",
+      "id": 5074378,
+      "comment_id": 3879746658,
+      "created_at": "2026-02-10T17:43:47Z",
+      "repoId": 1108837393,
+      "pullRequestNo": 1727
+    },
+    {
+      "name": "marlon-costa-dc",
+      "id": 128386606,
+      "comment_id": 3879827362,
+      "created_at": "2026-02-10T17:59:06Z",
+      "repoId": 1108837393,
+      "pullRequestNo": 1726
+    },
+    {
+      "name": "marlon-costa-dc",
+      "id": 128386606,
+      "comment_id": 3879847814,
+      "created_at": "2026-02-10T18:03:41Z",
+      "repoId": 1108837393,
+      "pullRequestNo": 1726
+    },
+    {
+      "name": "danpung2",
+      "id": 75434746,
+      "comment_id": 3881834946,
+      "created_at": "2026-02-11T02:52:34Z",
+      "repoId": 1108837393,
+      "pullRequestNo": 1741
+    },
+    {
+      "name": "ojh102",
+      "id": 14901903,
+      "comment_id": 3882254163,
+      "created_at": "2026-02-11T05:29:51Z",
+      "repoId": 1108837393,
+      "pullRequestNo": 1750
+    },
+    {
+      "name": "uyu423",
+      "id": 8033320,
+      "comment_id": 3884127858,
+      "created_at": "2026-02-11T12:30:37Z",
+      "repoId": 1108837393,
+      "pullRequestNo": 1762
+    },
+    {
+      "name": "WietRob",
+      "id": 203506602,
+      "comment_id": 3859280254,
+      "created_at": "2026-02-06T10:00:03Z",
+      "repoId": 1108837393,
+      "pullRequestNo": 1529
+    },
+    {
+      "name": "COLDTURNIP",
+      "id": 46220,
+      "comment_id": 3884966424,
+      "created_at": "2026-02-11T14:54:46Z",
+      "repoId": 1108837393,
+      "pullRequestNo": 1765
+    },
+    {
+      "name": "tcarac",
+      "id": 64477810,
+      "comment_id": 3885026481,
+      "created_at": "2026-02-11T15:03:25Z",
+      "repoId": 1108837393,
+      "pullRequestNo": 1766
+    },
+    {
+      "name": "youngbinkim0",
+      "id": 64558592,
+      "comment_id": 3887466814,
+      "created_at": "2026-02-11T22:03:00Z",
+      "repoId": 1108837393,
+      "pullRequestNo": 1777
+    },
+    {
+      "name": "raki-1203",
+      "id": 52475378,
+      "comment_id": 3889111683,
+      "created_at": "2026-02-12T07:27:39Z",
+      "repoId": 1108837393,
+      "pullRequestNo": 1790
+    },
+    {
+      "name": "G36maid",
+      "id": 53391375,
+      "comment_id": 3889208379,
+      "created_at": "2026-02-12T07:56:21Z",
+      "repoId": 1108837393,
+      "pullRequestNo": 1791
+    },
+    {
+      "name": "solssak",
+      "id": 107416133,
+      "comment_id": 3889740003,
+      "created_at": "2026-02-12T09:28:09Z",
+      "repoId": 1108837393,
+      "pullRequestNo": 1794
+    },
+    {
+      "name": "bvanderhorn",
+      "id": 9591412,
+      "comment_id": 3890297580,
+      "created_at": "2026-02-12T11:17:38Z",
+      "repoId": 1108837393,
+      "pullRequestNo": 1799
+    },
+    {
+      "name": "jardo5",
+      "id": 22041729,
+      "comment_id": 3890810423,
+      "created_at": "2026-02-12T12:57:06Z",
+      "repoId": 1108837393,
+      "pullRequestNo": 1802
+    },
+    {
+      "name": "willy-scr",
+      "id": 187001140,
+      "comment_id": 3894534811,
+      "created_at": "2026-02-13T02:56:20Z",
+      "repoId": 1108837393,
+      "pullRequestNo": 1809
+    },
+    {
+      "name": "professional-ALFIE",
+      "id": 219141081,
+      "comment_id": 3897671676,
+      "created_at": "2026-02-13T15:00:01Z",
+      "repoId": 1108837393,
+      "pullRequestNo": 1820
+    },
+    {
+      "name": "Strocs",
+      "id": 71996940,
+      "comment_id": 3898248552,
+      "created_at": "2026-02-13T16:56:54Z",
+      "repoId": 1108837393,
+      "pullRequestNo": 1822
+    },
+    {
+      "name": "cloudwaddie-agent",
+      "id": 261346076,
+      "comment_id": 3900805128,
+      "created_at": "2026-02-14T04:15:19Z",
+      "repoId": 1108837393,
+      "pullRequestNo": 1827
+    },
+    {
+      "name": "morphaxl",
+      "id": 57144942,
+      "comment_id": 3872741516,
+      "created_at": "2026-02-09T16:21:56Z",
+      "repoId": 1108837393,
+      "pullRequestNo": 1699
+    },
+    {
+      "name": "morphaxl",
+      "id": 57144942,
+      "comment_id": 3872742242,
+      "created_at": "2026-02-09T16:22:04Z",
+      "repoId": 1108837393,
+      "pullRequestNo": 1699
+    },
+    {
+      "name": "liu-qingyuan",
+      "id": 57737268,
+      "comment_id": 3902402078,
+      "created_at": "2026-02-14T19:39:58Z",
+      "repoId": 1108837393,
+      "pullRequestNo": 1844
+    },
+    {
+      "name": "iyoda",
+      "id": 31020,
+      "comment_id": 3902426789,
+      "created_at": "2026-02-14T19:58:19Z",
+      "repoId": 1108837393,
+      "pullRequestNo": 1845
+    },
+    {
+      "name": "Decrabbityyy",
+      "id": 99632363,
+      "comment_id": 3904649522,
+      "created_at": "2026-02-15T15:07:11Z",
+      "repoId": 1108837393,
+      "pullRequestNo": 1864
+    },
+    {
+      "name": "dankochetov",
+      "id": 33990502,
+      "comment_id": 3905398332,
+      "created_at": "2026-02-15T23:17:05Z",
+      "repoId": 1108837393,
+      "pullRequestNo": 1870
+    },
+    {
+      "name": "xinpengdr",
+      "id": 1885607,
+      "comment_id": 3910093356,
+      "created_at": "2026-02-16T19:01:33Z",
+      "repoId": 1108837393,
+      "pullRequestNo": 1906
     }
   ]
 }

sisyphus-prompt.md

@@ -7,7 +7,7 @@
 
 | Field | Value |
 |-------|-------|
-| Model | `anthropic/claude-opus-4-5` |
+| Model | `anthropic/claude-opus-4-6` |
 | Max Tokens | `64000` |
 | Mode | `primary` |
 | Thinking | Budget: 32000 |
@@ -212,7 +212,7 @@ Search **external references** (docs, OSS, web). Fire proactively when unfamilia
 - "Working with unfamiliar npm/pip/cargo packages"
 ### Pre-Delegation Planning (MANDATORY)
 
-**BEFORE every `delegate_task` call, EXPLICITLY declare your reasoning.**
+**BEFORE every `task` call, EXPLICITLY declare your reasoning.**
 
 #### Step 1: Identify Task Requirements
 
@@ -236,7 +236,7 @@ Ask yourself:
 **MANDATORY FORMAT:**
 
 ```
-I will use delegate_task with:
+I will use task with:
 - **Category**: [selected-category-name]
 - **Why this category**: [how category description matches task domain]
 - **load_skills**: [list of selected skills]
@@ -246,14 +246,14 @@ I will use delegate_task with:
 - **Expected Outcome**: [what success looks like]
 ```
 
-**Then** make the delegate_task call.
+**Then** make the task call.
 
 #### Examples
 
 **CORRECT: Full Evaluation**
 
 ```
-I will use delegate_task with:
+I will use task with:
 - **Category**: [category-name]
 - **Why this category**: Category description says "[quote description]" which matches this task's requirements
 - **load_skills**: ["skill-a", "skill-b"]
@@ -263,9 +263,11 @@ I will use delegate_task with:
   - skill-c: OMITTED - description says "[quote]" which doesn't apply because [reason]
 - **Expected Outcome**: [concrete deliverable]
 
-delegate_task(
+task(
   category="[category-name]",
   load_skills=["skill-a", "skill-b"],
+  description="[short task description]",
+  run_in_background=false,
   prompt="..."
 )
 ```
@@ -273,14 +275,16 @@ delegate_task(
 **CORRECT: Agent-Specific (for exploration/consultation)**
 
 ```
-I will use delegate_task with:
+I will use task with:
 - **Agent**: [agent-name]
 - **Reason**: This requires [agent's specialty] based on agent description
 - **load_skills**: [] (agents have built-in expertise)
 - **Expected Outcome**: [what agent should return]
 
-delegate_task(
+task(
   subagent_type="[agent-name]",
+  description="[short task description]",
+  run_in_background=false,
   load_skills=[],
   prompt="..."
 )
@@ -289,14 +293,15 @@ delegate_task(
 **CORRECT: Background Exploration**
 
 ```
-I will use delegate_task with:
+I will use task with:
 - **Agent**: explore
 - **Reason**: Need to find all authentication implementations across the codebase - this is contextual grep
 - **load_skills**: []
 - **Expected Outcome**: List of files containing auth patterns
 
-delegate_task(
+task(
   subagent_type="explore",
+  description="Find auth implementations",
   run_in_background=true,
   load_skills=[],
   prompt="Find all authentication implementations in the codebase"
@@ -306,7 +311,7 @@ delegate_task(
 **WRONG: No Skill Evaluation**
 
 ```
-delegate_task(category="...", load_skills=[], prompt="...")  // Where's the justification?
+task(category="...", load_skills=[], prompt="...")  // Where's the justification?
 ```
 
 **WRONG: Vague Category Selection**
@@ -317,7 +322,7 @@ I'll use this category because it seems right.
 
 #### Enforcement
 
-**BLOCKING VIOLATION**: If you call `delegate_task` without:
+**BLOCKING VIOLATION**: If you call `task` without:
 1. Explaining WHY category was selected (based on description)
 2. Evaluating EACH available skill for relevance
 
@@ -329,15 +334,15 @@ I'll use this category because it seems right.
 ```typescript
 // CORRECT: Always background, always parallel
 // Contextual Grep (internal)
-delegate_task(subagent_type="explore", run_in_background=true, load_skills=[], prompt="Find auth implementations in our codebase...")
-delegate_task(subagent_type="explore", run_in_background=true, load_skills=[], prompt="Find error handling patterns here...")
+task(subagent_type="explore", description="Find auth implementations", run_in_background=true, load_skills=[], prompt="Find auth implementations in our codebase...")
+task(subagent_type="explore", description="Find error handling patterns", run_in_background=true, load_skills=[], prompt="Find error handling patterns here...")
 // Reference Grep (external)
-delegate_task(subagent_type="librarian", run_in_background=true, load_skills=[], prompt="Find JWT best practices in official docs...")
-delegate_task(subagent_type="librarian", run_in_background=true, load_skills=[], prompt="Find how production apps handle auth in Express...")
+task(subagent_type="librarian", description="Find JWT best practices", run_in_background=true, load_skills=[], prompt="Find JWT best practices in official docs...")
+task(subagent_type="librarian", description="Find Express auth patterns", run_in_background=true, load_skills=[], prompt="Find how production apps handle auth in Express...")
 // Continue working immediately. Collect with background_output when needed.
 
 // WRONG: Sequential or blocking
-result = delegate_task(...)  // Never wait synchronously for explore/librarian
+result = task(...)  // Never wait synchronously for explore/librarian
 ```
 
 ### Background Result Collection:
@@ -347,16 +352,16 @@ result = delegate_task(...)  // Never wait synchronously for explore/librarian
 4. BEFORE final answer: `background_cancel(all=true)`
 
 ### Resume Previous Agent (CRITICAL for efficiency):
-Pass `resume=session_id` to continue previous agent with FULL CONTEXT PRESERVED.
+Pass `session_id` to continue previous agent with FULL CONTEXT PRESERVED.
 
-**ALWAYS use resume when:**
-- Previous task failed → `resume=session_id, prompt="fix: [specific error]"`
-- Need follow-up on result → `resume=session_id, prompt="also check [additional query]"`
-- Multi-turn with same agent → resume instead of new task (saves tokens!)
+**ALWAYS use session_id when:**
+- Previous task failed → `session_id="ses_xxx", prompt="fix: [specific error]"`
+- Need follow-up on result → `session_id="ses_xxx", prompt="also check [additional query]"`
+- Multi-turn with same agent → session_id instead of new task (saves tokens!)
 
 **Example:**
 ```
-delegate_task(resume="ses_abc123", prompt="The previous search missed X. Also look for Y.")
+task(session_id="ses_abc123", description="Follow-up search", run_in_background=false, load_skills=[], prompt="The previous search missed X. Also look for Y.")
 ```
 
 ### Search Stop Conditions
@@ -377,7 +382,7 @@ STOP searching when:
 3. Mark `completed` as soon as done (don't batch) - OBSESSIVELY TRACK YOUR WORK USING TODO TOOLS
 ### Category + Skills Delegation System
 
-**delegate_task() combines categories and skills for optimal task execution.**
+**task() combines categories and skills for optimal task execution.**
 
 #### Available Categories (Domain-Optimized Models)
 
@@ -442,7 +447,7 @@ SKILL EVALUATION for "[skill-name]":
 ### Delegation Pattern
 
 ```typescript
-delegate_task(
+task(
   category="[selected-category]",
   load_skills=["skill-1", "skill-2"],  // Include ALL relevant skills
   prompt="..."
@@ -451,7 +456,7 @@ delegate_task(
 
 **ANTI-PATTERN (will produce poor results):**
 ```typescript
-delegate_task(category="...", load_skills=[], prompt="...")  // Empty load_skills without justification
+task(category="...", load_skills=[], prompt="...")  // Empty load_skills without justification
 ```
 ### Delegation Table:
 

src/AGENTS.md

@@ -0,0 +1,81 @@
+# SRC KNOWLEDGE BASE
+
+## OVERVIEW
+
+Main plugin entry point and orchestration layer. Plugin initialization, hook registration, tool composition, and lifecycle management.
+
+## STRUCTURE
+
+```
+src/
+├── index.ts                          # Main plugin entry (106 lines) — OhMyOpenCodePlugin factory
+├── create-hooks.ts                   # Hook coordination: core, continuation, skill (62 lines)
+├── create-managers.ts                # Manager initialization: Tmux, Background, SkillMcp, Config (80 lines)
+├── create-tools.ts                   # Tool registry + skill context composition (54 lines)
+├── plugin-interface.ts               # Plugin interface assembly — 7 OpenCode hooks (66 lines)
+├── plugin-config.ts                  # Config loading orchestration (user + project merge, 180 lines)
+├── plugin-state.ts                   # Model cache state (context limits, anthropic 1M flag, 12 lines)
+├── agents/                           # 11 AI agents (32 files) — see agents/AGENTS.md
+├── cli/                              # CLI installer, doctor (107+ files) — see cli/AGENTS.md
+├── config/                           # Zod schema (21 component files) — see config/AGENTS.md
+├── features/                         # Background agents, skills, commands (18 dirs) — see features/AGENTS.md
+├── hooks/                            # 41 lifecycle hooks (36 dirs) — see hooks/AGENTS.md
+├── mcp/                              # Built-in MCPs (6 files) — see mcp/AGENTS.md
+├── plugin/                           # Plugin interface composition (21 files)
+├── plugin-handlers/                  # Config loading, plan inheritance (15 files) — see plugin-handlers/AGENTS.md
+├── shared/                           # Cross-cutting utilities (96 files) — see shared/AGENTS.md
+└── tools/                            # 26 tools (14 dirs) — see tools/AGENTS.md
+```
+
+## PLUGIN INITIALIZATION (10 steps)
+
+1. `injectServerAuthIntoClient(ctx.client)` — Auth injection
+2. `startTmuxCheck()` — Tmux availability
+3. `loadPluginConfig(ctx.directory, ctx)` — User + project config merge → Zod validation
+4. `createFirstMessageVariantGate()` — First message variant override gate
+5. `createModelCacheState()` — Model context limits cache
+6. `createManagers(...)` → 4 managers:
+   - `TmuxSessionManager` — Multi-pane tmux sessions
+   - `BackgroundManager` — Parallel subagent execution
+   - `SkillMcpManager` — MCP server lifecycle
+   - `ConfigHandler` — Plugin config API to OpenCode
+7. `createTools(...)` → `createSkillContext()` + `createAvailableCategories()` + `createToolRegistry()`
+8. `createHooks(...)` → `createCoreHooks()` + `createContinuationHooks()` + `createSkillHooks()`
+9. `createPluginInterface(...)` → 7 OpenCode hook handlers
+10. Return plugin with `experimental.session.compacting`
+
+## HOOK REGISTRATION (3 tiers)
+
+**Core Hooks** (`create-core-hooks.ts`):
+- Session (20): context-window-monitor, session-recovery, think-mode, ralph-loop, anthropic-effort, ...
+- Tool Guard (8): comment-checker, tool-output-truncator, rules-injector, write-existing-file-guard, ...
+- Transform (4): claude-code-hooks, keyword-detector, context-injector, thinking-block-validator
+
+**Continuation Hooks** (`create-continuation-hooks.ts`):
+- 7 hooks: stop-continuation-guard, compaction-context-injector, todo-continuation-enforcer, atlas, ...
+
+**Skill Hooks** (`create-skill-hooks.ts`):
+- 2 hooks: category-skill-reminder, auto-slash-command
+
+## PLUGIN INTERFACE (7 OpenCode handlers)
+
+| Handler | Source | Purpose |
+|---------|--------|---------|
+| `tool` | filteredTools | All registered tools |
+| `chat.params` | createChatParamsHandler | Anthropic effort level |
+| `chat.message` | createChatMessageHandler | First message variant, session setup |
+| `experimental.chat.messages.transform` | createMessagesTransformHandler | Context injection, keyword detection |
+| `config` | configHandler | Agent/MCP/command registration |
+| `event` | createEventHandler | Session lifecycle |
+| `tool.execute.before` | createToolExecuteBeforeHandler | Pre-tool hooks |
+| `tool.execute.after` | createToolExecuteAfterHandler | Post-tool hooks |
+
+## SAFE HOOK CREATION PATTERN
+
+```typescript
+const hook = isHookEnabled("hook-name")
+  ? safeCreateHook("hook-name", () => createHookFactory(ctx), { enabled: safeHookEnabled })
+  : null;
+```
+
+All hooks use this pattern for graceful degradation on failure.

src/agents/AGENTS.md

@@ -2,72 +2,84 @@
 
 ## OVERVIEW
 
-11 AI agents for multi-model orchestration. Each agent has factory function + metadata + fallback chains.
-
-**Primary Agents** (respect UI model selection):
-- Sisyphus, Atlas, Prometheus
-
-**Subagents** (use own fallback chains):
-- Hephaestus, Oracle, Librarian, Explore, Multimodal-Looker, Metis, Momus, Sisyphus-Junior
+11 AI agents with factory functions, fallback chains, and model-specific prompt variants. Each agent has metadata (category, cost, triggers) and configurable tool restrictions.
 
 ## STRUCTURE
 ```
 agents/
-├── atlas.ts                    # Master Orchestrator (holds todo list)
-├── sisyphus.ts                 # Main prompt (SF Bay Area engineer identity)
-├── hephaestus.ts               # Autonomous Deep Worker (GPT 5.2 Codex, "The Legitimate Craftsman")
-├── sisyphus-junior.ts          # Delegated task executor (category-spawned)
-├── oracle.ts                   # Strategic advisor (GPT-5.2)
-├── librarian.ts                # Multi-repo research (GitHub CLI, Context7)
-├── explore.ts                  # Fast contextual grep (Grok Code Fast)
-├── multimodal-looker.ts        # Media analyzer (Gemini 3 Flash)
-├── prometheus-prompt.ts        # Planning (Interview/Consultant mode, 1283 lines)
-├── metis.ts                    # Pre-planning analysis (Gap detection)
-├── momus.ts                    # Plan reviewer (Ruthless fault-finding)
-├── dynamic-agent-prompt-builder.ts  # Dynamic prompt generation
-├── types.ts                    # AgentModelConfig, AgentPromptMetadata
-├── utils.ts                    # createBuiltinAgents(), resolveModelWithFallback()
-└── index.ts                    # builtinAgents export
+├── sisyphus.ts                 # Main orchestrator (559 lines)
+├── hephaestus.ts               # Autonomous deep worker (651 lines)
+├── oracle.ts                   # Strategic advisor (171 lines)
+├── librarian.ts                # Multi-repo research (329 lines)
+├── explore.ts                  # Fast codebase grep (125 lines)
+├── multimodal-looker.ts        # Media analyzer (59 lines)
+├── metis.ts                    # Pre-planning analysis (347 lines)
+├── momus.ts                    # Plan validator (244 lines)
+├── atlas/                      # Master orchestrator (agent.ts + default.ts + gpt.ts)
+├── prometheus/                 # Planning agent (8 files, plan-template 423 lines)
+├── sisyphus-junior/            # Delegated task executor (agent.ts + default.ts + gpt.ts)
+├── dynamic-agent-prompt-builder.ts  # Dynamic prompt generation (433 lines)
+├── builtin-agents/             # Agent registry + model resolution
+├── agent-builder.ts            # Agent construction with category merging (51 lines)
+├── utils.ts                    # Agent creation, model fallback resolution (571 lines)
+├── types.ts                    # AgentModelConfig, AgentPromptMetadata (106 lines)
+└── index.ts                    # Exports
 ```
 
 ## AGENT MODELS
-| Agent | Model | Temp | Purpose |
-|-------|-------|------|---------|
-| Sisyphus | anthropic/claude-opus-4-5 | 0.1 | Primary orchestrator (fallback: kimi-k2.5 → glm-4.7 → gpt-5.2-codex → gemini-3-pro) |
-| Hephaestus | openai/gpt-5.2-codex | 0.1 | Autonomous deep worker, "The Legitimate Craftsman" (requires gpt-5.2-codex, no fallback) |
-| Atlas | anthropic/claude-sonnet-4-5 | 0.1 | Master orchestrator (fallback: kimi-k2.5 → gpt-5.2) |
-| oracle | openai/gpt-5.2 | 0.1 | Consultation, debugging |
-| librarian | zai-coding-plan/glm-4.7 | 0.1 | Docs, GitHub search (fallback: glm-4.7-free) |
-| explore | xai/grok-code-fast-1 | 0.1 | Fast contextual grep (fallback: claude-haiku-4-5 → gpt-5-mini → gpt-5-nano) |
-| multimodal-looker | google/gemini-3-flash | 0.1 | PDF/image analysis |
-| Prometheus | anthropic/claude-opus-4-5 | 0.1 | Strategic planning (fallback: kimi-k2.5 → gpt-5.2) |
-| Metis | anthropic/claude-opus-4-5 | 0.3 | Pre-planning analysis (fallback: kimi-k2.5 → gpt-5.2) |
-| Momus | openai/gpt-5.2 | 0.1 | Plan validation (fallback: claude-opus-4-5) |
-| Sisyphus-Junior | anthropic/claude-sonnet-4-5 | 0.1 | Category-spawned executor |
 
-## HOW TO ADD
-1. Create `src/agents/my-agent.ts` exporting factory + metadata.
-2. Add to `agentSources` in `src/agents/utils.ts`.
-3. Update `AgentNameSchema` in `src/config/schema.ts`.
-4. Register in `src/index.ts` initialization.
+| Agent | Model | Temp | Fallback Chain | Cost |
+|-------|-------|------|----------------|------|
+| Sisyphus | claude-opus-4-6 | 0.1 | kimi-k2.5 → glm-4.7 → gpt-5.3-codex → gemini-3-pro | EXPENSIVE |
+| Hephaestus | gpt-5.3-codex | 0.1 | NONE (required) | EXPENSIVE |
+| Atlas | claude-sonnet-4-5 | 0.1 | kimi-k2.5 → gpt-5.2 | EXPENSIVE |
+| Prometheus | claude-opus-4-6 | 0.1 | kimi-k2.5 → gpt-5.2 | EXPENSIVE |
+| oracle | gpt-5.2 | 0.1 | claude-opus-4-6 | EXPENSIVE |
+| librarian | glm-4.7 | 0.1 | glm-4.7-free | CHEAP |
+| explore | grok-code-fast-1 | 0.1 | claude-haiku-4-5 → gpt-5-mini → gpt-5-nano | FREE |
+| multimodal-looker | gemini-3-flash | 0.1 | NONE | CHEAP |
+| Metis | claude-opus-4-6 | 0.3 | kimi-k2.5 → gpt-5.2 | EXPENSIVE |
+| Momus | gpt-5.2 | 0.1 | claude-opus-4-6 | EXPENSIVE |
+| Sisyphus-Junior | claude-sonnet-4-5 | 0.1 | (user-configurable) | EXPENSIVE |
 
 ## TOOL RESTRICTIONS
-| Agent | Denied Tools |
-|-------|-------------|
-| oracle | write, edit, task, delegate_task |
-| librarian | write, edit, task, delegate_task, call_omo_agent |
-| explore | write, edit, task, delegate_task, call_omo_agent |
-| multimodal-looker | Allowlist: read only |
-| Sisyphus-Junior | task, delegate_task |
 
-## PATTERNS
-- **Factory**: `createXXXAgent(model: string): AgentConfig`
-- **Metadata**: `XXX_PROMPT_METADATA` with category, cost, triggers.
-- **Tool restrictions**: `createAgentToolRestrictions(tools)` or `createAgentToolAllowlist(tools)`.
-- **Thinking**: 32k budget tokens for Sisyphus, Oracle, Prometheus, Atlas.
+| Agent | Denied | Allowed |
+|-------|--------|---------|
+| oracle | write, edit, task, call_omo_agent | Read-only consultation |
+| librarian | write, edit, task, call_omo_agent | Research tools only |
+| explore | write, edit, task, call_omo_agent | Search tools only |
+| multimodal-looker | ALL except `read` | Vision-only |
+| Sisyphus-Junior | task | No delegation |
+| Atlas | task, call_omo_agent | Orchestration only |
+
+## THINKING / REASONING
+
+| Agent | Claude | GPT |
+|-------|--------|-----|
+| Sisyphus | 32k budget tokens | reasoningEffort: "medium" |
+| Hephaestus | — | reasoningEffort: "medium" |
+| Oracle | 32k budget tokens | reasoningEffort: "medium" |
+| Metis | 32k budget tokens | — |
+| Momus | 32k budget tokens | reasoningEffort: "medium" |
+| Sisyphus-Junior | 32k budget tokens | reasoningEffort: "medium" |
+
+## KEY PROMPT PATTERNS
+
+- **Sisyphus/Hephaestus**: Dynamic prompts via `dynamic-agent-prompt-builder.ts` injecting available tools/skills/categories
+- **Atlas, Sisyphus-Junior**: Model-specific prompts (Claude vs GPT variants)
+- **Prometheus**: 6-section modular prompt (identity → interview → plan-generation → high-accuracy → template → behavioral)
+
+## HOW TO ADD
+
+1. Create `src/agents/my-agent.ts` exporting factory + metadata
+2. Add to `agentSources` in `src/agents/builtin-agents/`
+3. Update `AgentNameSchema` in `src/config/schema/agent-names.ts`
+4. Register in `src/plugin-handlers/agent-config-handler.ts`
 
 ## ANTI-PATTERNS
-- **Trust reports**: NEVER trust "I'm done" - verify outputs.
-- **High temp**: Don't use >0.3 for code agents.
-- **Sequential calls**: Use `delegate_task` with `run_in_background` for exploration.
-- **Prometheus writing code**: Planner only - never implements.
+
+- **Trust agent self-reports**: NEVER — always verify outputs
+- **High temperature**: Don't use >0.3 for code agents
+- **Sequential calls**: Use `task` with `run_in_background` for exploration
+- **Prometheus writing code**: Planner only — never implements

src/agents/agent-builder.ts

@@ -0,0 +1,50 @@
+import type { AgentConfig } from "@opencode-ai/sdk"
+import type { AgentFactory } from "./types"
+import type { CategoriesConfig, CategoryConfig, GitMasterConfig } from "../config/schema"
+import type { BrowserAutomationProvider } from "../config/schema"
+import { mergeCategories } from "../shared/merge-categories"
+import { resolveMultipleSkills } from "../features/opencode-skill-loader/skill-content"
+
+export type AgentSource = AgentFactory | AgentConfig
+
+export function isFactory(source: AgentSource): source is AgentFactory {
+  return typeof source === "function"
+}
+
+export function buildAgent(
+  source: AgentSource,
+  model: string,
+  categories?: CategoriesConfig,
+  gitMasterConfig?: GitMasterConfig,
+  browserProvider?: BrowserAutomationProvider,
+  disabledSkills?: Set<string>
+): AgentConfig {
+  const base = isFactory(source) ? source(model) : { ...source }
+  const categoryConfigs: Record<string, CategoryConfig> = mergeCategories(categories)
+
+  const agentWithCategory = base as AgentConfig & { category?: string; skills?: string[]; variant?: string }
+  if (agentWithCategory.category) {
+    const categoryConfig = categoryConfigs[agentWithCategory.category]
+    if (categoryConfig) {
+      if (!base.model) {
+        base.model = categoryConfig.model
+      }
+      if (base.temperature === undefined && categoryConfig.temperature !== undefined) {
+        base.temperature = categoryConfig.temperature
+      }
+      if (base.variant === undefined && categoryConfig.variant !== undefined) {
+        base.variant = categoryConfig.variant
+      }
+    }
+  }
+
+  if (agentWithCategory.skills?.length) {
+    const { resolved } = resolveMultipleSkills(agentWithCategory.skills, { gitMasterConfig, browserProvider, disabledSkills })
+    if (resolved.size > 0) {
+      const skillContent = Array.from(resolved.values()).join("\n\n")
+      base.prompt = skillContent + (base.prompt ? "\n\n" + base.prompt : "")
+    }
+  }
+
+  return base
+}

src/agents/atlas/agent.ts

@@ -0,0 +1,142 @@
+/**
+ * Atlas - Master Orchestrator Agent
+ *
+ * Orchestrates work via task() to complete ALL tasks in a todo list until fully done.
+ * You are the conductor of a symphony of specialized agents.
+ *
+ * Routing:
+ * 1. GPT models (openai/*, github-copilot/gpt-*) → gpt.ts (GPT-5.2 optimized)
+ * 2. Default (Claude, etc.) → default.ts (Claude-optimized)
+ */
+
+import type { AgentConfig } from "@opencode-ai/sdk"
+import type { AgentMode, AgentPromptMetadata } from "../types"
+import { isGptModel } from "../types"
+import type { AvailableAgent, AvailableSkill, AvailableCategory } from "../dynamic-agent-prompt-builder"
+import { buildCategorySkillsDelegationGuide } from "../dynamic-agent-prompt-builder"
+import type { CategoryConfig } from "../../config/schema"
+import { mergeCategories } from "../../shared/merge-categories"
+import { createAgentToolRestrictions } from "../../shared/permission-compat"
+
+import { getDefaultAtlasPrompt } from "./default"
+import { getGptAtlasPrompt } from "./gpt"
+import {
+  getCategoryDescription,
+  buildAgentSelectionSection,
+  buildCategorySection,
+  buildSkillsSection,
+  buildDecisionMatrix,
+} from "./prompt-section-builder"
+
+const MODE: AgentMode = "primary"
+
+export type AtlasPromptSource = "default" | "gpt"
+
+/**
+ * Determines which Atlas prompt to use based on model.
+ */
+export function getAtlasPromptSource(model?: string): AtlasPromptSource {
+  if (model && isGptModel(model)) {
+    return "gpt"
+  }
+  return "default"
+}
+
+export interface OrchestratorContext {
+  model?: string
+  availableAgents?: AvailableAgent[]
+  availableSkills?: AvailableSkill[]
+  userCategories?: Record<string, CategoryConfig>
+}
+
+/**
+ * Gets the appropriate Atlas prompt based on model.
+ */
+export function getAtlasPrompt(model?: string): string {
+  const source = getAtlasPromptSource(model)
+
+  switch (source) {
+    case "gpt":
+      return getGptAtlasPrompt()
+    case "default":
+    default:
+      return getDefaultAtlasPrompt()
+  }
+}
+
+function buildDynamicOrchestratorPrompt(ctx?: OrchestratorContext): string {
+  const agents = ctx?.availableAgents ?? []
+  const skills = ctx?.availableSkills ?? []
+  const userCategories = ctx?.userCategories
+  const model = ctx?.model
+
+  const allCategories = mergeCategories(userCategories)
+  const availableCategories: AvailableCategory[] = Object.entries(allCategories).map(([name]) => ({
+    name,
+    description: getCategoryDescription(name, userCategories),
+  }))
+
+  const categorySection = buildCategorySection(userCategories)
+  const agentSection = buildAgentSelectionSection(agents)
+  const decisionMatrix = buildDecisionMatrix(agents, userCategories)
+  const skillsSection = buildSkillsSection(skills)
+  const categorySkillsGuide = buildCategorySkillsDelegationGuide(availableCategories, skills)
+
+  const basePrompt = getAtlasPrompt(model)
+
+  return basePrompt
+    .replace("{CATEGORY_SECTION}", categorySection)
+    .replace("{AGENT_SECTION}", agentSection)
+    .replace("{DECISION_MATRIX}", decisionMatrix)
+    .replace("{SKILLS_SECTION}", skillsSection)
+    .replace("{{CATEGORY_SKILLS_DELEGATION_GUIDE}}", categorySkillsGuide)
+}
+
+export function createAtlasAgent(ctx: OrchestratorContext): AgentConfig {
+  const restrictions = createAgentToolRestrictions([
+    "task",
+    "call_omo_agent",
+  ])
+
+  const baseConfig = {
+    description:
+      "Orchestrates work via task() to complete ALL tasks in a todo list until fully done. (Atlas - OhMyOpenCode)",
+    mode: MODE,
+    ...(ctx.model ? { model: ctx.model } : {}),
+    temperature: 0.1,
+    prompt: buildDynamicOrchestratorPrompt(ctx),
+    color: "#10B981",
+    ...restrictions,
+  }
+
+  return baseConfig as AgentConfig
+}
+createAtlasAgent.mode = MODE
+
+export const atlasPromptMetadata: AgentPromptMetadata = {
+  category: "advisor",
+  cost: "EXPENSIVE",
+  promptAlias: "Atlas",
+  triggers: [
+    {
+      domain: "Todo list orchestration",
+      trigger: "Complete ALL tasks in a todo list with verification",
+    },
+    {
+      domain: "Multi-agent coordination",
+      trigger: "Parallel task execution across specialized agents",
+    },
+  ],
+  useWhen: [
+    "User provides a todo list path (.sisyphus/plans/{name}.md)",
+    "Multiple tasks need to be completed in sequence or parallel",
+    "Work requires coordination across multiple specialized agents",
+  ],
+  avoidWhen: [
+    "Single simple task that doesn't require orchestration",
+    "Tasks that can be handled directly by one agent",
+    "When user wants to execute tasks manually",
+  ],
+  keyTrigger:
+    "Todo list path provided OR multiple tasks requiring multi-agent orchestration",
+}

src/agents/atlas/default.ts

@@ -19,18 +19,18 @@ You never write code yourself. You orchestrate specialists who do.
 </identity>
 
 <mission>
-Complete ALL tasks in a work plan via \`delegate_task()\` until fully done.
+Complete ALL tasks in a work plan via \`task()\` until fully done.
 One task per delegation. Parallel when independent. Verify everything.
 </mission>
 
 <delegation_system>
 ## How to Delegate
 
-Use \`delegate_task()\` with EITHER category OR agent (mutually exclusive):
+Use \`task()\` with EITHER category OR agent (mutually exclusive):
 
 \`\`\`typescript
 // Option A: Category + Skills (spawns Sisyphus-Junior with domain config)
-delegate_task(
+task(
   category="[category-name]",
   load_skills=["skill-1", "skill-2"],
   run_in_background=false,
@@ -38,7 +38,7 @@ delegate_task(
 )
 
 // Option B: Specialized Agent (for specific expert tasks)
-delegate_task(
+task(
   subagent_type="[agent-name]",
   load_skills=[],
   run_in_background=false,
@@ -58,7 +58,7 @@ delegate_task(
 
 ## 6-Section Prompt Structure (MANDATORY)
 
-Every \`delegate_task()\` prompt MUST include ALL 6 sections:
+Every \`task()\` prompt MUST include ALL 6 sections:
 
 \`\`\`markdown
 ## 1. TASK
@@ -149,7 +149,7 @@ Structure:
 ### 3.1 Check Parallelization
 If tasks can run in parallel:
 - Prepare prompts for ALL parallelizable tasks
-- Invoke multiple \`delegate_task()\` in ONE message
+- Invoke multiple \`task()\` in ONE message
 - Wait for all to complete
 - Verify all, then continue
 
@@ -167,10 +167,10 @@ Read(".sisyphus/notepads/{plan-name}/issues.md")
 
 Extract wisdom and include in prompt.
 
-### 3.3 Invoke delegate_task()
+### 3.3 Invoke task()
 
 \`\`\`typescript
-delegate_task(
+task(
   category="[category]",
   load_skills=["[relevant-skills]"],
   run_in_background=false,
@@ -178,39 +178,59 @@ delegate_task(
 )
 \`\`\`
 
-### 3.4 Verify (PROJECT-LEVEL QA)
+### 3.4 Verify (MANDATORY — EVERY SINGLE DELEGATION)
 
-**After EVERY delegation, YOU must verify:**
+**You are the QA gate. Subagents lie. Automated checks alone are NOT enough.**
 
-1. **Project-level diagnostics**:
-   \`lsp_diagnostics(filePath="src/")\` or \`lsp_diagnostics(filePath=".")\`
-   MUST return ZERO errors
+After EVERY delegation, complete ALL of these steps — no shortcuts:
 
-2. **Build verification**:
-   \`bun run build\` or \`bun run typecheck\`
-   Exit code MUST be 0
+#### A. Automated Verification
+1. \`lsp_diagnostics(filePath=".")\` → ZERO errors at project level
+2. \`bun run build\` or \`bun run typecheck\` → exit code 0
+3. \`bun test\` → ALL tests pass
 
-3. **Test verification**:
-   \`bun test\`
-   ALL tests MUST pass
+#### B. Manual Code Review (NON-NEGOTIABLE — DO NOT SKIP)
 
-4. **Manual inspection**:
-   - Read changed files
-   - Confirm changes match requirements
-   - Check for regressions
+**This is the step you are most tempted to skip. DO NOT SKIP IT.**
 
-**Checklist:**
+1. \`Read\` EVERY file the subagent created or modified — no exceptions
+2. For EACH file, check line by line:
+   - Does the logic actually implement the task requirement?
+   - Are there stubs, TODOs, placeholders, or hardcoded values?
+   - Are there logic errors or missing edge cases?
+   - Does it follow the existing codebase patterns?
+   - Are imports correct and complete?
+3. Cross-reference: compare what subagent CLAIMED vs what the code ACTUALLY does
+4. If anything doesn't match → resume session and fix immediately
+
+**If you cannot explain what the changed code does, you have not reviewed it.**
+
+#### C. Hands-On QA (if applicable)
+| Deliverable | Method | Tool |
+|-------------|--------|------|
+| Frontend/UI | Browser | \`/playwright\` |
+| TUI/CLI | Interactive | \`interactive_bash\` |
+| API/Backend | Real requests | curl |
+
+#### D. Check Boulder State Directly
+
+After verification, READ the plan file directly — every time, no exceptions:
 \`\`\`
-[ ] lsp_diagnostics at project level - ZERO errors
-[ ] Build command - exit 0
-[ ] Test suite - all pass
-[ ] Files exist and match requirements
-[ ] No regressions
+Read(".sisyphus/tasks/{plan-name}.yaml")
+\`\`\`
+Count remaining \`- [ ]\` tasks. This is your ground truth for what comes next.
+
+**Checklist (ALL must be checked):**
+\`\`\`
+[ ] Automated: lsp_diagnostics clean, build passes, tests pass
+[ ] Manual: Read EVERY changed file, verified logic matches requirements
+[ ] Cross-check: Subagent claims match actual code
+[ ] Boulder: Read plan file, confirmed current progress
 \`\`\`
 
 **If verification fails**: Resume the SAME session with the ACTUAL error output:
 \`\`\`typescript
-delegate_task(
+task(
   session_id="ses_xyz789",  // ALWAYS use the session from the failed task
   load_skills=[...],
   prompt="Verification failed: {actual error}. Fix."
@@ -221,13 +241,13 @@ delegate_task(
 
 **CRITICAL: When re-delegating, ALWAYS use \`session_id\` parameter.**
 
-Every \`delegate_task()\` output includes a session_id. STORE IT.
+Every \`task()\` output includes a session_id. STORE IT.
 
 If task fails:
 1. Identify what went wrong
 2. **Resume the SAME session** - subagent has full context already:
     \`\`\`typescript
-    delegate_task(
+    task(
       session_id="ses_xyz789",  // Session from failed task
       load_skills=[...],
       prompt="FAILED: {error}. Fix by: {specific instruction}"
@@ -274,21 +294,21 @@ ACCUMULATED WISDOM:
 
 **For exploration (explore/librarian)**: ALWAYS background
 \`\`\`typescript
-delegate_task(subagent_type="explore", run_in_background=true, ...)
-delegate_task(subagent_type="librarian", run_in_background=true, ...)
+task(subagent_type="explore", load_skills=[], run_in_background=true, ...)
+task(subagent_type="librarian", load_skills=[], run_in_background=true, ...)
 \`\`\`
 
 **For task execution**: NEVER background
 \`\`\`typescript
-delegate_task(category="...", run_in_background=false, ...)
+task(category="...", load_skills=[...], run_in_background=false, ...)
 \`\`\`
 
 **Parallel task groups**: Invoke multiple in ONE message
 \`\`\`typescript
 // Tasks 2, 3, 4 are independent - invoke together
-delegate_task(category="quick", load_skills=[], run_in_background=false, prompt="Task 2...")
-delegate_task(category="quick", load_skills=[], run_in_background=false, prompt="Task 3...")
-delegate_task(category="quick", load_skills=[], run_in_background=false, prompt="Task 4...")
+task(category="quick", load_skills=[], run_in_background=false, prompt="Task 2...")
+task(category="quick", load_skills=[], run_in_background=false, prompt="Task 3...")
+task(category="quick", load_skills=[], run_in_background=false, prompt="Task 4...")
 \`\`\`
 
 **Background management**:
@@ -325,22 +345,25 @@ delegate_task(category="quick", load_skills=[], run_in_background=false, prompt=
 
 You are the QA gate. Subagents lie. Verify EVERYTHING.
 
-**After each delegation**:
-1. \`lsp_diagnostics\` at PROJECT level (not file level)
-2. Run build command
-3. Run test suite
-4. Read changed files manually
-5. Confirm requirements met
+**After each delegation — BOTH automated AND manual verification are MANDATORY:**
+
+1. \`lsp_diagnostics\` at PROJECT level → ZERO errors
+2. Run build command → exit 0
+3. Run test suite → ALL pass
+4. **\`Read\` EVERY changed file line by line** → logic matches requirements
+5. **Cross-check**: subagent's claims vs actual code — do they match?
+6. **Check boulder state**: Read the plan file directly, count remaining tasks
 
 **Evidence required**:
 | Action | Evidence |
 |--------|----------|
-| Code change | lsp_diagnostics clean at project level |
+| Code change | lsp_diagnostics clean + manual Read of every changed file |
 | Build | Exit code 0 |
 | Tests | All pass |
-| Delegation | Verified independently |
+| Logic correct | You read the code and can explain what it does |
+| Boulder state | Read plan file, confirmed progress |
 
-**No evidence = not complete.**
+**No evidence = not complete. Skipping manual review = rubber-stamping broken work.**
 </verification_rules>
 
 <boundaries>

src/agents/atlas/gpt.ts

@@ -24,7 +24,7 @@ You DELEGATE, COORDINATE, and VERIFY. You NEVER write code yourself.
 </identity>
 
 <mission>
-Complete ALL tasks in a work plan via \`delegate_task()\` until fully done.
+Complete ALL tasks in a work plan via \`task()\` until fully done.
 - One task per delegation
 - Parallel when independent
 - Verify everything
@@ -71,14 +71,14 @@ Complete ALL tasks in a work plan via \`delegate_task()\` until fully done.
 <delegation_system>
 ## Delegation API
 
-Use \`delegate_task()\` with EITHER category OR agent (mutually exclusive):
+Use \`task()\` with EITHER category OR agent (mutually exclusive):
 
 \`\`\`typescript
 // Category + Skills (spawns Sisyphus-Junior)
-delegate_task(category="[name]", load_skills=["skill-1"], run_in_background=false, prompt="...")
+task(category="[name]", load_skills=["skill-1"], run_in_background=false, prompt="...")
 
 // Specialized Agent
-delegate_task(subagent_type="[agent]", load_skills=[], run_in_background=false, prompt="...")
+task(subagent_type="[agent]", load_skills=[], run_in_background=false, prompt="...")
 \`\`\`
 
 {CATEGORY_SECTION}
@@ -93,7 +93,7 @@ delegate_task(subagent_type="[agent]", load_skills=[], run_in_background=false,
 
 ## 6-Section Prompt Structure (MANDATORY)
 
-Every \`delegate_task()\` prompt MUST include ALL 6 sections:
+Every \`task()\` prompt MUST include ALL 6 sections:
 
 \`\`\`markdown
 ## 1. TASK
@@ -166,7 +166,7 @@ Structure: learnings.md, decisions.md, issues.md, problems.md
 ## Step 3: Execute Tasks
 
 ### 3.1 Parallelization Check
-- Parallel tasks → invoke multiple \`delegate_task()\` in ONE message
+- Parallel tasks → invoke multiple \`task()\` in ONE message
 - Sequential → process one at a time
 
 ### 3.2 Pre-Delegation (MANDATORY)
@@ -176,32 +176,64 @@ Read(".sisyphus/notepads/{plan-name}/issues.md")
 \`\`\`
 Extract wisdom → include in prompt.
 
-### 3.3 Invoke delegate_task()
+### 3.3 Invoke task()
 
 \`\`\`typescript
-delegate_task(category="[cat]", load_skills=["[skills]"], run_in_background=false, prompt=\`[6-SECTION PROMPT]\`)
+task(category="[cat]", load_skills=["[skills]"], run_in_background=false, prompt=\`[6-SECTION PROMPT]\`)
 \`\`\`
 
-### 3.4 Verify (PROJECT-LEVEL QA)
+### 3.4 Verify (MANDATORY — EVERY SINGLE DELEGATION)
 
-After EVERY delegation:
+After EVERY delegation, complete ALL steps — no shortcuts:
+
+#### A. Automated Verification
 1. \`lsp_diagnostics(filePath=".")\` → ZERO errors
 2. \`Bash("bun run build")\` → exit 0
 3. \`Bash("bun test")\` → all pass
-4. \`Read\` changed files → confirm requirements met
 
-Checklist:
-- [ ] lsp_diagnostics clean
-- [ ] Build passes
-- [ ] Tests pass
-- [ ] Files match requirements
+#### B. Manual Code Review (NON-NEGOTIABLE)
+1. \`Read\` EVERY file the subagent touched — no exceptions
+2. For each file, verify line by line:
+
+| Check | What to Look For |
+|-------|------------------|
+| Logic correctness | Does implementation match task requirements? |
+| Completeness | No stubs, TODOs, placeholders, hardcoded values? |
+| Edge cases | Off-by-one, null checks, error paths handled? |
+| Patterns | Follows existing codebase conventions? |
+| Imports | Correct, complete, no unused? |
+
+3. Cross-check: subagent's claims vs actual code — do they match?
+4. If mismatch found → resume session with \`session_id\` and fix
+
+**If you cannot explain what the changed code does, you have not reviewed it.**
+
+#### C. Hands-On QA (if applicable)
+| Deliverable | Method | Tool |
+|-------------|--------|------|
+| Frontend/UI | Browser | \`/playwright\` |
+| TUI/CLI | Interactive | \`interactive_bash\` |
+| API/Backend | Real requests | curl |
+
+#### D. Check Boulder State Directly
+After verification, READ the plan file — every time:
+\`\`\`
+Read(".sisyphus/tasks/{plan-name}.yaml")
+\`\`\`
+Count remaining \`- [ ]\` tasks. This is your ground truth.
+
+Checklist (ALL required):
+- [ ] Automated: diagnostics clean, build passes, tests pass
+- [ ] Manual: Read EVERY changed file, logic matches requirements
+- [ ] Cross-check: subagent claims match actual code
+- [ ] Boulder: Read plan file, confirmed current progress
 
 ### 3.5 Handle Failures
 
 **CRITICAL: Use \`session_id\` for retries.**
 
 \`\`\`typescript
-delegate_task(session_id="ses_xyz789", load_skills=[...], prompt="FAILED: {error}. Fix by: {instruction}")
+task(session_id="ses_xyz789", load_skills=[...], prompt="FAILED: {error}. Fix by: {instruction}")
 \`\`\`
 
 - Maximum 3 retries per task
@@ -231,18 +263,18 @@ ACCUMULATED WISDOM: [from notepad]
 <parallel_execution>
 **Exploration (explore/librarian)**: ALWAYS background
 \`\`\`typescript
-delegate_task(subagent_type="explore", run_in_background=true, ...)
+task(subagent_type="explore", load_skills=[], run_in_background=true, ...)
 \`\`\`
 
 **Task execution**: NEVER background
 \`\`\`typescript
-delegate_task(category="...", run_in_background=false, ...)
+task(category="...", load_skills=[...], run_in_background=false, ...)
 \`\`\`
 
 **Parallel task groups**: Invoke multiple in ONE message
 \`\`\`typescript
-delegate_task(category="quick", load_skills=[], run_in_background=false, prompt="Task 2...")
-delegate_task(category="quick", load_skills=[], run_in_background=false, prompt="Task 3...")
+task(category="quick", load_skills=[], run_in_background=false, prompt="Task 2...")
+task(category="quick", load_skills=[], run_in_background=false, prompt="Task 3...")
 \`\`\`
 
 **Background management**:
@@ -269,15 +301,23 @@ delegate_task(category="quick", load_skills=[], run_in_background=false, prompt=
 <verification_rules>
 You are the QA gate. Subagents lie. Verify EVERYTHING.
 
-**After each delegation**:
+**After each delegation — BOTH automated AND manual verification are MANDATORY**:
+
 | Step | Tool | Expected |
 |------|------|----------|
 | 1 | \`lsp_diagnostics(".")\` | ZERO errors |
 | 2 | \`Bash("bun run build")\` | exit 0 |
 | 3 | \`Bash("bun test")\` | all pass |
-| 4 | \`Read\` changed files | matches requirements |
+| 4 | \`Read\` EVERY changed file | logic matches requirements |
+| 5 | Cross-check claims vs code | subagent's report matches reality |
+| 6 | \`Read\` plan file | boulder state confirmed |
 
-**No evidence = not complete.**
+**Manual code review (Step 4) is NON-NEGOTIABLE:**
+- Read every line of every changed file
+- Verify logic correctness, completeness, edge cases
+- If you can't explain what the code does, you haven't reviewed it
+
+**No evidence = not complete. Skipping manual review = rubber-stamping broken work.**
 </verification_rules>
 
 <boundaries>

src/agents/atlas/index.ts

@@ -1,33 +1,3 @@
-/**
- * Atlas - Master Orchestrator Agent
- *
- * Orchestrates work via delegate_task() to complete ALL tasks in a todo list until fully done.
- * You are the conductor of a symphony of specialized agents.
- *
- * Routing:
- * 1. GPT models (openai/*, github-copilot/gpt-*) → gpt.ts (GPT-5.2 optimized)
- * 2. Default (Claude, etc.) → default.ts (Claude-optimized)
- */
-
-import type { AgentConfig } from "@opencode-ai/sdk"
-import type { AgentMode, AgentPromptMetadata } from "../types"
-import { isGptModel } from "../types"
-import type { AvailableAgent, AvailableSkill, AvailableCategory } from "../dynamic-agent-prompt-builder"
-import { buildCategorySkillsDelegationGuide } from "../dynamic-agent-prompt-builder"
-import type { CategoryConfig } from "../../config/schema"
-import { DEFAULT_CATEGORIES } from "../../tools/delegate-task/constants"
-import { createAgentToolRestrictions } from "../../shared/permission-compat"
-
-import { ATLAS_SYSTEM_PROMPT, getDefaultAtlasPrompt } from "./default"
-import { ATLAS_GPT_SYSTEM_PROMPT, getGptAtlasPrompt } from "./gpt"
-import {
-  getCategoryDescription,
-  buildAgentSelectionSection,
-  buildCategorySection,
-  buildSkillsSection,
-  buildDecisionMatrix,
-} from "./utils"
-
 export { ATLAS_SYSTEM_PROMPT, getDefaultAtlasPrompt } from "./default"
 export { ATLAS_GPT_SYSTEM_PROMPT, getGptAtlasPrompt } from "./gpt"
 export {
@@ -36,118 +6,9 @@ export {
   buildCategorySection,
   buildSkillsSection,
   buildDecisionMatrix,
-} from "./utils"
-export { isGptModel }
+} from "./prompt-section-builder"
 
-const MODE: AgentMode = "primary"
+export { createAtlasAgent, getAtlasPromptSource, getAtlasPrompt, atlasPromptMetadata } from "./agent"
+export type { AtlasPromptSource, OrchestratorContext } from "./agent"
 
-export type AtlasPromptSource = "default" | "gpt"
-
-/**
- * Determines which Atlas prompt to use based on model.
- */
-export function getAtlasPromptSource(model?: string): AtlasPromptSource {
-  if (model && isGptModel(model)) {
-    return "gpt"
-  }
-  return "default"
-}
-
-export interface OrchestratorContext {
-  model?: string
-  availableAgents?: AvailableAgent[]
-  availableSkills?: AvailableSkill[]
-  userCategories?: Record<string, CategoryConfig>
-}
-
-/**
- * Gets the appropriate Atlas prompt based on model.
- */
-export function getAtlasPrompt(model?: string): string {
-  const source = getAtlasPromptSource(model)
-
-  switch (source) {
-    case "gpt":
-      return getGptAtlasPrompt()
-    case "default":
-    default:
-      return getDefaultAtlasPrompt()
-  }
-}
-
-function buildDynamicOrchestratorPrompt(ctx?: OrchestratorContext): string {
-  const agents = ctx?.availableAgents ?? []
-  const skills = ctx?.availableSkills ?? []
-  const userCategories = ctx?.userCategories
-  const model = ctx?.model
-
-  const allCategories = { ...DEFAULT_CATEGORIES, ...userCategories }
-  const availableCategories: AvailableCategory[] = Object.entries(allCategories).map(([name]) => ({
-    name,
-    description: getCategoryDescription(name, userCategories),
-  }))
-
-  const categorySection = buildCategorySection(userCategories)
-  const agentSection = buildAgentSelectionSection(agents)
-  const decisionMatrix = buildDecisionMatrix(agents, userCategories)
-  const skillsSection = buildSkillsSection(skills)
-  const categorySkillsGuide = buildCategorySkillsDelegationGuide(availableCategories, skills)
-
-  const basePrompt = getAtlasPrompt(model)
-
-  return basePrompt
-    .replace("{CATEGORY_SECTION}", categorySection)
-    .replace("{AGENT_SECTION}", agentSection)
-    .replace("{DECISION_MATRIX}", decisionMatrix)
-    .replace("{SKILLS_SECTION}", skillsSection)
-    .replace("{{CATEGORY_SKILLS_DELEGATION_GUIDE}}", categorySkillsGuide)
-}
-
-export function createAtlasAgent(ctx: OrchestratorContext): AgentConfig {
-  const restrictions = createAgentToolRestrictions([
-    "task",
-    "call_omo_agent",
-  ])
-
-  const baseConfig = {
-    description:
-      "Orchestrates work via delegate_task() to complete ALL tasks in a todo list until fully done. (Atlas - OhMyOpenCode)",
-    mode: MODE,
-    ...(ctx.model ? { model: ctx.model } : {}),
-    temperature: 0.1,
-    prompt: buildDynamicOrchestratorPrompt(ctx),
-    color: "#10B981",
-    ...restrictions,
-  }
-
-  return baseConfig as AgentConfig
-}
-createAtlasAgent.mode = MODE
-
-export const atlasPromptMetadata: AgentPromptMetadata = {
-  category: "advisor",
-  cost: "EXPENSIVE",
-  promptAlias: "Atlas",
-  triggers: [
-    {
-      domain: "Todo list orchestration",
-      trigger: "Complete ALL tasks in a todo list with verification",
-    },
-    {
-      domain: "Multi-agent coordination",
-      trigger: "Parallel task execution across specialized agents",
-    },
-  ],
-  useWhen: [
-    "User provides a todo list path (.sisyphus/plans/{name}.md)",
-    "Multiple tasks need to be completed in sequence or parallel",
-    "Work requires coordination across multiple specialized agents",
-  ],
-  avoidWhen: [
-    "Single simple task that doesn't require orchestration",
-    "Tasks that can be handled directly by one agent",
-    "When user wants to execute tasks manually",
-  ],
-  keyTrigger:
-    "Todo list path provided OR multiple tasks requiring multi-agent orchestration",
-}
+export { isGptModel } from "../types"

src/agents/atlas/prompt-section-builder.ts

@@ -6,23 +6,25 @@
  */
 
 import type { CategoryConfig } from "../../config/schema"
-import type { AvailableAgent, AvailableSkill } from "../dynamic-agent-prompt-builder"
-import { DEFAULT_CATEGORIES, CATEGORY_DESCRIPTIONS } from "../../tools/delegate-task/constants"
+import { formatCustomSkillsBlock, type AvailableAgent, type AvailableSkill } from "../dynamic-agent-prompt-builder"
+import { CATEGORY_DESCRIPTIONS } from "../../tools/delegate-task/constants"
+import { mergeCategories } from "../../shared/merge-categories"
+import { truncateDescription } from "../../shared/truncate-description"
 
 export const getCategoryDescription = (name: string, userCategories?: Record<string, CategoryConfig>) =>
   userCategories?.[name]?.description ?? CATEGORY_DESCRIPTIONS[name] ?? "General tasks"
 
 export function buildAgentSelectionSection(agents: AvailableAgent[]): string {
-  if (agents.length === 0) {
-    return `##### Option B: Use AGENT directly (for specialized experts)
+   if (agents.length === 0) {
+     return `##### Option B: Use AGENT directly (for specialized experts)
 
-No agents available.`
-  }
+ No agents available.`
+   }
 
-  const rows = agents.map((a) => {
-    const shortDesc = a.description.split(".")[0] || a.description
-    return `| \`${a.name}\` | ${shortDesc} |`
-  })
+   const rows = agents.map((a) => {
+     const shortDesc = truncateDescription(a.description)
+     return `| \`${a.name}\` | ${shortDesc} |`
+   })
 
   return `##### Option B: Use AGENT directly (for specialized experts)
 
@@ -32,7 +34,7 @@ ${rows.join("\n")}`
 }
 
 export function buildCategorySection(userCategories?: Record<string, CategoryConfig>): string {
-  const allCategories = { ...DEFAULT_CATEGORIES, ...userCategories }
+  const allCategories = mergeCategories(userCategories)
   const categoryRows = Object.entries(allCategories).map(([name, config]) => {
     const temp = config.temperature ?? 0.5
     return `| \`${name}\` | ${temp} | ${getCategoryDescription(name, userCategories)} |`
@@ -47,7 +49,7 @@ Categories spawn \`Sisyphus-Junior-{category}\` with optimized settings:
 ${categoryRows.join("\n")}
 
 \`\`\`typescript
-delegate_task(category="[category-name]", load_skills=[...], run_in_background=false, prompt="...")
+task(category="[category-name]", load_skills=[...], run_in_background=false, prompt="...")
 \`\`\``
 }
 
@@ -56,21 +58,48 @@ export function buildSkillsSection(skills: AvailableSkill[]): string {
     return ""
   }
 
-  const skillRows = skills.map((s) => {
-    const shortDesc = s.description.split(".")[0] || s.description
-    return `| \`${s.name}\` | ${shortDesc} |`
-  })
+  const builtinSkills = skills.filter((s) => s.location === "plugin")
+  const customSkills = skills.filter((s) => s.location !== "plugin")
+
+   const builtinRows = builtinSkills.map((s) => {
+     const shortDesc = truncateDescription(s.description)
+     return `| \`${s.name}\` | ${shortDesc} |`
+   })
+
+   const customRows = customSkills.map((s) => {
+     const shortDesc = truncateDescription(s.description)
+     const source = s.location === "project" ? "project" : "user"
+     return `| \`${s.name}\` | ${shortDesc} | ${source} |`
+   })
+
+  const customSkillBlock = formatCustomSkillsBlock(customRows, customSkills, "**")
+
+  let skillsTable: string
+
+  if (customSkills.length > 0 && builtinSkills.length > 0) {
+    skillsTable = `**Built-in Skills:**
+
+| Skill | When to Use |
+|-------|-------------|
+${builtinRows.join("\n")}
+
+${customSkillBlock}`
+  } else if (customSkills.length > 0) {
+    skillsTable = customSkillBlock
+  } else {
+    skillsTable = `| Skill | When to Use |
+|-------|-------------|
+${builtinRows.join("\n")}`
+  }
 
   return `
 #### 3.2.2: Skill Selection (PREPEND TO PROMPT)
 
 **Skills are specialized instructions that guide subagent behavior. Consider them alongside category selection.**
 
-| Skill | When to Use |
-|-------|-------------|
-${skillRows.join("\n")}
+${skillsTable}
 
-**MANDATORY: Evaluate ALL skills for relevance to your task.**
+**MANDATORY: Evaluate ALL skills (built-in AND user-installed) for relevance to your task.**
 
 Read each skill's description and ask: "Does this skill's domain overlap with my task?"
 - If YES: INCLUDE in load_skills=[...]
@@ -78,7 +107,7 @@ Read each skill's description and ask: "Does this skill's domain overlap with my
 
 **Usage:**
 \`\`\`typescript
-delegate_task(category="[category]", load_skills=["skill-1", "skill-2"], run_in_background=false, prompt="...")
+task(category="[category]", load_skills=["skill-1", "skill-2"], run_in_background=false, prompt="...")
 \`\`\`
 
 **IMPORTANT:**
@@ -88,16 +117,16 @@ delegate_task(category="[category]", load_skills=["skill-1", "skill-2"], run_in_
 }
 
 export function buildDecisionMatrix(agents: AvailableAgent[], userCategories?: Record<string, CategoryConfig>): string {
-  const allCategories = { ...DEFAULT_CATEGORIES, ...userCategories }
+  const allCategories = mergeCategories(userCategories)
 
   const categoryRows = Object.entries(allCategories).map(([name]) =>
     `| ${getCategoryDescription(name, userCategories)} | \`category="${name}", load_skills=[...]\` |`
   )
 
-  const agentRows = agents.map((a) => {
-    const shortDesc = a.description.split(".")[0] || a.description
-    return `| ${shortDesc} | \`agent="${a.name}"\` |`
-  })
+   const agentRows = agents.map((a) => {
+     const shortDesc = truncateDescription(a.description)
+     return `| ${shortDesc} | \`agent="${a.name}"\` |`
+   })
 
   return `##### Decision Matrix
 

src/agents/builtin-agents.ts

@@ -0,0 +1,192 @@
+import type { AgentConfig } from "@opencode-ai/sdk"
+import type { BuiltinAgentName, AgentOverrides, AgentFactory, AgentPromptMetadata } from "./types"
+import type { CategoriesConfig, GitMasterConfig } from "../config/schema"
+import type { LoadedSkill } from "../features/opencode-skill-loader/types"
+import type { BrowserAutomationProvider } from "../config/schema"
+import { createSisyphusAgent } from "./sisyphus"
+import { createOracleAgent, ORACLE_PROMPT_METADATA } from "./oracle"
+import { createLibrarianAgent, LIBRARIAN_PROMPT_METADATA } from "./librarian"
+import { createExploreAgent, EXPLORE_PROMPT_METADATA } from "./explore"
+import { createMultimodalLookerAgent, MULTIMODAL_LOOKER_PROMPT_METADATA } from "./multimodal-looker"
+import { createMetisAgent, metisPromptMetadata } from "./metis"
+import { createAtlasAgent, atlasPromptMetadata } from "./atlas"
+import { createMomusAgent, momusPromptMetadata } from "./momus"
+import { createHephaestusAgent } from "./hephaestus"
+import type { AvailableCategory } from "./dynamic-agent-prompt-builder"
+import {
+  fetchAvailableModels,
+  readConnectedProvidersCache,
+  readProviderModelsCache,
+} from "../shared"
+import { CATEGORY_DESCRIPTIONS } from "../tools/delegate-task/constants"
+import { mergeCategories } from "../shared/merge-categories"
+import { buildAvailableSkills } from "./builtin-agents/available-skills"
+import { collectPendingBuiltinAgents } from "./builtin-agents/general-agents"
+import { maybeCreateSisyphusConfig } from "./builtin-agents/sisyphus-agent"
+import { maybeCreateHephaestusConfig } from "./builtin-agents/hephaestus-agent"
+import { maybeCreateAtlasConfig } from "./builtin-agents/atlas-agent"
+import { buildCustomAgentMetadata, parseRegisteredAgentSummaries } from "./custom-agent-summaries"
+
+type AgentSource = AgentFactory | AgentConfig
+
+const agentSources: Record<BuiltinAgentName, AgentSource> = {
+  sisyphus: createSisyphusAgent,
+  hephaestus: createHephaestusAgent,
+  oracle: createOracleAgent,
+  librarian: createLibrarianAgent,
+  explore: createExploreAgent,
+  "multimodal-looker": createMultimodalLookerAgent,
+  metis: createMetisAgent,
+  momus: createMomusAgent,
+  // Note: Atlas is handled specially in createBuiltinAgents()
+  // because it needs OrchestratorContext, not just a model string
+  atlas: createAtlasAgent as AgentFactory,
+}
+
+/**
+ * Metadata for each agent, used to build Sisyphus's dynamic prompt sections
+ * (Delegation Table, Tool Selection, Key Triggers, etc.)
+ */
+const agentMetadata: Partial<Record<BuiltinAgentName, AgentPromptMetadata>> = {
+  oracle: ORACLE_PROMPT_METADATA,
+  librarian: LIBRARIAN_PROMPT_METADATA,
+  explore: EXPLORE_PROMPT_METADATA,
+  "multimodal-looker": MULTIMODAL_LOOKER_PROMPT_METADATA,
+  metis: metisPromptMetadata,
+  momus: momusPromptMetadata,
+  atlas: atlasPromptMetadata,
+}
+
+export async function createBuiltinAgents(
+  disabledAgents: string[] = [],
+  agentOverrides: AgentOverrides = {},
+  directory?: string,
+  systemDefaultModel?: string,
+  categories?: CategoriesConfig,
+  gitMasterConfig?: GitMasterConfig,
+  discoveredSkills: LoadedSkill[] = [],
+  customAgentSummaries?: unknown,
+  browserProvider?: BrowserAutomationProvider,
+  uiSelectedModel?: string,
+  disabledSkills?: Set<string>,
+  useTaskSystem = false
+): Promise<Record<string, AgentConfig>> {
+  const connectedProviders = readConnectedProvidersCache()
+  const providerModelsConnected = connectedProviders
+    ? (readProviderModelsCache()?.connected ?? [])
+    : []
+  const mergedConnectedProviders = Array.from(
+    new Set([...(connectedProviders ?? []), ...providerModelsConnected])
+  )
+  // IMPORTANT: Do NOT call OpenCode client APIs during plugin initialization.
+  // This function is called from config handler, and calling client API causes deadlock.
+  // See: https://github.com/code-yeongyu/oh-my-opencode/issues/1301
+  const availableModels = await fetchAvailableModels(undefined, {
+    connectedProviders: mergedConnectedProviders.length > 0 ? mergedConnectedProviders : undefined,
+  })
+  const isFirstRunNoCache =
+    availableModels.size === 0 && mergedConnectedProviders.length === 0
+
+  const result: Record<string, AgentConfig> = {}
+
+  const mergedCategories = mergeCategories(categories)
+
+  const availableCategories: AvailableCategory[] = Object.entries(mergedCategories).map(([name]) => ({
+    name,
+    description: categories?.[name]?.description ?? CATEGORY_DESCRIPTIONS[name] ?? "General tasks",
+  }))
+
+  const availableSkills = buildAvailableSkills(discoveredSkills, browserProvider, disabledSkills)
+
+  // Collect general agents first (for availableAgents), but don't add to result yet
+  const { pendingAgentConfigs, availableAgents } = collectPendingBuiltinAgents({
+    agentSources,
+    agentMetadata,
+    disabledAgents,
+    agentOverrides,
+    directory,
+    systemDefaultModel,
+    mergedCategories,
+    gitMasterConfig,
+    browserProvider,
+    uiSelectedModel,
+    availableModels,
+    disabledSkills,
+  })
+
+  const registeredAgents = parseRegisteredAgentSummaries(customAgentSummaries)
+  const builtinAgentNames = new Set(Object.keys(agentSources).map((name) => name.toLowerCase()))
+  const disabledAgentNames = new Set(disabledAgents.map((name) => name.toLowerCase()))
+
+  for (const agent of registeredAgents) {
+    const lowerName = agent.name.toLowerCase()
+    if (builtinAgentNames.has(lowerName)) continue
+    if (disabledAgentNames.has(lowerName)) continue
+    if (availableAgents.some((availableAgent) => availableAgent.name.toLowerCase() === lowerName)) continue
+
+    availableAgents.push({
+      name: agent.name,
+      description: agent.description,
+      metadata: buildCustomAgentMetadata(agent.name, agent.description),
+    })
+  }
+
+  const sisyphusConfig = maybeCreateSisyphusConfig({
+    disabledAgents,
+    agentOverrides,
+    uiSelectedModel,
+    availableModels,
+    systemDefaultModel,
+    isFirstRunNoCache,
+    availableAgents,
+    availableSkills,
+    availableCategories,
+    mergedCategories,
+    directory,
+    userCategories: categories,
+    useTaskSystem,
+  })
+  if (sisyphusConfig) {
+    result["sisyphus"] = sisyphusConfig
+  }
+
+  const hephaestusConfig = maybeCreateHephaestusConfig({
+    disabledAgents,
+    agentOverrides,
+    availableModels,
+    systemDefaultModel,
+    isFirstRunNoCache,
+    availableAgents,
+    availableSkills,
+    availableCategories,
+    mergedCategories,
+    directory,
+    useTaskSystem,
+  })
+  if (hephaestusConfig) {
+    result["hephaestus"] = hephaestusConfig
+  }
+
+  // Add pending agents after sisyphus and hephaestus to maintain order
+  for (const [name, config] of pendingAgentConfigs) {
+    result[name] = config
+  }
+
+  const atlasConfig = maybeCreateAtlasConfig({
+    disabledAgents,
+    agentOverrides,
+    uiSelectedModel,
+    availableModels,
+    systemDefaultModel,
+    availableAgents,
+    availableSkills,
+    mergedCategories,
+    directory,
+    userCategories: categories,
+  })
+  if (atlasConfig) {
+    result["atlas"] = atlasConfig
+  }
+
+  return result
+}

src/agents/builtin-agents/agent-overrides.ts

@@ -0,0 +1,71 @@
+import type { AgentConfig } from "@opencode-ai/sdk"
+import type { AgentOverrideConfig } from "../types"
+import type { CategoryConfig } from "../../config/schema"
+import { deepMerge, migrateAgentConfig } from "../../shared"
+import { resolvePromptAppend } from "./resolve-file-uri"
+
+/**
+ * Expands a category reference from an agent override into concrete config properties.
+ * Category properties are applied unconditionally (overwriting factory defaults),
+ * because the user's chosen category should take priority over factory base values.
+ * Direct override properties applied later via mergeAgentConfig() will supersede these.
+ */
+export function applyCategoryOverride(
+  config: AgentConfig,
+  categoryName: string,
+  mergedCategories: Record<string, CategoryConfig>
+): AgentConfig {
+  const categoryConfig = mergedCategories[categoryName]
+  if (!categoryConfig) return config
+
+  const result = { ...config } as AgentConfig & Record<string, unknown>
+  if (categoryConfig.model) result.model = categoryConfig.model
+  if (categoryConfig.variant !== undefined) result.variant = categoryConfig.variant
+  if (categoryConfig.temperature !== undefined) result.temperature = categoryConfig.temperature
+  if (categoryConfig.reasoningEffort !== undefined) result.reasoningEffort = categoryConfig.reasoningEffort
+  if (categoryConfig.textVerbosity !== undefined) result.textVerbosity = categoryConfig.textVerbosity
+  if (categoryConfig.thinking !== undefined) result.thinking = categoryConfig.thinking
+  if (categoryConfig.top_p !== undefined) result.top_p = categoryConfig.top_p
+  if (categoryConfig.maxTokens !== undefined) result.maxTokens = categoryConfig.maxTokens
+
+  if (categoryConfig.prompt_append && typeof result.prompt === "string") {
+    result.prompt = result.prompt + "\n" + resolvePromptAppend(categoryConfig.prompt_append)
+  }
+
+  return result as AgentConfig
+}
+
+export function mergeAgentConfig(
+  base: AgentConfig,
+  override: AgentOverrideConfig,
+  directory?: string
+): AgentConfig {
+  const migratedOverride = migrateAgentConfig(override as Record<string, unknown>) as AgentOverrideConfig
+  const { prompt_append, ...rest } = migratedOverride
+  const merged = deepMerge(base, rest as Partial<AgentConfig>)
+
+  if (prompt_append && merged.prompt) {
+    merged.prompt = merged.prompt + "\n" + resolvePromptAppend(prompt_append, directory)
+  }
+
+  return merged
+}
+
+export function applyOverrides(
+  config: AgentConfig,
+  override: AgentOverrideConfig | undefined,
+  mergedCategories: Record<string, CategoryConfig>,
+  directory?: string
+): AgentConfig {
+  let result = config
+  const overrideCategory = (override as Record<string, unknown> | undefined)?.category as string | undefined
+  if (overrideCategory) {
+    result = applyCategoryOverride(result, overrideCategory, mergedCategories)
+  }
+
+  if (override) {
+    result = mergeAgentConfig(result, override, directory)
+  }
+
+  return result
+}

src/agents/builtin-agents/atlas-agent.ts

@@ -0,0 +1,66 @@
+import type { AgentConfig } from "@opencode-ai/sdk"
+import type { AgentOverrides } from "../types"
+import type { CategoriesConfig, CategoryConfig } from "../../config/schema"
+import type { AvailableAgent, AvailableSkill } from "../dynamic-agent-prompt-builder"
+import { AGENT_MODEL_REQUIREMENTS } from "../../shared"
+import { applyOverrides } from "./agent-overrides"
+import { applyModelResolution } from "./model-resolution"
+import { createAtlasAgent } from "../atlas"
+
+export function maybeCreateAtlasConfig(input: {
+  disabledAgents: string[]
+  agentOverrides: AgentOverrides
+  uiSelectedModel?: string
+  availableModels: Set<string>
+  systemDefaultModel?: string
+  availableAgents: AvailableAgent[]
+  availableSkills: AvailableSkill[]
+  mergedCategories: Record<string, CategoryConfig>
+  directory?: string
+  userCategories?: CategoriesConfig
+  useTaskSystem?: boolean
+}): AgentConfig | undefined {
+  const {
+    disabledAgents,
+    agentOverrides,
+    uiSelectedModel,
+    availableModels,
+    systemDefaultModel,
+    availableAgents,
+    availableSkills,
+    mergedCategories,
+    directory,
+    userCategories,
+  } = input
+
+  if (disabledAgents.includes("atlas")) return undefined
+
+  const orchestratorOverride = agentOverrides["atlas"]
+  const atlasRequirement = AGENT_MODEL_REQUIREMENTS["atlas"]
+
+  const atlasResolution = applyModelResolution({
+    uiSelectedModel: orchestratorOverride?.model ? undefined : uiSelectedModel,
+    userModel: orchestratorOverride?.model,
+    requirement: atlasRequirement,
+    availableModels,
+    systemDefaultModel,
+  })
+
+  if (!atlasResolution) return undefined
+  const { model: atlasModel, variant: atlasResolvedVariant } = atlasResolution
+
+  let orchestratorConfig = createAtlasAgent({
+    model: atlasModel,
+    availableAgents,
+    availableSkills,
+    userCategories,
+  })
+
+  if (atlasResolvedVariant) {
+    orchestratorConfig = { ...orchestratorConfig, variant: atlasResolvedVariant }
+  }
+
+  orchestratorConfig = applyOverrides(orchestratorConfig, orchestratorOverride, mergedCategories, directory)
+
+  return orchestratorConfig
+}

src/agents/builtin-agents/available-skills.ts

@@ -0,0 +1,35 @@
+import type { AvailableSkill } from "../dynamic-agent-prompt-builder"
+import type { BrowserAutomationProvider } from "../../config/schema"
+import type { LoadedSkill, SkillScope } from "../../features/opencode-skill-loader/types"
+import { createBuiltinSkills } from "../../features/builtin-skills"
+
+function mapScopeToLocation(scope: SkillScope): AvailableSkill["location"] {
+  if (scope === "user" || scope === "opencode") return "user"
+  if (scope === "project" || scope === "opencode-project") return "project"
+  return "plugin"
+}
+
+export function buildAvailableSkills(
+  discoveredSkills: LoadedSkill[],
+  browserProvider?: BrowserAutomationProvider,
+  disabledSkills?: Set<string>
+): AvailableSkill[] {
+  const builtinSkills = createBuiltinSkills({ browserProvider, disabledSkills })
+  const builtinSkillNames = new Set(builtinSkills.map(s => s.name))
+
+  const builtinAvailable: AvailableSkill[] = builtinSkills.map((skill) => ({
+    name: skill.name,
+    description: skill.description,
+    location: "plugin" as const,
+  }))
+
+  const discoveredAvailable: AvailableSkill[] = discoveredSkills
+    .filter(s => !builtinSkillNames.has(s.name) && !disabledSkills?.has(s.name))
+    .map((skill) => ({
+      name: skill.name,
+      description: skill.definition.description ?? "",
+      location: mapScopeToLocation(skill.scope),
+    }))
+
+  return [...builtinAvailable, ...discoveredAvailable]
+}

src/agents/builtin-agents/environment-context.ts

@@ -0,0 +1,8 @@
+import type { AgentConfig } from "@opencode-ai/sdk"
+import { createEnvContext } from "../env-context"
+
+export function applyEnvironmentContext(config: AgentConfig, directory?: string): AgentConfig {
+  if (!directory || !config.prompt) return config
+  const envContext = createEnvContext()
+  return { ...config, prompt: config.prompt + envContext }
+}

src/agents/builtin-agents/general-agents.ts

@@ -0,0 +1,103 @@
+import type { AgentConfig } from "@opencode-ai/sdk"
+import type { BuiltinAgentName, AgentOverrides, AgentPromptMetadata } from "../types"
+import type { CategoryConfig, GitMasterConfig } from "../../config/schema"
+import type { BrowserAutomationProvider } from "../../config/schema"
+import type { AvailableAgent } from "../dynamic-agent-prompt-builder"
+import { AGENT_MODEL_REQUIREMENTS, isModelAvailable } from "../../shared"
+import { buildAgent, isFactory } from "../agent-builder"
+import { applyOverrides } from "./agent-overrides"
+import { applyEnvironmentContext } from "./environment-context"
+import { applyModelResolution } from "./model-resolution"
+
+export function collectPendingBuiltinAgents(input: {
+  agentSources: Record<BuiltinAgentName, import("../agent-builder").AgentSource>
+  agentMetadata: Partial<Record<BuiltinAgentName, AgentPromptMetadata>>
+  disabledAgents: string[]
+  agentOverrides: AgentOverrides
+  directory?: string
+  systemDefaultModel?: string
+  mergedCategories: Record<string, CategoryConfig>
+  gitMasterConfig?: GitMasterConfig
+  browserProvider?: BrowserAutomationProvider
+  uiSelectedModel?: string
+  availableModels: Set<string>
+  disabledSkills?: Set<string>
+  useTaskSystem?: boolean
+}): { pendingAgentConfigs: Map<string, AgentConfig>; availableAgents: AvailableAgent[] } {
+  const {
+    agentSources,
+    agentMetadata,
+    disabledAgents,
+    agentOverrides,
+    directory,
+    systemDefaultModel,
+    mergedCategories,
+    gitMasterConfig,
+    browserProvider,
+    uiSelectedModel,
+    availableModels,
+    disabledSkills,
+  } = input
+
+  const availableAgents: AvailableAgent[] = []
+  const pendingAgentConfigs: Map<string, AgentConfig> = new Map()
+
+  for (const [name, source] of Object.entries(agentSources)) {
+    const agentName = name as BuiltinAgentName
+
+    if (agentName === "sisyphus") continue
+    if (agentName === "hephaestus") continue
+    if (agentName === "atlas") continue
+    if (disabledAgents.some((name) => name.toLowerCase() === agentName.toLowerCase())) continue
+
+    const override = agentOverrides[agentName]
+      ?? Object.entries(agentOverrides).find(([key]) => key.toLowerCase() === agentName.toLowerCase())?.[1]
+    const requirement = AGENT_MODEL_REQUIREMENTS[agentName]
+
+    // Check if agent requires a specific model
+    if (requirement?.requiresModel && availableModels) {
+      if (!isModelAvailable(requirement.requiresModel, availableModels)) {
+        continue
+      }
+    }
+
+    const isPrimaryAgent = isFactory(source) && source.mode === "primary"
+
+    const resolution = applyModelResolution({
+      uiSelectedModel: (isPrimaryAgent && !override?.model) ? uiSelectedModel : undefined,
+      userModel: override?.model,
+      requirement,
+      availableModels,
+      systemDefaultModel,
+    })
+    if (!resolution) continue
+    const { model, variant: resolvedVariant } = resolution
+
+    let config = buildAgent(source, model, mergedCategories, gitMasterConfig, browserProvider, disabledSkills)
+
+    // Apply resolved variant from model fallback chain
+    if (resolvedVariant) {
+      config = { ...config, variant: resolvedVariant }
+    }
+
+    if (agentName === "librarian") {
+      config = applyEnvironmentContext(config, directory)
+    }
+
+    config = applyOverrides(config, override, mergedCategories, directory)
+
+    // Store for later - will be added after sisyphus and hephaestus
+    pendingAgentConfigs.set(name, config)
+
+    const metadata = agentMetadata[agentName]
+    if (metadata) {
+      availableAgents.push({
+        name: agentName,
+        description: config.description ?? "",
+        metadata,
+      })
+    }
+  }
+
+  return { pendingAgentConfigs, availableAgents }
+}

src/agents/builtin-agents/hephaestus-agent.ts

@@ -0,0 +1,91 @@
+import type { AgentConfig } from "@opencode-ai/sdk"
+import type { AgentOverrides } from "../types"
+import type { CategoryConfig } from "../../config/schema"
+import type { AvailableAgent, AvailableCategory, AvailableSkill } from "../dynamic-agent-prompt-builder"
+import { AGENT_MODEL_REQUIREMENTS, isAnyProviderConnected } from "../../shared"
+import { createHephaestusAgent } from "../hephaestus"
+import { createEnvContext } from "../env-context"
+import { applyCategoryOverride, mergeAgentConfig } from "./agent-overrides"
+import { applyModelResolution, getFirstFallbackModel } from "./model-resolution"
+
+export function maybeCreateHephaestusConfig(input: {
+  disabledAgents: string[]
+  agentOverrides: AgentOverrides
+  availableModels: Set<string>
+  systemDefaultModel?: string
+  isFirstRunNoCache: boolean
+  availableAgents: AvailableAgent[]
+  availableSkills: AvailableSkill[]
+  availableCategories: AvailableCategory[]
+  mergedCategories: Record<string, CategoryConfig>
+  directory?: string
+  useTaskSystem: boolean
+}): AgentConfig | undefined {
+  const {
+    disabledAgents,
+    agentOverrides,
+    availableModels,
+    systemDefaultModel,
+    isFirstRunNoCache,
+    availableAgents,
+    availableSkills,
+    availableCategories,
+    mergedCategories,
+    directory,
+    useTaskSystem,
+  } = input
+
+  if (disabledAgents.includes("hephaestus")) return undefined
+
+  const hephaestusOverride = agentOverrides["hephaestus"]
+  const hephaestusRequirement = AGENT_MODEL_REQUIREMENTS["hephaestus"]
+  const hasHephaestusExplicitConfig = hephaestusOverride !== undefined
+
+  const hasRequiredProvider =
+    !hephaestusRequirement?.requiresProvider ||
+    hasHephaestusExplicitConfig ||
+    isFirstRunNoCache ||
+    isAnyProviderConnected(hephaestusRequirement.requiresProvider, availableModels)
+
+  if (!hasRequiredProvider) return undefined
+
+  let hephaestusResolution = applyModelResolution({
+    userModel: hephaestusOverride?.model,
+    requirement: hephaestusRequirement,
+    availableModels,
+    systemDefaultModel,
+  })
+
+  if (isFirstRunNoCache && !hephaestusOverride?.model) {
+    hephaestusResolution = getFirstFallbackModel(hephaestusRequirement)
+  }
+
+  if (!hephaestusResolution) return undefined
+  const { model: hephaestusModel, variant: hephaestusResolvedVariant } = hephaestusResolution
+
+  let hephaestusConfig = createHephaestusAgent(
+    hephaestusModel,
+    availableAgents,
+    undefined,
+    availableSkills,
+    availableCategories,
+    useTaskSystem
+  )
+
+  hephaestusConfig = { ...hephaestusConfig, variant: hephaestusResolvedVariant ?? "medium" }
+
+  const hepOverrideCategory = (hephaestusOverride as Record<string, unknown> | undefined)?.category as string | undefined
+  if (hepOverrideCategory) {
+    hephaestusConfig = applyCategoryOverride(hephaestusConfig, hepOverrideCategory, mergedCategories)
+  }
+
+  if (directory && hephaestusConfig.prompt) {
+    const envContext = createEnvContext()
+    hephaestusConfig = { ...hephaestusConfig, prompt: hephaestusConfig.prompt + envContext }
+  }
+
+  if (hephaestusOverride) {
+    hephaestusConfig = mergeAgentConfig(hephaestusConfig, hephaestusOverride, directory)
+  }
+  return hephaestusConfig
+}

src/agents/builtin-agents/model-resolution.ts

@@ -0,0 +1,28 @@
+import { resolveModelPipeline } from "../../shared"
+
+export function applyModelResolution(input: {
+  uiSelectedModel?: string
+  userModel?: string
+  requirement?: { fallbackChain?: { providers: string[]; model: string; variant?: string }[] }
+  availableModels: Set<string>
+  systemDefaultModel?: string
+}) {
+  const { uiSelectedModel, userModel, requirement, availableModels, systemDefaultModel } = input
+  return resolveModelPipeline({
+    intent: { uiSelectedModel, userModel },
+    constraints: { availableModels },
+    policy: { fallbackChain: requirement?.fallbackChain, systemDefaultModel },
+  })
+}
+
+export function getFirstFallbackModel(requirement?: {
+  fallbackChain?: { providers: string[]; model: string; variant?: string }[]
+}) {
+  const entry = requirement?.fallbackChain?.[0]
+  if (!entry || entry.providers.length === 0) return undefined
+  return {
+    model: `${entry.providers[0]}/${entry.model}`,
+    provenance: "provider-fallback" as const,
+    variant: entry.variant,
+  }
+}

src/agents/builtin-agents/resolve-file-uri.test.ts

@@ -0,0 +1,109 @@
+import { afterAll, beforeAll, describe, expect, test } from "bun:test"
+import { mkdirSync, rmSync, writeFileSync } from "node:fs"
+import { homedir, tmpdir } from "node:os"
+import { join } from "node:path"
+import { resolvePromptAppend } from "./resolve-file-uri"
+
+describe("resolvePromptAppend", () => {
+  const fixtureRoot = join(tmpdir(), `resolve-file-uri-${Date.now()}`)
+  const configDir = join(fixtureRoot, "config")
+  const homeFixtureDir = join(homedir(), `.resolve-file-uri-home-${Date.now()}`)
+
+  const absoluteFilePath = join(fixtureRoot, "absolute.txt")
+  const relativeFilePath = join(configDir, "relative.txt")
+  const spacedFilePath = join(fixtureRoot, "with space.txt")
+  const homeFilePath = join(homeFixtureDir, "home.txt")
+
+  beforeAll(() => {
+    mkdirSync(fixtureRoot, { recursive: true })
+    mkdirSync(configDir, { recursive: true })
+    mkdirSync(homeFixtureDir, { recursive: true })
+
+    writeFileSync(absoluteFilePath, "absolute-content", "utf8")
+    writeFileSync(relativeFilePath, "relative-content", "utf8")
+    writeFileSync(spacedFilePath, "encoded-content", "utf8")
+    writeFileSync(homeFilePath, "home-content", "utf8")
+  })
+
+  afterAll(() => {
+    rmSync(fixtureRoot, { recursive: true, force: true })
+    rmSync(homeFixtureDir, { recursive: true, force: true })
+  })
+
+  test("returns non-file URI strings unchanged", () => {
+    //#given
+    const input = "append this text"
+
+    //#when
+    const resolved = resolvePromptAppend(input)
+
+    //#then
+    expect(resolved).toBe(input)
+  })
+
+  test("resolves absolute file URI to file contents", () => {
+    //#given
+    const input = `file://${absoluteFilePath}`
+
+    //#when
+    const resolved = resolvePromptAppend(input)
+
+    //#then
+    expect(resolved).toBe("absolute-content")
+  })
+
+  test("resolves relative file URI using configDir", () => {
+    //#given
+    const input = "file://./relative.txt"
+
+    //#when
+    const resolved = resolvePromptAppend(input, configDir)
+
+    //#then
+    expect(resolved).toBe("relative-content")
+  })
+
+  test("resolves home directory URI path", () => {
+    //#given
+    const input = `file://~/${homeFixtureDir.split("/").pop()}/home.txt`
+
+    //#when
+    const resolved = resolvePromptAppend(input)
+
+    //#then
+    expect(resolved).toBe("home-content")
+  })
+
+  test("resolves percent-encoded URI path", () => {
+    //#given
+    const input = `file://${encodeURIComponent(spacedFilePath)}`
+
+    //#when
+    const resolved = resolvePromptAppend(input)
+
+    //#then
+    expect(resolved).toBe("encoded-content")
+  })
+
+  test("returns warning for malformed percent-encoding", () => {
+    //#given
+    const input = "file://%E0%A4%A"
+
+    //#when
+    const resolved = resolvePromptAppend(input)
+
+    //#then
+    expect(resolved).toContain("[WARNING: Malformed file URI")
+  })
+
+  test("returns warning when file does not exist", () => {
+    //#given
+    const input = "file:///path/does/not/exist.txt"
+
+    //#when
+    const resolved = resolvePromptAppend(input)
+
+    //#then
+    expect(resolved).toContain("[WARNING: Could not resolve file URI")
+  })
+})

src/agents/builtin-agents/resolve-file-uri.ts

@@ -0,0 +1,30 @@
+import { existsSync, readFileSync } from "node:fs"
+import { homedir } from "node:os"
+import { isAbsolute, resolve } from "node:path"
+
+export function resolvePromptAppend(promptAppend: string, configDir?: string): string {
+  if (!promptAppend.startsWith("file://")) return promptAppend
+
+  const encoded = promptAppend.slice(7)
+
+  let filePath: string
+  try {
+    const decoded = decodeURIComponent(encoded)
+    const expanded = decoded.startsWith("~/") ? decoded.replace(/^~\//, `${homedir()}/`) : decoded
+    filePath = isAbsolute(expanded)
+      ? expanded
+      : resolve(configDir ?? process.cwd(), expanded)
+  } catch {
+    return `[WARNING: Malformed file URI (invalid percent-encoding): ${promptAppend}]`
+  }
+
+  if (!existsSync(filePath)) {
+    return `[WARNING: Could not resolve file URI: ${promptAppend}]`
+  }
+
+  try {
+    return readFileSync(filePath, "utf8")
+  } catch {
+    return `[WARNING: Could not read file: ${promptAppend}]`
+  }
+}

src/agents/builtin-agents/sisyphus-agent.ts

@@ -0,0 +1,84 @@
+import type { AgentConfig } from "@opencode-ai/sdk"
+import type { AgentOverrides } from "../types"
+import type { CategoriesConfig, CategoryConfig } from "../../config/schema"
+import type { AvailableAgent, AvailableCategory, AvailableSkill } from "../dynamic-agent-prompt-builder"
+import { AGENT_MODEL_REQUIREMENTS, isAnyFallbackModelAvailable } from "../../shared"
+import { applyEnvironmentContext } from "./environment-context"
+import { applyOverrides } from "./agent-overrides"
+import { applyModelResolution, getFirstFallbackModel } from "./model-resolution"
+import { createSisyphusAgent } from "../sisyphus"
+
+export function maybeCreateSisyphusConfig(input: {
+  disabledAgents: string[]
+  agentOverrides: AgentOverrides
+  uiSelectedModel?: string
+  availableModels: Set<string>
+  systemDefaultModel?: string
+  isFirstRunNoCache: boolean
+  availableAgents: AvailableAgent[]
+  availableSkills: AvailableSkill[]
+  availableCategories: AvailableCategory[]
+  mergedCategories: Record<string, CategoryConfig>
+  directory?: string
+  userCategories?: CategoriesConfig
+  useTaskSystem: boolean
+}): AgentConfig | undefined {
+  const {
+    disabledAgents,
+    agentOverrides,
+    uiSelectedModel,
+    availableModels,
+    systemDefaultModel,
+    isFirstRunNoCache,
+    availableAgents,
+    availableSkills,
+    availableCategories,
+    mergedCategories,
+    directory,
+    useTaskSystem,
+  } = input
+
+  const sisyphusOverride = agentOverrides["sisyphus"]
+  const sisyphusRequirement = AGENT_MODEL_REQUIREMENTS["sisyphus"]
+  const hasSisyphusExplicitConfig = sisyphusOverride !== undefined
+  const meetsSisyphusAnyModelRequirement =
+    !sisyphusRequirement?.requiresAnyModel ||
+    hasSisyphusExplicitConfig ||
+    isFirstRunNoCache ||
+    isAnyFallbackModelAvailable(sisyphusRequirement.fallbackChain, availableModels)
+
+  if (disabledAgents.includes("sisyphus") || !meetsSisyphusAnyModelRequirement) return undefined
+
+  let sisyphusResolution = applyModelResolution({
+    uiSelectedModel: sisyphusOverride?.model ? undefined : uiSelectedModel,
+    userModel: sisyphusOverride?.model,
+    requirement: sisyphusRequirement,
+    availableModels,
+    systemDefaultModel,
+  })
+
+  if (isFirstRunNoCache && !sisyphusOverride?.model && !uiSelectedModel) {
+    sisyphusResolution = getFirstFallbackModel(sisyphusRequirement)
+  }
+
+  if (!sisyphusResolution) return undefined
+  const { model: sisyphusModel, variant: sisyphusResolvedVariant } = sisyphusResolution
+
+  let sisyphusConfig = createSisyphusAgent(
+    sisyphusModel,
+    availableAgents,
+    undefined,
+    availableSkills,
+    availableCategories,
+    useTaskSystem
+  )
+
+  if (sisyphusResolvedVariant) {
+    sisyphusConfig = { ...sisyphusConfig, variant: sisyphusResolvedVariant }
+  }
+
+  sisyphusConfig = applyOverrides(sisyphusConfig, sisyphusOverride, mergedCategories, directory)
+  sisyphusConfig = applyEnvironmentContext(sisyphusConfig, directory)
+
+  return sisyphusConfig
+}

src/agents/custom-agent-summaries.ts

@@ -0,0 +1,61 @@
+import type { AgentPromptMetadata } from "./types"
+import { truncateDescription } from "../shared/truncate-description"
+
+type RegisteredAgentSummary = {
+  name: string
+  description: string
+}
+
+function sanitizeMarkdownTableCell(value: string): string {
+  return value
+    .replace(/\r?\n/g, " ")
+    .replace(/\|/g, "\\|")
+    .replace(/\s+/g, " ")
+    .trim()
+}
+
+function isRecord(value: unknown): value is Record<string, unknown> {
+  return typeof value === "object" && value !== null
+}
+
+export function parseRegisteredAgentSummaries(input: unknown): RegisteredAgentSummary[] {
+  if (!Array.isArray(input)) return []
+
+  const result: RegisteredAgentSummary[] = []
+  for (const item of input) {
+    if (!isRecord(item)) continue
+
+    const name = typeof item.name === "string" ? item.name : undefined
+    if (!name) continue
+
+    const hidden = item.hidden
+    if (hidden === true) continue
+
+    const disabled = item.disabled
+    if (disabled === true) continue
+
+    const enabled = item.enabled
+    if (enabled === false) continue
+
+    const description = typeof item.description === "string" ? item.description : ""
+    result.push({ name: sanitizeMarkdownTableCell(name), description: sanitizeMarkdownTableCell(description) })
+  }
+
+  return result
+}
+
+export function buildCustomAgentMetadata(agentName: string, description: string): AgentPromptMetadata {
+  const shortDescription = sanitizeMarkdownTableCell(truncateDescription(description))
+  const safeAgentName = sanitizeMarkdownTableCell(agentName)
+
+  return {
+    category: "specialist",
+    cost: "CHEAP",
+    triggers: [
+      {
+        domain: `Custom agent: ${safeAgentName}`,
+        trigger: shortDescription || "Use when this agent's description matches the task",
+      },
+    ],
+  }
+}

src/agents/dynamic-agent-prompt-builder.test.ts

@@ -0,0 +1,205 @@
+/// <reference types="bun-types" />
+
+import { describe, it, expect } from "bun:test"
+import {
+  buildCategorySkillsDelegationGuide,
+  buildUltraworkSection,
+  formatCustomSkillsBlock,
+  type AvailableSkill,
+  type AvailableCategory,
+  type AvailableAgent,
+} from "./dynamic-agent-prompt-builder"
+
+describe("buildCategorySkillsDelegationGuide", () => {
+  const categories: AvailableCategory[] = [
+    { name: "visual-engineering", description: "Frontend, UI/UX" },
+    { name: "quick", description: "Trivial tasks" },
+  ]
+
+  const builtinSkills: AvailableSkill[] = [
+    { name: "playwright", description: "Browser automation via Playwright", location: "plugin" },
+    { name: "frontend-ui-ux", description: "Designer-turned-developer", location: "plugin" },
+  ]
+
+  const customUserSkills: AvailableSkill[] = [
+    { name: "react-19", description: "React 19 patterns and best practices", location: "user" },
+    { name: "tailwind-4", description: "Tailwind CSS v4 utilities", location: "user" },
+  ]
+
+  const customProjectSkills: AvailableSkill[] = [
+    { name: "our-design-system", description: "Internal design system components", location: "project" },
+  ]
+
+  it("should separate builtin and custom skills into distinct sections", () => {
+    //#given: mix of builtin and custom skills
+    const allSkills = [...builtinSkills, ...customUserSkills]
+
+    //#when: building the delegation guide
+    const result = buildCategorySkillsDelegationGuide(categories, allSkills)
+
+    //#then: should have separate sections
+    expect(result).toContain("Built-in Skills")
+    expect(result).toContain("User-Installed Skills")
+    expect(result).toContain("HIGH PRIORITY")
+  })
+
+  it("should include custom skill names in CRITICAL warning", () => {
+    //#given: custom skills installed
+    const allSkills = [...builtinSkills, ...customUserSkills]
+
+    //#when: building the delegation guide
+    const result = buildCategorySkillsDelegationGuide(categories, allSkills)
+
+    //#then: should mention custom skills by name in the warning
+    expect(result).toContain('"react-19"')
+    expect(result).toContain('"tailwind-4"')
+    expect(result).toContain("CRITICAL")
+  })
+
+  it("should show source column for custom skills (user vs project)", () => {
+    //#given: both user and project custom skills
+    const allSkills = [...builtinSkills, ...customUserSkills, ...customProjectSkills]
+
+    //#when: building the delegation guide
+    const result = buildCategorySkillsDelegationGuide(categories, allSkills)
+
+    //#then: should show source for each custom skill
+    expect(result).toContain("| user |")
+    expect(result).toContain("| project |")
+  })
+
+  it("should not show custom skill section when only builtin skills exist", () => {
+    //#given: only builtin skills
+    const allSkills = [...builtinSkills]
+
+    //#when: building the delegation guide
+    const result = buildCategorySkillsDelegationGuide(categories, allSkills)
+
+    //#then: should not contain custom skill emphasis
+    expect(result).not.toContain("User-Installed Skills")
+    expect(result).not.toContain("HIGH PRIORITY")
+    expect(result).toContain("Available Skills")
+  })
+
+  it("should handle only custom skills (no builtins)", () => {
+    //#given: only custom skills, no builtins
+    const allSkills = [...customUserSkills]
+
+    //#when: building the delegation guide
+    const result = buildCategorySkillsDelegationGuide(categories, allSkills)
+
+    //#then: should show custom skills with emphasis, no builtin section
+    expect(result).toContain("User-Installed Skills")
+    expect(result).toContain("HIGH PRIORITY")
+    expect(result).not.toContain("Built-in Skills")
+  })
+
+  it("should include priority note for custom skills in evaluation step", () => {
+    //#given: custom skills present
+    const allSkills = [...builtinSkills, ...customUserSkills]
+
+    //#when: building the delegation guide
+    const result = buildCategorySkillsDelegationGuide(categories, allSkills)
+
+    //#then: evaluation section should mention user-installed priority
+    expect(result).toContain("User-installed skills get PRIORITY")
+    expect(result).toContain("INCLUDE it rather than omit it")
+  })
+
+  it("should NOT include priority note when no custom skills", () => {
+    //#given: only builtin skills
+    const allSkills = [...builtinSkills]
+
+    //#when: building the delegation guide
+    const result = buildCategorySkillsDelegationGuide(categories, allSkills)
+
+    //#then: no priority note for custom skills
+    expect(result).not.toContain("User-installed skills get PRIORITY")
+  })
+
+  it("should return empty string when no categories and no skills", () => {
+    //#given: no categories and no skills
+    //#when: building the delegation guide
+    const result = buildCategorySkillsDelegationGuide([], [])
+
+    //#then: should return empty string
+    expect(result).toBe("")
+  })
+})
+
+describe("buildUltraworkSection", () => {
+  const agents: AvailableAgent[] = []
+
+  it("should separate builtin and custom skills", () => {
+    //#given: mix of builtin and custom skills
+    const skills: AvailableSkill[] = [
+      { name: "playwright", description: "Browser automation", location: "plugin" },
+      { name: "react-19", description: "React 19 patterns", location: "user" },
+    ]
+
+    //#when: building ultrawork section
+    const result = buildUltraworkSection(agents, [], skills)
+
+    //#then: should have separate sections
+    expect(result).toContain("Built-in Skills")
+    expect(result).toContain("User-Installed Skills")
+    expect(result).toContain("HIGH PRIORITY")
+  })
+
+  it("should not separate when only builtin skills", () => {
+    //#given: only builtin skills
+    const skills: AvailableSkill[] = [
+      { name: "playwright", description: "Browser automation", location: "plugin" },
+    ]
+
+    //#when: building ultrawork section
+    const result = buildUltraworkSection(agents, [], skills)
+
+    //#then: should have single section
+    expect(result).toContain("Built-in Skills")
+    expect(result).not.toContain("User-Installed Skills")
+  })
+})
+
+describe("formatCustomSkillsBlock", () => {
+  const customSkills: AvailableSkill[] = [
+    { name: "react-19", description: "React 19 patterns", location: "user" },
+    { name: "tailwind-4", description: "Tailwind v4", location: "project" },
+  ]
+
+  const customRows = customSkills.map((s) => {
+    const source = s.location === "project" ? "project" : "user"
+    return `| \`${s.name}\` | ${s.description} | ${source} |`
+  })
+
+  it("should produce consistent output used by both builders", () => {
+    //#given: custom skills and rows
+    //#when: formatting with default header level
+    const result = formatCustomSkillsBlock(customRows, customSkills)
+
+    //#then: contains all expected elements
+    expect(result).toContain("User-Installed Skills (HIGH PRIORITY)")
+    expect(result).toContain("CRITICAL")
+    expect(result).toContain('"react-19"')
+    expect(result).toContain('"tailwind-4"')
+    expect(result).toContain("| user |")
+    expect(result).toContain("| project |")
+  })
+
+  it("should use #### header by default", () => {
+    //#given: default header level
+    const result = formatCustomSkillsBlock(customRows, customSkills)
+
+    //#then: uses markdown h4
+    expect(result).toContain("#### User-Installed Skills")
+  })
+
+  it("should use bold header when specified", () => {
+    //#given: bold header level (used by Atlas)
+    const result = formatCustomSkillsBlock(customRows, customSkills, "**")
+
+    //#then: uses bold instead of h4
+    expect(result).toContain("**User-Installed Skills (HIGH PRIORITY):**")
+    expect(result).not.toContain("#### User-Installed Skills")
+  })
+})

src/agents/dynamic-agent-prompt-builder.ts

@@ -1,7 +1,8 @@
-import type { AgentPromptMetadata, BuiltinAgentName } from "./types"
+import type { AgentPromptMetadata } from "./types"
+import { truncateDescription } from "../shared/truncate-description"
 
 export interface AvailableAgent {
-  name: BuiltinAgentName
+  name: string
   description: string
   metadata: AgentPromptMetadata
 }
@@ -20,6 +21,7 @@ export interface AvailableSkill {
 export interface AvailableCategory {
   name: string
   description: string
+  model?: string
 }
 
 export function categorizeTools(toolNames: string[]): AvailableTool[] {
@@ -166,6 +168,33 @@ export function buildDelegationTable(agents: AvailableAgent[]): string {
   return rows.join("\n")
 }
 
+/**
+ * Renders the "User-Installed Skills (HIGH PRIORITY)" block used across multiple agent prompts.
+ * Extracted to avoid duplication between buildCategorySkillsDelegationGuide, buildSkillsSection, etc.
+ */
+export function formatCustomSkillsBlock(
+  customRows: string[],
+  customSkills: AvailableSkill[],
+  headerLevel: "####" | "**" = "####"
+): string {
+  const customSkillNames = customSkills.map((s) => `"${s.name}"`).join(", ")
+  const header = headerLevel === "####"
+    ? `#### User-Installed Skills (HIGH PRIORITY)`
+    : `**User-Installed Skills (HIGH PRIORITY):**`
+
+  return `${header}
+
+**The user has installed these custom skills. They MUST be evaluated for EVERY delegation.**
+Subagents are STATELESS — they lose all custom knowledge unless you pass these skills via \`load_skills\`.
+
+| Skill | Expertise Domain | Source |
+|-------|------------------|--------|
+${customRows.join("\n")}
+
+> **CRITICAL**: Ignoring user-installed skills when they match the task domain is a failure.
+> The user installed ${customSkillNames} for a reason — USE THEM when the task overlaps with their domain.`
+}
+
 export function buildCategorySkillsDelegationGuide(categories: AvailableCategory[], skills: AvailableSkill[]): string {
   if (categories.length === 0 && skills.length === 0) return ""
 
@@ -174,14 +203,47 @@ export function buildCategorySkillsDelegationGuide(categories: AvailableCategory
     return `| \`${c.name}\` | ${desc} |`
   })
 
-  const skillRows = skills.map((s) => {
-    const desc = s.description.split(".")[0] || s.description
-    return `| \`${s.name}\` | ${desc} |`
-  })
+  const builtinSkills = skills.filter((s) => s.location === "plugin")
+  const customSkills = skills.filter((s) => s.location !== "plugin")
+
+   const builtinRows = builtinSkills.map((s) => {
+     const desc = truncateDescription(s.description)
+     return `| \`${s.name}\` | ${desc} |`
+   })
+
+   const customRows = customSkills.map((s) => {
+     const desc = truncateDescription(s.description)
+     const source = s.location === "project" ? "project" : "user"
+     return `| \`${s.name}\` | ${desc} | ${source} |`
+   })
+
+  const customSkillBlock = formatCustomSkillsBlock(customRows, customSkills)
+
+  let skillsSection: string
+
+  if (customSkills.length > 0 && builtinSkills.length > 0) {
+    skillsSection = `#### Built-in Skills
+
+| Skill | Expertise Domain |
+|-------|------------------|
+${builtinRows.join("\n")}
+
+${customSkillBlock}`
+  } else if (customSkills.length > 0) {
+    skillsSection = customSkillBlock
+  } else {
+    skillsSection = `#### Available Skills (Domain Expertise Injection)
+
+Skills inject specialized instructions into the subagent. Read the description to understand when each skill applies.
+
+| Skill | Expertise Domain |
+|-------|------------------|
+${builtinRows.join("\n")}`
+  }
 
   return `### Category + Skills Delegation System
 
-**delegate_task() combines categories and skills for optimal task execution.**
+**task() combines categories and skills for optimal task execution.**
 
 #### Available Categories (Domain-Optimized Models)
 
@@ -191,13 +253,7 @@ Each category is configured with a model optimized for that domain. Read the des
 |----------|-------------------|
 ${categoryRows.join("\n")}
 
-#### Available Skills (Domain Expertise Injection)
-
-Skills inject specialized instructions into the subagent. Read the description to understand when each skill applies.
-
-| Skill | Expertise Domain |
-|-------|------------------|
-${skillRows.join("\n")}
+${skillsSection}
 
 ---
 
@@ -208,12 +264,15 @@ ${skillRows.join("\n")}
 - Match task requirements to category domain
 - Select the category whose domain BEST fits the task
 
-**STEP 2: Evaluate ALL Skills**
+**STEP 2: Evaluate ALL Skills (Built-in AND User-Installed)**
 For EVERY skill listed above, ask yourself:
 > "Does this skill's expertise domain overlap with my task?"
 
 - If YES → INCLUDE in \`load_skills=[...]\`
 - If NO → You MUST justify why (see below)
+${customSkills.length > 0 ? `
+> **User-installed skills get PRIORITY.** The user explicitly installed them for their workflow.
+> When in doubt about a user-installed skill, INCLUDE it rather than omit it.` : ""}
 
 **STEP 3: Justify Omissions**
 
@@ -238,16 +297,16 @@ SKILL EVALUATION for "[skill-name]":
 ### Delegation Pattern
 
 \`\`\`typescript
-delegate_task(
+task(
   category="[selected-category]",
-  load_skills=["skill-1", "skill-2"],  // Include ALL relevant skills
+  load_skills=["skill-1", "skill-2"],  // Include ALL relevant skills — ESPECIALLY user-installed ones
   prompt="..."
 )
 \`\`\`
 
 **ANTI-PATTERN (will produce poor results):**
 \`\`\`typescript
-delegate_task(category="...", load_skills=[], run_in_background=false, prompt="...")  // Empty load_skills without justification
+task(category="...", load_skills=[], run_in_background=false, prompt="...")  // Empty load_skills without justification
 \`\`\``
 }
 
@@ -277,6 +336,10 @@ ${avoidWhen.map((w) => `- ${w}`).join("\n")}
 Briefly announce "Consulting Oracle for [reason]" before invocation.
 
 **Exception**: This is the ONLY case where you announce before acting. For all other work, start immediately without status updates.
+
+### Oracle Background Task Policy:
+- Oracle takes 20+ min by design. Always wait for Oracle results via \`background_output\` before final answer.
+- Oracle provides independent analysis from a different angle that catches blind spots — even when you believe you already have sufficient context, Oracle's perspective is worth the wait.
 </Oracle_Usage>`
 }
 
@@ -328,12 +391,26 @@ export function buildUltraworkSection(
   }
 
   if (skills.length > 0) {
-    lines.push("**Skills** (combine with categories - EVALUATE ALL for relevance):")
-    for (const skill of skills) {
-      const shortDesc = skill.description.split(".")[0] || skill.description
-      lines.push(`- \`${skill.name}\`: ${shortDesc}`)
+    const builtinSkills = skills.filter((s) => s.location === "plugin")
+    const customSkills = skills.filter((s) => s.location !== "plugin")
+
+    if (builtinSkills.length > 0) {
+      lines.push("**Built-in Skills** (combine with categories):")
+      for (const skill of builtinSkills) {
+        const shortDesc = skill.description.split(".")[0] || skill.description
+        lines.push(`- \`${skill.name}\`: ${shortDesc}`)
+      }
+      lines.push("")
+    }
+
+    if (customSkills.length > 0) {
+      lines.push("**User-Installed Skills** (HIGH PRIORITY - user installed these for their workflow):")
+      for (const skill of customSkills) {
+        const shortDesc = skill.description.split(".")[0] || skill.description
+        lines.push(`- \`${skill.name}\`: ${shortDesc}`)
+      }
+      lines.push("")
     }
-    lines.push("")
   }
 
   if (agents.length > 0) {
@@ -349,7 +426,7 @@ export function buildUltraworkSection(
 
     lines.push("**Agents** (for specialized consultation/exploration):")
     for (const agent of sortedAgents) {
-      const shortDesc = agent.description.split(".")[0] || agent.description
+      const shortDesc = agent.description.length > 120 ? agent.description.slice(0, 120) + "..." : agent.description
       const suffix = agent.name === "explore" || agent.name === "librarian" ? " (multiple)" : ""
       lines.push(`- \`${agent.name}${suffix}\`: ${shortDesc}`)
     }

src/agents/env-context.ts

@@ -0,0 +1,33 @@
+/**
+ * Creates OmO-specific environment context (time, timezone, locale).
+ * Note: Working directory, platform, and date are already provided by OpenCode's system.ts,
+ * so we only include fields that OpenCode doesn't provide to avoid duplication.
+ * See: https://github.com/code-yeongyu/oh-my-opencode/issues/379
+ */
+export function createEnvContext(): string {
+  const now = new Date()
+  const timezone = Intl.DateTimeFormat().resolvedOptions().timeZone
+  const locale = Intl.DateTimeFormat().resolvedOptions().locale
+
+  const dateStr = now.toLocaleDateString(locale, {
+    weekday: "short",
+    year: "numeric",
+    month: "short",
+    day: "numeric",
+  })
+
+  const timeStr = now.toLocaleTimeString(locale, {
+    hour: "2-digit",
+    minute: "2-digit",
+    second: "2-digit",
+    hour12: true,
+  })
+
+  return `
+<omo-env>
+  Current date: ${dateStr}
+  Current time: ${timeStr}
+  Timezone: ${timezone}
+  Locale: ${locale}
+</omo-env>`
+}

src/agents/explore.ts

@@ -29,7 +29,7 @@ export function createExploreAgent(model: string): AgentConfig {
     "write",
     "edit",
     "task",
-    "delegate_task",
+    "task",
     "call_omo_agent",
   ])
 

src/agents/hephaestus.ts

@@ -1,6 +1,11 @@
-import type { AgentConfig } from "@opencode-ai/sdk"
-import type { AgentMode } from "./types"
-import type { AvailableAgent, AvailableTool, AvailableSkill, AvailableCategory } from "./dynamic-agent-prompt-builder"
+import type { AgentConfig } from "@opencode-ai/sdk";
+import type { AgentMode } from "./types";
+import type {
+  AvailableAgent,
+  AvailableTool,
+  AvailableSkill,
+  AvailableCategory,
+} from "./dynamic-agent-prompt-builder";
 import {
   buildKeyTriggersSection,
   buildToolSelectionTable,
@@ -12,9 +17,9 @@ import {
   buildHardBlocksSection,
   buildAntiPatternsSection,
   categorizeTools,
-} from "./dynamic-agent-prompt-builder"
+} from "./dynamic-agent-prompt-builder";
 
-const MODE: AgentMode = "primary"
+const MODE: AgentMode = "primary";
 
 function buildTodoDisciplineSection(useTaskSystem: boolean): string {
   if (useTaskSystem) {
@@ -26,15 +31,15 @@ function buildTodoDisciplineSection(useTaskSystem: boolean): string {
 
 | Trigger | Action |
 |---------|--------|
-| 2+ step task | \`TaskCreate\` FIRST, atomic breakdown |
-| Uncertain scope | \`TaskCreate\` to clarify thinking |
+| 2+ step task | \`task_create\` FIRST, atomic breakdown |
+| Uncertain scope | \`task_create\` to clarify thinking |
 | Complex single task | Break down into trackable steps |
 
 ### Workflow (STRICT)
 
-1. **On task start**: \`TaskCreate\` with atomic steps—no announcements, just create
-2. **Before each step**: \`TaskUpdate(status="in_progress")\` (ONE at a time)
-3. **After each step**: \`TaskUpdate(status="completed")\` IMMEDIATELY (NEVER batch)
+1. **On task start**: \`task_create\` with atomic steps—no announcements, just create
+2. **Before each step**: \`task_update(status=\"in_progress\")\` (ONE at a time)
+3. **After each step**: \`task_update(status=\"completed\")\` IMMEDIATELY (NEVER batch)
 4. **Scope changes**: Update tasks BEFORE proceeding
 
 ### Why This Matters
@@ -52,7 +57,7 @@ function buildTodoDisciplineSection(useTaskSystem: boolean): string {
 | Proceeding without \`in_progress\` | No indication of current work |
 | Finishing without completing tasks | Task appears incomplete |
 
-**NO TASKS ON MULTI-STEP WORK = INCOMPLETE WORK.**`
+**NO TASKS ON MULTI-STEP WORK = INCOMPLETE WORK.**`;
   }
 
   return `## Todo Discipline (NON-NEGOTIABLE)
@@ -89,7 +94,7 @@ function buildTodoDisciplineSection(useTaskSystem: boolean): string {
 | Proceeding without \`in_progress\` | No indication of current work |
 | Finishing without completing todos | Task appears incomplete |
 
-**NO TODOS ON MULTI-STEP WORK = INCOMPLETE WORK.**`
+**NO TODOS ON MULTI-STEP WORK = INCOMPLETE WORK.**`;
 }
 
 /**
@@ -98,7 +103,7 @@ function buildTodoDisciplineSection(useTaskSystem: boolean): string {
  * Named after the Greek god of forge, fire, metalworking, and craftsmanship.
  * Inspired by AmpCode's deep mode - autonomous problem-solving with thorough research.
  *
- * Powered by GPT 5.2 Codex with medium reasoning effort.
+ * Powered by GPT Codex models.
  * Optimized for:
  * - Goal-oriented autonomous execution (not step-by-step instructions)
  * - Deep exploration before decisive action
@@ -111,56 +116,58 @@ function buildHephaestusPrompt(
   availableTools: AvailableTool[] = [],
   availableSkills: AvailableSkill[] = [],
   availableCategories: AvailableCategory[] = [],
-  useTaskSystem = false
+  useTaskSystem = false,
 ): string {
-  const keyTriggers = buildKeyTriggersSection(availableAgents, availableSkills)
-  const toolSelection = buildToolSelectionTable(availableAgents, availableTools, availableSkills)
-  const exploreSection = buildExploreSection(availableAgents)
-  const librarianSection = buildLibrarianSection(availableAgents)
-  const categorySkillsGuide = buildCategorySkillsDelegationGuide(availableCategories, availableSkills)
-  const delegationTable = buildDelegationTable(availableAgents)
-  const oracleSection = buildOracleSection(availableAgents)
-  const hardBlocks = buildHardBlocksSection()
-  const antiPatterns = buildAntiPatternsSection()
-  const todoDiscipline = buildTodoDisciplineSection(useTaskSystem)
+  const keyTriggers = buildKeyTriggersSection(availableAgents, availableSkills);
+  const toolSelection = buildToolSelectionTable(
+    availableAgents,
+    availableTools,
+    availableSkills,
+  );
+  const exploreSection = buildExploreSection(availableAgents);
+  const librarianSection = buildLibrarianSection(availableAgents);
+  const categorySkillsGuide = buildCategorySkillsDelegationGuide(
+    availableCategories,
+    availableSkills,
+  );
+  const delegationTable = buildDelegationTable(availableAgents);
+  const oracleSection = buildOracleSection(availableAgents);
+  const hardBlocks = buildHardBlocksSection();
+  const antiPatterns = buildAntiPatternsSection();
+  const todoDiscipline = buildTodoDisciplineSection(useTaskSystem);
 
   return `You are Hephaestus, an autonomous deep worker for software engineering.
 
-## Reasoning Configuration (ROUTER NUDGE - GPT 5.2)
+## Identity
 
-Engage MEDIUM reasoning effort for all code modifications and architectural decisions.
-Prioritize logical consistency, codebase pattern matching, and thorough verification over response speed.
-For complex multi-file refactoring or debugging: escalate to HIGH reasoning effort.
+You operate as a **Senior Staff Engineer**. You do not guess. You verify. You do not stop early. You complete.
 
-## Identity & Expertise
+**You must keep going until the task is completely resolved, before ending your turn.** Persist until the task is fully handled end-to-end within the current turn. Persevere even when tool calls fail. Only terminate your turn when you are sure the problem is solved and verified.
 
-You operate as a **Senior Staff Engineer** with deep expertise in:
-- Repository-scale architecture comprehension
-- Autonomous problem decomposition and execution
-- Multi-file refactoring with full context awareness
-- Pattern recognition across large codebases
+When blocked: try a different approach → decompose the problem → challenge assumptions → explore how others solved it.
+Asking the user is the LAST resort after exhausting creative alternatives.
 
-You do not guess. You verify. You do not stop early. You complete.
+### Do NOT Ask — Just Do
 
-## Hard Constraints (MUST READ FIRST - GPT 5.2 Constraint-First)
+**FORBIDDEN:**
+- "Should I proceed with X?" → JUST DO IT.
+- "Do you want me to run tests?" → RUN THEM.
+- "I noticed Y, should I fix it?" → FIX IT OR NOTE IN FINAL MESSAGE.
+- Stopping after partial implementation → 100% OR NOTHING.
+
+**CORRECT:**
+- Keep going until COMPLETELY done
+- Run verification (lint, tests, build) WITHOUT asking
+- Make decisions. Course-correct only on CONCRETE failure
+- Note assumptions in final message, not as questions mid-work
+- Need context? Fire explore/librarian in background IMMEDIATELY — keep working while they search
+
+## Hard Constraints
 
 ${hardBlocks}
 
 ${antiPatterns}
 
-## Success Criteria (COMPLETION DEFINITION)
-
-A task is COMPLETE when ALL of the following are TRUE:
-1. All requested functionality implemented exactly as specified
-2. \`lsp_diagnostics\` returns zero errors on ALL modified files
-3. Build command exits with code 0 (if applicable)
-4. Tests pass (or pre-existing failures documented)
-5. No temporary/debug code remains
-6. Code matches existing codebase patterns (verified via exploration)
-7. Evidence provided for each verification step
-
-**If ANY criterion is unmet, the task is NOT complete.**
-
 ## Phase 0 - Intent Gate (EVERY task)
 
 ${keyTriggers}
@@ -175,79 +182,46 @@ ${keyTriggers}
 | **Open-ended** | "Improve", "Refactor", "Add feature" | Full Execution Loop required |
 | **Ambiguous** | Unclear scope, multiple interpretations | Ask ONE clarifying question |
 
-### Step 2: Handle Ambiguity WITHOUT Questions (GPT 5.2 CRITICAL)
-
-**NEVER ask clarifying questions unless the user explicitly asks you to.**
-
-**Default: EXPLORE FIRST. Questions are the LAST resort.**
+### Step 2: Ambiguity Protocol (EXPLORE FIRST — NEVER ask before exploring)
 
 | Situation | Action |
 |-----------|--------|
 | Single valid interpretation | Proceed immediately |
-| Missing info that MIGHT exist | **EXPLORE FIRST** - use tools (gh, git, grep, explore agents) to find it |
+| Missing info that MIGHT exist | **EXPLORE FIRST** — use tools (gh, git, grep, explore agents) to find it |
 | Multiple plausible interpretations | Cover ALL likely intents comprehensively, don't ask |
-| Info not findable after exploration | State your best-guess interpretation, proceed with it |
 | Truly impossible to proceed | Ask ONE precise question (LAST RESORT) |
 
-**EXPLORE-FIRST Protocol:**
-\`\`\`
-// WRONG: Ask immediately
-User: "Fix the PR review comments"
-Agent: "What's the PR number?"  // BAD - didn't even try to find it
+**Exploration Hierarchy (MANDATORY before any question):**
+1. Direct tools: \`gh pr list\`, \`git log\`, \`grep\`, \`rg\`, file reads
+2. Explore agents: Fire 2-3 parallel background searches
+3. Librarian agents: Check docs, GitHub, external sources
+4. Context inference: Educated guess from surrounding context
+5. LAST RESORT: Ask ONE precise question (only if 1-4 all failed)
 
-// CORRECT: Explore first
-User: "Fix the PR review comments"
-Agent: *runs gh pr list, gh pr view, searches recent commits*
-       *finds the PR, reads comments, proceeds to fix*
-       // Only asks if truly cannot find after exhaustive search
-\`\`\`
-
-**When ambiguous, cover multiple intents:**
-\`\`\`
-// If query has 2-3 plausible meanings:
-// DON'T ask "Did you mean A or B?"
-// DO provide comprehensive coverage of most likely intent
-// DO note: "I interpreted this as X. If you meant Y, let me know."
-\`\`\`
+If you notice a potential issue — fix it or note it in final message. Don't ask for permission.
 
 ### Step 3: Validate Before Acting
 
-**Delegation Check (MANDATORY before acting directly):**
+**Assumptions Check:**
+- Do I have any implicit assumptions that might affect the outcome?
+- Is the search scope clear?
+
+**Delegation Check (MANDATORY):**
+0. Find relevant skills to load — load them IMMEDIATELY.
 1. Is there a specialized agent that perfectly matches this request?
-2. If not, is there a \`delegate_task\` category that best describes this task? What skills are available to equip the agent with?
-   - MUST FIND skills to use: \`delegate_task(load_skills=[{skill1}, ...])\`
+2. If not, what \`task\` category + skills to equip? → \`task(load_skills=[{skill1}, ...])\`
 3. Can I do it myself for the best result, FOR SURE?
 
 **Default Bias: DELEGATE for complex tasks. Work yourself ONLY when trivial.**
 
-### Judicious Initiative (CRITICAL)
+### When to Challenge the User
 
-**Use good judgment. EXPLORE before asking. Deliver results, not questions.**
+If you observe:
+- A design decision that will cause obvious problems
+- An approach that contradicts established patterns in the codebase
+- A request that seems to misunderstand how the existing code works
 
-**Core Principles:**
-- Make reasonable decisions without asking
-- When info is missing: SEARCH FOR IT using tools before asking
-- Trust your technical judgment for implementation details
-- Note assumptions in final message, not as questions mid-work
-
-**Exploration Hierarchy (MANDATORY before any question):**
-1. **Direct tools**: \`gh pr list\`, \`git log\`, \`grep\`, \`rg\`, file reads
-2. **Explore agents**: Fire 2-3 parallel background searches
-3. **Librarian agents**: Check docs, GitHub, external sources
-4. **Context inference**: Use surrounding context to make educated guess
-5. **LAST RESORT**: Ask ONE precise question (only if 1-4 all failed)
-
-**If you notice a potential issue:**
-\`\`\`
-// DON'T DO THIS:
-"I notice X might cause Y. Should I proceed?"
-
-// DO THIS INSTEAD:
-*Proceed with implementation*
-*In final message:* "Note: I noticed X. I handled it by doing Z to avoid Y."
-\`\`\`
-
-**Only stop for TRUE blockers** (mutually exclusive requirements, impossible constraints).
+Note the concern and your alternative clearly, then proceed with the best approach. If the risk is major, flag it before implementing.
 
 ---
 
@@ -259,29 +233,40 @@ ${exploreSection}
 
 ${librarianSection}
 
-### Parallel Execution (DEFAULT behavior - NON-NEGOTIABLE)
+### Parallel Execution & Tool Usage (DEFAULT — NON-NEGOTIABLE)
 
-**Explore/Librarian = Grep, not consultants. ALWAYS run them in parallel as background tasks.**
+**Parallelize EVERYTHING. Independent reads, searches, and agents run SIMULTANEOUSLY.**
 
-\`\`\`typescript
-// CORRECT: Always background, always parallel
-// Prompt structure: [CONTEXT: what I'm doing] + [GOAL: what I'm trying to achieve] + [QUESTION: what I need to know] + [REQUEST: what to find]
-// Contextual Grep (internal)
-delegate_task(subagent_type="explore", run_in_background=true, load_skills=[], prompt="I'm implementing user authentication for our API. I need to understand how auth is currently structured in this codebase. Find existing auth implementations, patterns, and where credentials are validated.")
-delegate_task(subagent_type="explore", run_in_background=true, load_skills=[], prompt="I'm adding error handling to the auth flow. I want to follow existing project conventions for consistency. Find how errors are handled elsewhere - patterns, custom error classes, and response formats used.")
-// Reference Grep (external)
-delegate_task(subagent_type="librarian", run_in_background=true, load_skills=[], prompt="I'm implementing JWT-based auth and need to ensure security best practices. Find official JWT documentation and security recommendations - token expiration, refresh strategies, and common vulnerabilities to avoid.")
-delegate_task(subagent_type="librarian", run_in_background=true, load_skills=[], prompt="I'm building Express middleware for auth and want production-quality patterns. Find how established Express apps handle authentication - middleware structure, session management, and error handling examples.")
-// Continue immediately - collect results when needed
+<tool_usage_rules>
+- Parallelize independent tool calls: multiple file reads, grep searches, agent fires — all at once
+- Explore/Librarian = background grep. ALWAYS \`run_in_background=true\`, ALWAYS parallel
+- After any file edit: restate what changed, where, and what validation follows
+- Prefer tools over guessing whenever you need specific data (files, configs, patterns)
+</tool_usage_rules>
 
-// WRONG: Sequential or blocking - NEVER DO THIS
-result = delegate_task(..., run_in_background=false)  // Never wait synchronously for explore/librarian
+**How to call explore/librarian (EXACT syntax — use \`subagent_type\`, NOT \`category\`):**
 \`\`\`
+// Codebase search — use subagent_type="explore"
+task(subagent_type="explore", run_in_background=true, load_skills=[], description="Find [what]", prompt="[CONTEXT]: ... [GOAL]: ... [REQUEST]: ...")
+
+// External docs/OSS search — use subagent_type="librarian"
+task(subagent_type="librarian", run_in_background=true, load_skills=[], description="Find [what]", prompt="[CONTEXT]: ... [GOAL]: ... [REQUEST]: ...")
+
+// ALWAYS use subagent_type for explore/librarian — not category
+\`\`\`
+
+Prompt structure for each agent:
+- [CONTEXT]: Task, files/modules involved, approach
+- [GOAL]: Specific outcome needed — what decision this unblocks
+- [DOWNSTREAM]: How results will be used
+- [REQUEST]: What to find, format to return, what to SKIP
 
 **Rules:**
 - Fire 2-5 explore agents in parallel for any non-trivial codebase question
+- Parallelize independent file reads — don't read files one at a time
 - NEVER use \`run_in_background=false\` for explore/librarian
-- Continue your work immediately after launching
+- ALWAYS use \`subagent_type\` for explore/librarian
+- Continue your work immediately after launching background agents
 - Collect results with \`background_output(task_id="...")\` when needed
 - BEFORE final answer: \`background_cancel(all=true)\` to clean up
 
@@ -297,49 +282,20 @@ STOP searching when:
 
 ---
 
-## Execution Loop (EXPLORE → PLAN → DECIDE → EXECUTE)
+## Execution Loop (EXPLORE → PLAN → DECIDE → EXECUTE → VERIFY)
 
-For any non-trivial task, follow this loop:
+1. **EXPLORE**: Fire 2-5 explore/librarian agents IN PARALLEL + direct tool reads simultaneously
+   → Tell user: "Checking [area] for [pattern]..."
+2. **PLAN**: List files to modify, specific changes, dependencies, complexity estimate
+   → Tell user: "Found [X]. Here's my plan: [clear summary]."
+3. **DECIDE**: Trivial (<10 lines, single file) → self. Complex (multi-file, >100 lines) → MUST delegate
+4. **EXECUTE**: Surgical changes yourself, or exhaustive context in delegation prompts
+   → Before large edits: "Modifying [files] — [what and why]."
+   → After edits: "Updated [file] — [what changed]. Running verification."
+5. **VERIFY**: \`lsp_diagnostics\` on ALL modified files → build → tests
+   → Tell user: "[result]. [any issues or all clear]."
 
-### Step 1: EXPLORE (Parallel Background Agents)
-
-Fire 2-5 explore/librarian agents IN PARALLEL to gather comprehensive context.
-
-### Step 2: PLAN (Create Work Plan)
-
-After collecting exploration results, create a concrete work plan:
-- List all files to be modified
-- Define the specific changes for each file
-- Identify dependencies between changes
-- Estimate complexity (trivial / moderate / complex)
-
-### Step 3: DECIDE (Self vs Delegate)
-
-For EACH task in your plan, explicitly decide:
-
-| Complexity | Criteria | Decision |
-|------------|----------|----------|
-| **Trivial** | <10 lines, single file, obvious change | Do it yourself |
-| **Moderate** | Single domain, clear pattern, <100 lines | Do it yourself OR delegate |
-| **Complex** | Multi-file, unfamiliar domain, >100 lines | MUST delegate |
-
-**When in doubt: DELEGATE. The overhead is worth the quality.**
-
-### Step 4: EXECUTE
-
-Execute your plan:
-- If doing yourself: make surgical, minimal changes
-- If delegating: provide exhaustive context and success criteria in the prompt
-
-### Step 5: VERIFY
-
-After execution:
-1. Run \`lsp_diagnostics\` on ALL modified files
-2. Run build command (if applicable)
-3. Run tests (if applicable)
-4. Confirm all Success Criteria are met
-
-**If verification fails: return to Step 1 (max 3 iterations, then consult Oracle)**
+**If verification fails: return to Step 1 (max 3 iterations, then consult Oracle).**
 
 ---
 
@@ -347,219 +303,169 @@ ${todoDiscipline}
 
 ---
 
+## Progress Updates
+
+**Report progress proactively — the user should always know what you're doing and why.**
+
+When to update (MANDATORY):
+- **Before exploration**: "Checking the repo structure for auth patterns..."
+- **After discovery**: "Found the config in \`src/config/\`. The pattern uses factory functions."
+- **Before large edits**: "About to refactor the handler — touching 3 files."
+- **On phase transitions**: "Exploration done. Moving to implementation."
+- **On blockers**: "Hit a snag with the types — trying generics instead."
+
+Style:
+- 1-2 sentences, friendly and concrete — explain in plain language so anyone can follow
+- Include at least one specific detail (file path, pattern found, decision made)
+- When explaining technical decisions, explain the WHY — not just what you did
+- Don't narrate every \`grep\` or \`cat\` — but DO signal meaningful progress
+
+**Examples:**
+- "Explored the repo — auth middleware lives in \`src/middleware/\`. Now patching the handler."
+- "All tests passing. Just cleaning up the 2 lint errors from my changes."
+- "Found the pattern in \`utils/parser.ts\`. Applying the same approach to the new module."
+- "Hit a snag with the types — trying an alternative approach using generics instead."
+
+---
+
 ## Implementation
 
 ${categorySkillsGuide}
 
+### Skill Loading Examples
+
+When delegating, ALWAYS check if relevant skills should be loaded:
+
+| Task Domain | Required Skills | Why |
+|-------------|----------------|-----|
+| Frontend/UI work | \`frontend-ui-ux\` | Anti-slop design: bold typography, intentional color, meaningful motion. Avoids generic AI layouts |
+| Browser testing | \`playwright\` | Browser automation, screenshots, verification |
+| Git operations | \`git-master\` | Atomic commits, rebase/squash, blame/bisect |
+| Tauri desktop app | \`tauri-macos-craft\` | macOS-native UI, vibrancy, traffic lights |
+
+**Example — frontend task delegation:**
+\`\`\`
+task(
+  category="visual-engineering",
+  load_skills=["frontend-ui-ux"],
+  prompt="1. TASK: Build the settings page... 2. EXPECTED OUTCOME: ..."
+)
+\`\`\`
+
+**CRITICAL**: User-installed skills get PRIORITY. Always evaluate ALL available skills before delegating.
+
 ${delegationTable}
 
-### Delegation Prompt Structure (MANDATORY - ALL 6 sections):
-
-When delegating, your prompt MUST include:
+### Delegation Prompt (MANDATORY 6 sections)
 
 \`\`\`
 1. TASK: Atomic, specific goal (one action per delegation)
 2. EXPECTED OUTCOME: Concrete deliverables with success criteria
-3. REQUIRED TOOLS: Explicit tool whitelist (prevents tool sprawl)
-4. MUST DO: Exhaustive requirements - leave NOTHING implicit
-5. MUST NOT DO: Forbidden actions - anticipate and block rogue behavior
+3. REQUIRED TOOLS: Explicit tool whitelist
+4. MUST DO: Exhaustive requirements — leave NOTHING implicit
+5. MUST NOT DO: Forbidden actions — anticipate and block rogue behavior
 6. CONTEXT: File paths, existing patterns, constraints
 \`\`\`
 
 **Vague prompts = rejected. Be exhaustive.**
 
-### Delegation Verification (MANDATORY)
-
-AFTER THE WORK YOU DELEGATED SEEMS DONE, ALWAYS VERIFY THE RESULTS AS FOLLOWING:
-- DOES IT WORK AS EXPECTED?
-- DOES IT FOLLOW THE EXISTING CODEBASE PATTERN?
-- DID THE EXPECTED RESULT COME OUT?
-- DID THE AGENT FOLLOW "MUST DO" AND "MUST NOT DO" REQUIREMENTS?
-
+After delegation, ALWAYS verify: works as expected? follows codebase pattern? MUST DO / MUST NOT DO respected?
 **NEVER trust subagent self-reports. ALWAYS verify with your own tools.**
 
-### Session Continuity (MANDATORY)
+### Session Continuity
 
-Every \`delegate_task()\` output includes a session_id. **USE IT.**
+Every \`task()\` output includes a session_id. **USE IT for follow-ups.**
 
-**ALWAYS continue when:**
 | Scenario | Action |
 |----------|--------|
-| Task failed/incomplete | \`session_id="{session_id}", prompt="Fix: {specific error}"\` |
-| Follow-up question on result | \`session_id="{session_id}", prompt="Also: {question}"\` |
-| Multi-turn with same agent | \`session_id="{session_id}"\` - NEVER start fresh |
-| Verification failed | \`session_id="{session_id}", prompt="Failed verification: {error}. Fix."\` |
+| Task failed/incomplete | \`session_id="{id}", prompt="Fix: {error}"\` |
+| Follow-up on result | \`session_id="{id}", prompt="Also: {question}"\` |
+| Verification failed | \`session_id="{id}", prompt="Failed: {error}. Fix."\` |
 
-**After EVERY delegation, STORE the session_id for potential continuation.**
-
-${oracleSection ? `
+${
+  oracleSection
+    ? `
 ${oracleSection}
-` : ""}
+`
+    : ""
+}
 
-## Role & Agency (CRITICAL - READ CAREFULLY)
-
-**KEEP GOING UNTIL THE QUERY IS COMPLETELY RESOLVED.**
-
-Only terminate your turn when you are SURE the problem is SOLVED.
-Autonomously resolve the query to the BEST of your ability.
-Do NOT guess. Do NOT ask unnecessary questions. Do NOT stop early.
-
-**Completion Checklist (ALL must be true):**
-1. User asked for X → X is FULLY implemented (not partial, not "basic version")
-2. X passes lsp_diagnostics (zero errors on ALL modified files)
-3. X passes related tests (or you documented pre-existing failures)
-4. Build succeeds (if applicable)
-5. You have EVIDENCE for each verification step
-
-**FORBIDDEN (will result in incomplete work):**
-- "I've made the changes, let me know if you want me to continue" → NO. FINISH IT.
-- "Should I proceed with X?" → NO. JUST DO IT.
-- "Do you want me to run tests?" → NO. RUN THEM YOURSELF.
-- "I noticed Y, should I fix it?" → NO. FIX IT OR NOTE IT IN FINAL MESSAGE.
-- Stopping after partial implementation → NO. 100% OR NOTHING.
-- Asking about implementation details → NO. YOU DECIDE.
-
-**CORRECT behavior:**
-- Keep going until COMPLETELY done. No intermediate checkpoints with user.
-- Run verification (lint, tests, build) WITHOUT asking—just do it.
-- Make decisions. Course-correct only on CONCRETE failure.
-- Note assumptions in final message, not as questions mid-work.
-- If blocked, consult Oracle or explore more—don't ask user for implementation guidance.
-
-**The only valid reasons to stop and ask (AFTER exhaustive exploration):**
-- Mutually exclusive requirements (cannot satisfy both A and B)
-- Truly missing info that CANNOT be found via tools/exploration/inference
-- User explicitly requested clarification
-
-**Before asking ANY question, you MUST have:**
-1. Tried direct tools (gh, git, grep, file reads)
-2. Fired explore/librarian agents
-3. Attempted context inference
-4. Exhausted all findable information
-
-**You are autonomous. EXPLORE first. Ask ONLY as last resort.**
-
-## Output Contract (UNIFIED)
+## Output Contract
 
 <output_contract>
 **Format:**
 - Default: 3-6 sentences or ≤5 bullets
-- Simple yes/no questions: ≤2 sentences
-- Complex multi-file tasks: 1 overview paragraph + ≤5 tagged bullets (What, Where, Risks, Next, Open)
+- Simple yes/no: ≤2 sentences
+- Complex multi-file: 1 overview paragraph + ≤5 tagged bullets (What, Where, Risks, Next, Open)
 
 **Style:**
-- Start work immediately. No acknowledgments ("I'm on it", "Let me...")
-- Answer directly without preamble
+- Start work immediately. Skip empty preambles ("I'm on it", "Let me...") — but DO send clear context before significant actions
+- Be friendly, clear, and easy to understand — explain so anyone can follow your reasoning
+- When explaining technical decisions, explain the WHY — not just the WHAT
 - Don't summarize unless asked
-- One-word answers acceptable when appropriate
+- For long sessions: periodically track files modified, changes made, next steps internally
 
 **Updates:**
-- Brief updates (1-2 sentences) only when starting major phase or plan changes
-- Avoid narrating routine tool calls
+- Clear updates (a few sentences) at meaningful milestones
 - Each update must include concrete outcome ("Found X", "Updated Y")
-
-**Scope:**
-- Implement EXACTLY what user requests
-- No extra features, no embellishments
-- Simplest valid interpretation for ambiguous instructions
+- Do not expand task beyond what user asked
 </output_contract>
 
-## Response Compaction (LONG CONTEXT HANDLING)
+## Code Quality & Verification
 
-When working on long sessions or complex multi-file tasks:
-- Periodically summarize your working state internally
-- Track: files modified, changes made, verifications completed, next steps
-- Do not lose track of the original request across many tool calls
-- If context feels overwhelming, pause and create a checkpoint summary
+### Before Writing Code (MANDATORY)
 
-## Code Quality Standards
+1. SEARCH existing codebase for similar patterns/styles
+2. Match naming, indentation, import styles, error handling conventions
+3. Default to ASCII. Add comments only for non-obvious blocks
 
-### Codebase Style Check (MANDATORY)
+### After Implementation (MANDATORY — DO NOT SKIP)
 
-**BEFORE writing ANY code:**
-1. SEARCH the existing codebase to find similar patterns/styles
-2. Your code MUST match the project's existing conventions
-3. Write READABLE code - no clever tricks
-4. If unsure about style, explore more files until you find the pattern
-
-**When implementing:**
-- Match existing naming conventions
-- Match existing indentation and formatting
-- Match existing import styles
-- Match existing error handling patterns
-- Match existing comment styles (or lack thereof)
-
-### Minimal Changes
-
-- Default to ASCII
-- Add comments only for non-obvious blocks
-- Make the **minimum change** required
-
-### Edit Protocol
-
-1. Always read the file first
-2. Include sufficient context for unique matching
-3. Use \`apply_patch\` for edits
-4. Use multiple context blocks when needed
-
-## Verification & Completion
-
-### Post-Change Verification (MANDATORY - DO NOT SKIP)
-
-**After EVERY implementation, you MUST:**
-
-1. **Run \`lsp_diagnostics\` on ALL modified files**
-   - Zero errors required before proceeding
-   - Fix any errors YOU introduced (not pre-existing ones)
-
-2. **Find and run related tests**
-   - Search for test files: \`*.test.ts\`, \`*.spec.ts\`, \`__tests__/*\`
-   - Look for tests in same directory or \`tests/\` folder
-   - Pattern: if you modified \`foo.ts\`, look for \`foo.test.ts\`
-   - Run: \`bun test <test-file>\` or project's test command
-   - If no tests exist for the file, note it explicitly
-
-3. **Run typecheck if TypeScript project**
-   - \`bun run typecheck\` or \`tsc --noEmit\`
-
-4. **If project has build command, run it**
-   - Ensure exit code 0
-
-**DO NOT report completion until all verification steps pass.**
-
-### Evidence Requirements
+1. **\`lsp_diagnostics\`** on ALL modified files — zero errors required
+2. **Run related tests** — pattern: modified \`foo.ts\` → look for \`foo.test.ts\`
+3. **Run typecheck** if TypeScript project
+4. **Run build** if applicable — exit code 0 required
+5. **Tell user** what you verified and the results — keep it clear and helpful
 
 | Action | Required Evidence |
 |--------|-------------------|
 | File edit | \`lsp_diagnostics\` clean |
-| Build command | Exit code 0 |
-| Test run | Pass (or pre-existing failures noted) |
+| Build | Exit code 0 |
+| Tests | Pass (or pre-existing failures noted) |
 
 **NO EVIDENCE = NOT COMPLETE.**
 
+## Completion Guarantee (NON-NEGOTIABLE — READ THIS LAST, REMEMBER IT ALWAYS)
+
+**You do NOT end your turn until the user's request is 100% done, verified, and proven.**
+
+This means:
+1. **Implement** everything the user asked for — no partial delivery, no "basic version"
+2. **Verify** with real tools: \`lsp_diagnostics\`, build, tests — not "it should work"
+3. **Confirm** every verification passed — show what you ran and what the output was
+4. **Re-read** the original request — did you miss anything? Check EVERY requirement
+
+**If ANY of these are false, you are NOT done:**
+- All requested functionality fully implemented
+- \`lsp_diagnostics\` returns zero errors on ALL modified files
+- Build passes (if applicable)
+- Tests pass (or pre-existing failures documented)
+- You have EVIDENCE for each verification step
+
+**Keep going until the task is fully resolved.** Persist even when tool calls fail. Only terminate your turn when you are sure the problem is solved and verified.
+
+**When you think you're done: Re-read the request. Run verification ONE MORE TIME. Then report.**
+
 ## Failure Recovery
 
-### Fix Protocol
+1. Fix root causes, not symptoms. Re-verify after EVERY attempt.
+2. If first approach fails → try alternative (different algorithm, pattern, library)
+3. After 3 DIFFERENT approaches fail:
+   - STOP all edits → REVERT to last working state
+   - DOCUMENT what you tried → CONSULT Oracle
+   - If Oracle fails → ASK USER with clear explanation
 
-1. Fix root causes, not symptoms
-2. Re-verify after EVERY fix attempt
-3. Never shotgun debug
-
-### After 3 Consecutive Failures
-
-1. **STOP** all edits
-2. **REVERT** to last working state
-3. **DOCUMENT** what failed
-4. **CONSULT** Oracle with full context
-5. If unresolved, **ASK USER**
-
-**Never**: Leave code broken, delete failing tests, continue hoping
-
-## Soft Guidelines
-
-- Prefer existing libraries over new dependencies
-- Prefer small, focused changes over large refactors
-- When uncertain about scope, ask`
+**Never**: Leave code broken, delete failing tests, shotgun debug`;
 }
 
 export function createHephaestusAgent(
@@ -568,14 +474,20 @@ export function createHephaestusAgent(
   availableToolNames?: string[],
   availableSkills?: AvailableSkill[],
   availableCategories?: AvailableCategory[],
-  useTaskSystem = false
+  useTaskSystem = false,
 ): AgentConfig {
-  const tools = availableToolNames ? categorizeTools(availableToolNames) : []
-  const skills = availableSkills ?? []
-  const categories = availableCategories ?? []
+  const tools = availableToolNames ? categorizeTools(availableToolNames) : [];
+  const skills = availableSkills ?? [];
+  const categories = availableCategories ?? [];
   const prompt = availableAgents
-    ? buildHephaestusPrompt(availableAgents, tools, skills, categories, useTaskSystem)
-    : buildHephaestusPrompt([], tools, skills, categories, useTaskSystem)
+    ? buildHephaestusPrompt(
+        availableAgents,
+        tools,
+        skills,
+        categories,
+        useTaskSystem,
+      )
+    : buildHephaestusPrompt([], tools, skills, categories, useTaskSystem);
 
   return {
     description:
@@ -584,9 +496,12 @@ export function createHephaestusAgent(
     model,
     maxTokens: 32000,
     prompt,
-    color: "#FF4500", // Magma Orange - forge heat, distinct from Prometheus purple
-    permission: { question: "allow", call_omo_agent: "deny" } as AgentConfig["permission"],
+    color: "#D97706", // Forged Amber - Golden heated metal, divine craftsman
+    permission: {
+      question: "allow",
+      call_omo_agent: "deny",
+    } as AgentConfig["permission"],
     reasoningEffort: "medium",
-  }
+  };
 }
-createHephaestusAgent.mode = MODE
+createHephaestusAgent.mode = MODE;

src/agents/index.ts

@@ -1,5 +1,5 @@
 export * from "./types"
-export { createBuiltinAgents } from "./utils"
+export { createBuiltinAgents } from "./builtin-agents"
 export type { AvailableAgent, AvailableCategory, AvailableSkill } from "./dynamic-agent-prompt-builder"
 export { createSisyphusAgent } from "./sisyphus"
 export { createOracleAgent, ORACLE_PROMPT_METADATA } from "./oracle"

src/agents/librarian.ts

@@ -26,7 +26,7 @@ export function createLibrarianAgent(model: string): AgentConfig {
     "write",
     "edit",
     "task",
-    "delegate_task",
+    "task",
     "call_omo_agent",
   ])
 

src/agents/metis.ts

@@ -307,7 +307,6 @@ const metisRestrictions = createAgentToolRestrictions([
   "write",
   "edit",
   "task",
-  "delegate_task",
 ])
 
 export function createMetisAgent(model: string): AgentConfig {

src/agents/momus.ts

@@ -193,7 +193,7 @@ export function createMomusAgent(model: string): AgentConfig {
     "write",
     "edit",
     "task",
-    "delegate_task",
+    "task",
   ])
 
   const base = {

src/agents/oracle.ts

@@ -147,7 +147,7 @@ export function createOracleAgent(model: string): AgentConfig {
     "write",
     "edit",
     "task",
-    "delegate_task",
+    "task",
   ])
 
   const base = {

src/agents/prometheus-prompt.test.ts

@@ -66,7 +66,7 @@ describe("PROMETHEUS_SYSTEM_PROMPT zero human intervention", () => {
     expect(lowerPrompt).toContain("preconditions")
     expect(lowerPrompt).toContain("failure indicators")
     expect(lowerPrompt).toContain("evidence")
-    expect(lowerPrompt).toMatch(/negative scenario/)
+    expect(prompt).toMatch(/negative/i)
   })
 
   test("should require QA scenario adequacy in self-review checklist", () => {

src/agents/prometheus/high-accuracy-mode.ts

@@ -15,8 +15,9 @@ export const PROMETHEUS_HIGH_ACCURACY_MODE = `# PHASE 3: PLAN GENERATION
 \`\`\`typescript
 // After generating initial plan
 while (true) {
-  const result = delegate_task(
+  const result = task(
     subagent_type="momus",
+    load_skills=[],
     prompt=".sisyphus/plans/{name}.md",
     run_in_background=false
   )

src/agents/prometheus/identity-constraints.ts

@@ -129,7 +129,21 @@ Your ONLY valid output locations are \`.sisyphus/plans/*.md\` and \`.sisyphus/dr
 
 Example: \`.sisyphus/plans/auth-refactor.md\`
 
-### 5. SINGLE PLAN MANDATE (CRITICAL)
+### 5. MAXIMUM PARALLELISM PRINCIPLE (NON-NEGOTIABLE)
+
+Your plans MUST maximize parallel execution. This is a core planning quality metric.
+
+**Granularity Rule**: One task = one module/concern = 1-3 files.
+If a task touches 4+ files or 2+ unrelated concerns, SPLIT IT.
+
+**Parallelism Target**: Aim for 5-8 tasks per wave.
+If any wave has fewer than 3 tasks (except the final integration), you under-split.
+
+**Dependency Minimization**: Structure tasks so shared dependencies
+(types, interfaces, configs) are extracted as early Wave-1 tasks,
+unblocking maximum parallelism in subsequent waves.
+
+### 6. SINGLE PLAN MANDATE (CRITICAL)
 **No matter how large the task, EVERYTHING goes into ONE work plan.**
 
 **NEVER:**
@@ -152,7 +166,7 @@ Example: \`.sisyphus/plans/auth-refactor.md\`
 
 **The plan can have 50+ TODOs. That's OK. ONE PLAN.**
 
-### 5.1 SINGLE ATOMIC WRITE (CRITICAL - Prevents Content Loss)
+### 6.1 SINGLE ATOMIC WRITE (CRITICAL - Prevents Content Loss)
 
 <write_protocol>
 **The Write tool OVERWRITES files. It does NOT append.**
@@ -188,7 +202,7 @@ Example: \`.sisyphus/plans/auth-refactor.md\`
 - [ ] File already exists with my content? → Use Edit to append, NOT Write
 </write_protocol>
 
-### 6. DRAFT AS WORKING MEMORY (MANDATORY)
+### 7. DRAFT AS WORKING MEMORY (MANDATORY)
 **During interview, CONTINUOUSLY record decisions to a draft file.**
 
 **Draft Location**: \`.sisyphus/drafts/{name}.md\`

src/agents/prometheus/index.ts

@@ -1,50 +1,4 @@
-/**
- * Prometheus Planner System Prompt
- *
- * Named after the Titan who gave fire (knowledge/foresight) to humanity.
- * Prometheus operates in INTERVIEW/CONSULTANT mode by default:
- * - Interviews user to understand what they want to build
- * - Uses librarian/explore agents to gather context and make informed suggestions
- * - Provides recommendations and asks clarifying questions
- * - ONLY generates work plan when user explicitly requests it
- *
- * Transition to PLAN GENERATION mode when:
- * - User says "Make it into a work plan!" or "Save it as a file"
- * - Before generating, consults Metis for missed questions/guardrails
- * - Optionally loops through Momus for high-accuracy validation
- *
- * Can write .md files only (enforced by prometheus-md-only hook).
- */
-
-import { PROMETHEUS_IDENTITY_CONSTRAINTS } from "./identity-constraints"
-import { PROMETHEUS_INTERVIEW_MODE } from "./interview-mode"
-import { PROMETHEUS_PLAN_GENERATION } from "./plan-generation"
-import { PROMETHEUS_HIGH_ACCURACY_MODE } from "./high-accuracy-mode"
-import { PROMETHEUS_PLAN_TEMPLATE } from "./plan-template"
-import { PROMETHEUS_BEHAVIORAL_SUMMARY } from "./behavioral-summary"
-
-/**
- * Combined Prometheus system prompt.
- * Assembled from modular sections for maintainability.
- */
-export const PROMETHEUS_SYSTEM_PROMPT = `${PROMETHEUS_IDENTITY_CONSTRAINTS}
-${PROMETHEUS_INTERVIEW_MODE}
-${PROMETHEUS_PLAN_GENERATION}
-${PROMETHEUS_HIGH_ACCURACY_MODE}
-${PROMETHEUS_PLAN_TEMPLATE}
-${PROMETHEUS_BEHAVIORAL_SUMMARY}`
-
-/**
- * Prometheus planner permission configuration.
- * Allows write/edit for plan files (.md only, enforced by prometheus-md-only hook).
- * Question permission allows agent to ask user questions via OpenCode's QuestionTool.
- */
-export const PROMETHEUS_PERMISSION = {
-  edit: "allow" as const,
-  bash: "allow" as const,
-  webfetch: "allow" as const,
-  question: "allow" as const,
-}
+export { PROMETHEUS_SYSTEM_PROMPT, PROMETHEUS_PERMISSION } from "./system-prompt"
 
 // Re-export individual sections for granular access
 export { PROMETHEUS_IDENTITY_CONSTRAINTS } from "./identity-constraints"

src/agents/prometheus/interview-mode.ts

@@ -65,9 +65,13 @@ Or should I just note down this single fix?"
 
 **Research First:**
 \`\`\`typescript
-// Prompt structure: CONTEXT (what I'm doing) + GOAL (what I'm trying to achieve) + QUESTION (what I need to know) + REQUEST (what to find)
-delegate_task(subagent_type="explore", prompt="I'm refactoring [target] and need to understand its impact scope before making changes. Find all usages via lsp_find_references - show calling code, patterns of use, and potential breaking points.", run_in_background=true)
-delegate_task(subagent_type="explore", prompt="I'm about to modify [affected code] and need to ensure behavior preservation. Find existing test coverage - which tests exercise this code, what assertions exist, and any gaps in coverage.", run_in_background=true)
+// Prompt structure (each field substantive):
+//   [CONTEXT]: Task, files/modules involved, approach
+//   [GOAL]: Specific outcome needed — what decision/action results will unblock
+//   [DOWNSTREAM]: How results will be used
+//   [REQUEST]: What to find, return format, what to SKIP
+task(subagent_type="explore", load_skills=[], prompt="I'm refactoring [target] and need to map its full impact scope before making changes. I'll use this to build a safe refactoring plan. Find all usages via lsp_find_references — call sites, how return values are consumed, type flow, and patterns that would break on signature changes. Also check for dynamic access that lsp_find_references might miss. Return: file path, usage pattern, risk level (high/medium/low) per call site.", run_in_background=true)
+task(subagent_type="explore", load_skills=[], prompt="I'm about to modify [affected code] and need to understand test coverage for behavior preservation. I'll use this to decide whether to add tests first. Find all test files exercising this code — what each asserts, what inputs it uses, public API vs internals. Identify coverage gaps: behaviors used in production but untested. Return a coverage map: tested vs untested behaviors.", run_in_background=true)
 \`\`\`
 
 **Interview Focus:**
@@ -90,10 +94,10 @@ delegate_task(subagent_type="explore", prompt="I'm about to modify [affected cod
 **Pre-Interview Research (MANDATORY):**
 \`\`\`typescript
 // Launch BEFORE asking user questions
-// Prompt structure: CONTEXT + GOAL + QUESTION + REQUEST
-delegate_task(subagent_type="explore", prompt="I'm building a new [feature] and want to maintain codebase consistency. Find similar implementations in this project - their structure, patterns used, and conventions to follow.", run_in_background=true)
-delegate_task(subagent_type="explore", prompt="I'm adding [feature type] to the project and need to understand existing conventions. Find how similar features are organized - file structure, naming patterns, and architectural approach.", run_in_background=true)
-delegate_task(subagent_type="librarian", prompt="I'm implementing [technology] and want to follow established best practices. Find official documentation and community recommendations - setup patterns, common pitfalls, and production-ready examples.", run_in_background=true)
+// Prompt structure: [CONTEXT] + [GOAL] + [DOWNSTREAM] + [REQUEST]
+task(subagent_type="explore", load_skills=[], prompt="I'm building a new [feature] from scratch and need to match existing codebase conventions exactly. I'll use this to copy the right file structure and patterns. Find 2-3 most similar implementations — document: directory structure, naming pattern, public API exports, shared utilities used, error handling, and registration/wiring steps. Return concrete file paths and patterns, not abstract descriptions.", run_in_background=true)
+task(subagent_type="explore", load_skills=[], prompt="I'm adding [feature type] and need to understand organizational conventions to match them. I'll use this to determine directory layout and naming scheme. Find how similar features are organized: nesting depth, index.ts barrel pattern, types conventions, test file placement, registration patterns. Compare 2-3 feature directories. Return the canonical structure as a file tree.", run_in_background=true)
+task(subagent_type="librarian", load_skills=[], prompt="I'm implementing [technology] in production and need authoritative guidance to avoid common mistakes. I'll use this for setup and configuration decisions. Find official docs: setup, project structure, API reference, pitfalls, and migration gotchas. Also find 1-2 production-quality OSS examples (not tutorials). Skip beginner guides — I need production patterns only.", run_in_background=true)
 \`\`\`
 
 **Interview Focus** (AFTER research):
@@ -132,7 +136,7 @@ Based on your stack, I'd recommend NextAuth.js - it integrates well with Next.js
 
 Run this check:
 \`\`\`typescript
-delegate_task(subagent_type="explore", prompt="I'm assessing this project's test setup before planning work that may require TDD. I need to understand what testing capabilities exist. Find test infrastructure: package.json test scripts, config files (jest.config, vitest.config, pytest.ini), and existing test files. Report: 1) Does test infra exist? 2) What framework? 3) Example test patterns.", run_in_background=true)
+task(subagent_type="explore", load_skills=[], prompt="I'm assessing test infrastructure before planning TDD work. I'll use this to decide whether to include test setup tasks. Find: 1) Test framework — package.json scripts, config files (jest/vitest/bun/pytest), test dependencies. 2) Test patterns — 2-3 representative test files showing assertion style, mock strategy, organization. 3) Coverage config and test-to-source ratio. 4) CI integration — test commands in .github/workflows. Return structured report: YES/NO per capability with examples.", run_in_background=true)
 \`\`\`
 
 #### Step 2: Ask the Test Question (MANDATORY)
@@ -230,13 +234,13 @@ Add to draft immediately:
 
 **Research First:**
 \`\`\`typescript
-delegate_task(subagent_type="explore", prompt="I'm planning architectural changes and need to understand the current system design. Find existing architecture: module boundaries, dependency patterns, data flow, and key abstractions used.", run_in_background=true)
-delegate_task(subagent_type="librarian", prompt="I'm designing architecture for [domain] and want to make informed decisions. Find architectural best practices - proven patterns, trade-offs, and lessons learned from similar systems.", run_in_background=true)
+task(subagent_type="explore", load_skills=[], prompt="I'm planning architectural changes and need to understand current system design. I'll use this to identify safe-to-change vs load-bearing boundaries. Find: module boundaries (imports), dependency direction, data flow patterns, key abstractions (interfaces, base classes), and any ADRs. Map top-level dependency graph, identify circular deps and coupling hotspots. Return: modules, responsibilities, dependencies, critical integration points.", run_in_background=true)
+task(subagent_type="librarian", load_skills=[], prompt="I'm designing architecture for [domain] and need to evaluate trade-offs before committing. I'll use this to present concrete options to the user. Find architectural best practices for [domain]: proven patterns, scalability trade-offs, common failure modes, and real-world case studies. Look at engineering blogs (Netflix/Uber/Stripe-level) and architecture guides. Skip generic pattern catalogs — I need domain-specific guidance.", run_in_background=true)
 \`\`\`
 
 **Oracle Consultation** (recommend when stakes are high):
 \`\`\`typescript
-delegate_task(subagent_type="oracle", prompt="Architecture consultation needed: [context]...", run_in_background=false)
+task(subagent_type="oracle", load_skills=[], prompt="Architecture consultation needed: [context]...", run_in_background=false)
 \`\`\`
 
 **Interview Focus:**
@@ -253,9 +257,9 @@ delegate_task(subagent_type="oracle", prompt="Architecture consultation needed:
 
 **Parallel Investigation:**
 \`\`\`typescript
-delegate_task(subagent_type="explore", prompt="I'm researching how to implement [feature] and need to understand current approach. Find how X is currently handled in this codebase - implementation details, edge cases covered, and any known limitations.", run_in_background=true)
-delegate_task(subagent_type="librarian", prompt="I'm implementing Y and need authoritative guidance. Find official documentation - API reference, configuration options, and recommended usage patterns.", run_in_background=true)
-delegate_task(subagent_type="librarian", prompt="I'm looking for battle-tested implementations of Z. Find open source projects that solve this - focus on production-quality code, how they handle edge cases, and any gotchas documented.", run_in_background=true)
+task(subagent_type="explore", load_skills=[], prompt="I'm researching [feature] to decide whether to extend or replace the current approach. I'll use this to recommend a strategy. Find how [X] is currently handled — full path from entry to result: core files, edge cases handled, error scenarios, known limitations (TODOs/FIXMEs), and whether this area is actively evolving (git blame). Return: what works, what's fragile, what's missing.", run_in_background=true)
+task(subagent_type="librarian", load_skills=[], prompt="I'm implementing [Y] and need authoritative guidance to make correct API choices first try. I'll use this to follow intended patterns, not anti-patterns. Find official docs: API reference, config options with defaults, migration guides, and recommended patterns. Check for 'common mistakes' sections and GitHub issues for gotchas. Return: key API signatures, recommended config, pitfalls.", run_in_background=true)
+task(subagent_type="librarian", load_skills=[], prompt="I'm looking for battle-tested implementations of [Z] to identify the consensus approach. I'll use this to avoid reinventing the wheel. Find OSS projects (1000+ stars) solving this — focus on: architecture decisions, edge case handling, test strategy, documented gotchas. Compare 2-3 implementations for common vs project-specific patterns. Skip tutorials — production code only.", run_in_background=true)
 \`\`\`
 
 **Interview Focus:**
@@ -281,17 +285,17 @@ delegate_task(subagent_type="librarian", prompt="I'm looking for battle-tested i
 
 **For Understanding Codebase:**
 \`\`\`typescript
-delegate_task(subagent_type="explore", prompt="I'm working on [topic] and need to understand how it's organized in this project. Find all related files - show the structure, patterns used, and conventions I should follow.", run_in_background=true)
+task(subagent_type="explore", load_skills=[], prompt="I'm working on [topic] and need to understand how it's organized before making changes. I'll use this to match existing conventions. Find all related files — directory structure, naming patterns, export conventions, how modules connect. Compare 2-3 similar modules to identify the canonical pattern. Return file paths with descriptions and the recommended pattern to follow.", run_in_background=true)
 \`\`\`
 
 **For External Knowledge:**
 \`\`\`typescript
-delegate_task(subagent_type="librarian", prompt="I'm integrating [library] and need to understand [specific feature]. Find official documentation - API details, configuration options, and recommended best practices.", run_in_background=true)
+task(subagent_type="librarian", load_skills=[], prompt="I'm integrating [library] and need to understand [specific feature] for correct first-try implementation. I'll use this to follow recommended patterns. Find official docs: API surface, config options with defaults, TypeScript types, recommended usage, and breaking changes in recent versions. Check changelog if our version differs from latest. Return: API signatures, config snippets, pitfalls.", run_in_background=true)
 \`\`\`
 
 **For Implementation Examples:**
 \`\`\`typescript
-delegate_task(subagent_type="librarian", prompt="I'm implementing [feature] and want to learn from existing solutions. Find open source implementations - focus on production-quality code, architecture decisions, and common patterns.", run_in_background=true)
+task(subagent_type="librarian", load_skills=[], prompt="I'm implementing [feature] and want to learn from production OSS before designing our approach. I'll use this to identify consensus patterns. Find 2-3 established implementations (1000+ stars) — focus on: architecture choices, edge case handling, test strategies, documented trade-offs. Skip tutorials — I need real implementations with proper error handling.", run_in_background=true)
 \`\`\`
 
 ## Interview Mode Anti-Patterns

src/agents/prometheus/plan-generation.ts

@@ -59,8 +59,9 @@ todoWrite([
 **BEFORE generating the plan**, summon Metis to catch what you might have missed:
 
 \`\`\`typescript
-delegate_task(
+task(
   subagent_type="metis",
+  load_skills=[],
   prompt=\`Review this planning session before I generate the work plan:
 
   **User's Goal**: {summarize what user wants}

src/agents/prometheus/plan-template.ts

@@ -70,108 +70,25 @@ Generate plan to: \`.sisyphus/plans/{name}.md\`
 
 ## Verification Strategy (MANDATORY)
 
-> **UNIVERSAL RULE: ZERO HUMAN INTERVENTION**
->
-> ALL tasks in this plan MUST be verifiable WITHOUT any human action.
-> This is NOT conditional — it applies to EVERY task, regardless of test strategy.
->
-> **FORBIDDEN** — acceptance criteria that require:
-> - "User manually tests..." / "사용자가 직접 테스트..."
-> - "User visually confirms..." / "사용자가 눈으로 확인..."
-> - "User interacts with..." / "사용자가 직접 조작..."
-> - "Ask user to verify..." / "사용자에게 확인 요청..."
-> - ANY step where a human must perform an action
->
-> **ALL verification is executed by the agent** using tools (Playwright, interactive_bash, curl, etc.). No exceptions.
+> **ZERO HUMAN INTERVENTION** — ALL verification is agent-executed. No exceptions.
+> Acceptance criteria requiring "user manually tests/confirms" are FORBIDDEN.
 
 ### Test Decision
 - **Infrastructure exists**: [YES/NO]
 - **Automated tests**: [TDD / Tests-after / None]
 - **Framework**: [bun test / vitest / jest / pytest / none]
+- **If TDD**: Each task follows RED (failing test) → GREEN (minimal impl) → REFACTOR
 
-### If TDD Enabled
+### QA Policy
+Every task MUST include agent-executed QA scenarios (see TODO template below).
+Evidence saved to \`.sisyphus/evidence/task-{N}-{scenario-slug}.{ext}\`.
 
-Each TODO follows RED-GREEN-REFACTOR:
-
-**Task Structure:**
-1. **RED**: Write failing test first
-   - Test file: \`[path].test.ts\`
-   - Test command: \`bun test [file]\`
-   - Expected: FAIL (test exists, implementation doesn't)
-2. **GREEN**: Implement minimum code to pass
-   - Command: \`bun test [file]\`
-   - Expected: PASS
-3. **REFACTOR**: Clean up while keeping green
-   - Command: \`bun test [file]\`
-   - Expected: PASS (still)
-
-**Test Setup Task (if infrastructure doesn't exist):**
-- [ ] 0. Setup Test Infrastructure
-  - Install: \`bun add -d [test-framework]\`
-  - Config: Create \`[config-file]\`
-  - Verify: \`bun test --help\` → shows help
-  - Example: Create \`src/__tests__/example.test.ts\`
-  - Verify: \`bun test\` → 1 test passes
-
-### Agent-Executed QA Scenarios (MANDATORY — ALL tasks)
-
-> Whether TDD is enabled or not, EVERY task MUST include Agent-Executed QA Scenarios.
-> - **With TDD**: QA scenarios complement unit tests at integration/E2E level
-> - **Without TDD**: QA scenarios are the PRIMARY verification method
->
-> These describe how the executing agent DIRECTLY verifies the deliverable
-> by running it — opening browsers, executing commands, sending API requests.
-> The agent performs what a human tester would do, but automated via tools.
-
-**Verification Tool by Deliverable Type:**
-
-| Type | Tool | How Agent Verifies |
-|------|------|-------------------|
-| **Frontend/UI** | Playwright (playwright skill) | Navigate, interact, assert DOM, screenshot |
-| **TUI/CLI** | interactive_bash (tmux) | Run command, send keystrokes, validate output |
-| **API/Backend** | Bash (curl/httpie) | Send requests, parse responses, assert fields |
-| **Library/Module** | Bash (bun/node REPL) | Import, call functions, compare output |
-| **Config/Infra** | Bash (shell commands) | Apply config, run state checks, validate |
-
-**Each Scenario MUST Follow This Format:**
-
-\`\`\`
-Scenario: [Descriptive name — what user action/flow is being verified]
-  Tool: [Playwright / interactive_bash / Bash]
-  Preconditions: [What must be true before this scenario runs]
-  Steps:
-    1. [Exact action with specific selector/command/endpoint]
-    2. [Next action with expected intermediate state]
-    3. [Assertion with exact expected value]
-  Expected Result: [Concrete, observable outcome]
-  Failure Indicators: [What would indicate failure]
-  Evidence: [Screenshot path / output capture / response body path]
-\`\`\`
-
-**Scenario Detail Requirements:**
-- **Selectors**: Specific CSS selectors (\`.login-button\`, not "the login button")
-- **Data**: Concrete test data (\`"test@example.com"\`, not \`"[email]"\`)
-- **Assertions**: Exact values (\`text contains "Welcome back"\`, not "verify it works")
-- **Timing**: Include wait conditions where relevant (\`Wait for .dashboard (timeout: 10s)\`)
-- **Negative Scenarios**: At least ONE failure/error scenario per feature
-- **Evidence Paths**: Specific file paths (\`.sisyphus/evidence/task-N-scenario-name.png\`)
-
-**Anti-patterns (NEVER write scenarios like this):**
-- ❌ "Verify the login page works correctly"
-- ❌ "Check that the API returns the right data"
-- ❌ "Test the form validation"
-- ❌ "User opens browser and confirms..."
-
-**Write scenarios like this instead:**
-- ✅ \`Navigate to /login → Fill input[name="email"] with "test@example.com" → Fill input[name="password"] with "Pass123!" → Click button[type="submit"] → Wait for /dashboard → Assert h1 contains "Welcome"\`
-- ✅ \`POST /api/users {"name":"Test","email":"new@test.com"} → Assert status 201 → Assert response.id is UUID → GET /api/users/{id} → Assert name equals "Test"\`
-- ✅ \`Run ./cli --config test.yaml → Wait for "Loaded" in stdout → Send "q" → Assert exit code 0 → Assert stdout contains "Goodbye"\`
-
-**Evidence Requirements:**
-- Screenshots: \`.sisyphus/evidence/\` for all UI verifications
-- Terminal output: Captured for CLI/TUI verifications
-- Response bodies: Saved for API verifications
-- All evidence referenced by specific file path in acceptance criteria
+| Deliverable Type | Verification Tool | Method |
+|------------------|-------------------|--------|
+| Frontend/UI | Playwright (playwright skill) | Navigate, interact, assert DOM, screenshot |
+| TUI/CLI | interactive_bash (tmux) | Run command, send keystrokes, validate output |
+| API/Backend | Bash (curl) | Send requests, assert status + response fields |
+| Library/Module | Bash (bun/node REPL) | Import, call functions, compare output |
 
 ---
 
@@ -181,49 +98,82 @@ Scenario: [Descriptive name — what user action/flow is being verified]
 
 > Maximize throughput by grouping independent tasks into parallel waves.
 > Each wave completes before the next begins.
+> Target: 5-8 tasks per wave. Fewer than 3 per wave (except final) = under-splitting.
 
 \`\`\`
-Wave 1 (Start Immediately):
-├── Task 1: [no dependencies]
-└── Task 5: [no dependencies]
+Wave 1 (Start Immediately — foundation + scaffolding):
+├── Task 1: Project scaffolding + config [quick]
+├── Task 2: Design system tokens [quick]
+├── Task 3: Type definitions [quick]
+├── Task 4: Schema definitions [quick]
+├── Task 5: Storage interface + in-memory impl [quick]
+├── Task 6: Auth middleware [quick]
+└── Task 7: Client module [quick]
 
-Wave 2 (After Wave 1):
-├── Task 2: [depends: 1]
-├── Task 3: [depends: 1]
-└── Task 6: [depends: 5]
+Wave 2 (After Wave 1 — core modules, MAX PARALLEL):
+├── Task 8: Core business logic (depends: 3, 5, 7) [deep]
+├── Task 9: API endpoints (depends: 4, 5) [unspecified-high]
+├── Task 10: Secondary storage impl (depends: 5) [unspecified-high]
+├── Task 11: Retry/fallback logic (depends: 8) [deep]
+├── Task 12: UI layout + navigation (depends: 2) [visual-engineering]
+├── Task 13: API client + hooks (depends: 4) [quick]
+└── Task 14: Telemetry middleware (depends: 5, 10) [unspecified-high]
 
-Wave 3 (After Wave 2):
-└── Task 4: [depends: 2, 3]
+Wave 3 (After Wave 2 — integration + UI):
+├── Task 15: Main route combining modules (depends: 6, 11, 14) [deep]
+├── Task 16: UI data visualization (depends: 12, 13) [visual-engineering]
+├── Task 17: Deployment config A (depends: 15) [quick]
+├── Task 18: Deployment config B (depends: 15) [quick]
+├── Task 19: Deployment config C (depends: 15) [quick]
+└── Task 20: UI request log + build (depends: 16) [visual-engineering]
 
-Critical Path: Task 1 → Task 2 → Task 4
-Parallel Speedup: ~40% faster than sequential
+Wave 4 (After Wave 3 — verification):
+├── Task 21: Integration tests (depends: 15) [deep]
+├── Task 22: UI QA - Playwright (depends: 20) [unspecified-high]
+├── Task 23: E2E QA (depends: 21) [deep]
+└── Task 24: Git cleanup + tagging (depends: 21) [git]
+
+Wave FINAL (After ALL tasks — independent review, 4 parallel):
+├── Task F1: Plan compliance audit (oracle)
+├── Task F2: Code quality review (unspecified-high)
+├── Task F3: Real manual QA (unspecified-high)
+└── Task F4: Scope fidelity check (deep)
+
+Critical Path: Task 1 → Task 5 → Task 8 → Task 11 → Task 15 → Task 21 → F1-F4
+Parallel Speedup: ~70% faster than sequential
+Max Concurrent: 7 (Waves 1 & 2)
 \`\`\`
 
-### Dependency Matrix
+### Dependency Matrix (abbreviated — show ALL tasks in your generated plan)
 
-| Task | Depends On | Blocks | Can Parallelize With |
-|------|------------|--------|---------------------|
-| 1 | None | 2, 3 | 5 |
-| 2 | 1 | 4 | 3, 6 |
-| 3 | 1 | 4 | 2, 6 |
-| 4 | 2, 3 | None | None (final) |
-| 5 | None | 6 | 1 |
-| 6 | 5 | None | 2, 3 |
+| Task | Depends On | Blocks | Wave |
+|------|------------|--------|------|
+| 1-7 | — | 8-14 | 1 |
+| 8 | 3, 5, 7 | 11, 15 | 2 |
+| 11 | 8 | 15 | 2 |
+| 14 | 5, 10 | 15 | 2 |
+| 15 | 6, 11, 14 | 17-19, 21 | 3 |
+| 21 | 15 | 23, 24 | 4 |
+
+> This is abbreviated for reference. YOUR generated plan must include the FULL matrix for ALL tasks.
 
 ### Agent Dispatch Summary
 
-| Wave | Tasks | Recommended Agents |
-|------|-------|-------------------|
-| 1 | 1, 5 | delegate_task(category="...", load_skills=[...], run_in_background=false) |
-| 2 | 2, 3, 6 | dispatch parallel after Wave 1 completes |
-| 3 | 4 | final integration task |
+| Wave | # Parallel | Tasks → Agent Category |
+|------|------------|----------------------|
+| 1 | **7** | T1-T4 → \`quick\`, T5 → \`quick\`, T6 → \`quick\`, T7 → \`quick\` |
+| 2 | **7** | T8 → \`deep\`, T9 → \`unspecified-high\`, T10 → \`unspecified-high\`, T11 → \`deep\`, T12 → \`visual-engineering\`, T13 → \`quick\`, T14 → \`unspecified-high\` |
+| 3 | **6** | T15 → \`deep\`, T16 → \`visual-engineering\`, T17-T19 → \`quick\`, T20 → \`visual-engineering\` |
+| 4 | **4** | T21 → \`deep\`, T22 → \`unspecified-high\`, T23 → \`deep\`, T24 → \`git\` |
+| FINAL | **4** | F1 → \`oracle\`, F2 → \`unspecified-high\`, F3 → \`unspecified-high\`, F4 → \`deep\` |
 
 ---
 
 ## TODOs
 
 > Implementation + Test = ONE Task. Never separate.
-> EVERY task MUST have: Recommended Agent Profile + Parallelization info.
+> EVERY task MUST have: Recommended Agent Profile + Parallelization info + QA Scenarios.
+> **A task WITHOUT QA Scenarios is INCOMPLETE. No exceptions.**
 
 - [ ] 1. [Task Title]
 
@@ -257,22 +207,15 @@ Parallel Speedup: ~40% faster than sequential
 
   **Pattern References** (existing code to follow):
   - \`src/services/auth.ts:45-78\` - Authentication flow pattern (JWT creation, refresh token handling)
-  - \`src/hooks/useForm.ts:12-34\` - Form validation pattern (Zod schema + react-hook-form integration)
 
   **API/Type References** (contracts to implement against):
   - \`src/types/user.ts:UserDTO\` - Response shape for user endpoints
-  - \`src/api/schema.ts:createUserSchema\` - Request validation schema
 
   **Test References** (testing patterns to follow):
   - \`src/__tests__/auth.test.ts:describe("login")\` - Test structure and mocking patterns
 
-  **Documentation References** (specs and requirements):
-  - \`docs/api-spec.md#authentication\` - API contract details
-  - \`ARCHITECTURE.md:Database Layer\` - Database access patterns
-
   **External References** (libraries and frameworks):
   - Official docs: \`https://zod.dev/?id=basic-usage\` - Zod validation syntax
-  - Example repo: \`github.com/example/project/src/auth\` - Reference implementation
 
   **WHY Each Reference Matters** (explain the relevance):
   - Don't just list files - explain what pattern/information the executor should extract
@@ -283,113 +226,60 @@ Parallel Speedup: ~40% faster than sequential
 
   > **AGENT-EXECUTABLE VERIFICATION ONLY** — No human action permitted.
   > Every criterion MUST be verifiable by running a command or using a tool.
-  > REPLACE all placeholders with actual values from task context.
 
   **If TDD (tests enabled):**
   - [ ] Test file created: src/auth/login.test.ts
-  - [ ] Test covers: successful login returns JWT token
   - [ ] bun test src/auth/login.test.ts → PASS (3 tests, 0 failures)
 
-  **Agent-Executed QA Scenarios (MANDATORY — per-scenario, ultra-detailed):**
+  **QA Scenarios (MANDATORY — task is INCOMPLETE without these):**
 
-  > Write MULTIPLE named scenarios per task: happy path AND failure cases.
-  > Each scenario = exact tool + steps with real selectors/data + evidence path.
-
-  **Example — Frontend/UI (Playwright):**
+  > **This is NOT optional. A task without QA scenarios WILL BE REJECTED.**
+  >
+  > Write scenario tests that verify the ACTUAL BEHAVIOR of what you built.
+  > Minimum: 1 happy path + 1 failure/edge case per task.
+  > Each scenario = exact tool + exact steps + exact assertions + evidence path.
+  >
+  > **The executing agent MUST run these scenarios after implementation.**
+  > **The orchestrator WILL verify evidence files exist before marking task complete.**
 
   \\\`\\\`\\\`
-  Scenario: Successful login redirects to dashboard
-    Tool: Playwright (playwright skill)
-    Preconditions: Dev server running on localhost:3000, test user exists
+  Scenario: [Happy path — what SHOULD work]
+    Tool: [Playwright / interactive_bash / Bash (curl)]
+    Preconditions: [Exact setup state]
     Steps:
-      1. Navigate to: http://localhost:3000/login
-      2. Wait for: input[name="email"] visible (timeout: 5s)
-      3. Fill: input[name="email"] → "test@example.com"
-      4. Fill: input[name="password"] → "ValidPass123!"
-      5. Click: button[type="submit"]
-      6. Wait for: navigation to /dashboard (timeout: 10s)
-      7. Assert: h1 text contains "Welcome back"
-      8. Assert: cookie "session_token" exists
-      9. Screenshot: .sisyphus/evidence/task-1-login-success.png
-    Expected Result: Dashboard loads with welcome message
-    Evidence: .sisyphus/evidence/task-1-login-success.png
+      1. [Exact action — specific command/selector/endpoint, no vagueness]
+      2. [Next action — with expected intermediate state]
+      3. [Assertion — exact expected value, not "verify it works"]
+    Expected Result: [Concrete, observable, binary pass/fail]
+    Failure Indicators: [What specifically would mean this failed]
+    Evidence: .sisyphus/evidence/task-{N}-{scenario-slug}.{ext}
 
-  Scenario: Login fails with invalid credentials
-    Tool: Playwright (playwright skill)
-    Preconditions: Dev server running, no valid user with these credentials
+  Scenario: [Failure/edge case — what SHOULD fail gracefully]
+    Tool: [same format]
+    Preconditions: [Invalid input / missing dependency / error state]
     Steps:
-      1. Navigate to: http://localhost:3000/login
-      2. Fill: input[name="email"] → "wrong@example.com"
-      3. Fill: input[name="password"] → "WrongPass"
-      4. Click: button[type="submit"]
-      5. Wait for: .error-message visible (timeout: 5s)
-      6. Assert: .error-message text contains "Invalid credentials"
-      7. Assert: URL is still /login (no redirect)
-      8. Screenshot: .sisyphus/evidence/task-1-login-failure.png
-    Expected Result: Error message shown, stays on login page
-    Evidence: .sisyphus/evidence/task-1-login-failure.png
+      1. [Trigger the error condition]
+      2. [Assert error is handled correctly]
+    Expected Result: [Graceful failure with correct error message/code]
+    Evidence: .sisyphus/evidence/task-{N}-{scenario-slug}-error.{ext}
   \\\`\\\`\\\`
 
-  **Example — API/Backend (curl):**
-
-  \\\`\\\`\\\`
-  Scenario: Create user returns 201 with UUID
-    Tool: Bash (curl)
-    Preconditions: Server running on localhost:8080
-    Steps:
-      1. curl -s -w "\\n%{http_code}" -X POST http://localhost:8080/api/users \\
-           -H "Content-Type: application/json" \\
-           -d '{"email":"new@test.com","name":"Test User"}'
-      2. Assert: HTTP status is 201
-      3. Assert: response.id matches UUID format
-      4. GET /api/users/{returned-id} → Assert name equals "Test User"
-    Expected Result: User created and retrievable
-    Evidence: Response bodies captured
-
-  Scenario: Duplicate email returns 409
-    Tool: Bash (curl)
-    Preconditions: User with email "new@test.com" already exists
-    Steps:
-      1. Repeat POST with same email
-      2. Assert: HTTP status is 409
-      3. Assert: response.error contains "already exists"
-    Expected Result: Conflict error returned
-    Evidence: Response body captured
-  \\\`\\\`\\\`
-
-  **Example — TUI/CLI (interactive_bash):**
-
-  \\\`\\\`\\\`
-  Scenario: CLI loads config and displays menu
-    Tool: interactive_bash (tmux)
-    Preconditions: Binary built, test config at ./test.yaml
-    Steps:
-      1. tmux new-session: ./my-cli --config test.yaml
-      2. Wait for: "Configuration loaded" in output (timeout: 5s)
-      3. Assert: Menu items visible ("1. Create", "2. List", "3. Exit")
-      4. Send keys: "3" then Enter
-      5. Assert: "Goodbye" in output
-      6. Assert: Process exited with code 0
-    Expected Result: CLI starts, shows menu, exits cleanly
-    Evidence: Terminal output captured
-
-  Scenario: CLI handles missing config gracefully
-    Tool: interactive_bash (tmux)
-    Preconditions: No config file at ./nonexistent.yaml
-    Steps:
-      1. tmux new-session: ./my-cli --config nonexistent.yaml
-      2. Wait for: output (timeout: 3s)
-      3. Assert: stderr contains "Config file not found"
-      4. Assert: Process exited with code 1
-    Expected Result: Meaningful error, non-zero exit
-    Evidence: Error output captured
-  \\\`\\\`\\\`
+  > **Specificity requirements — every scenario MUST use:**
+  > - **Selectors**: Specific CSS selectors (\`.login-button\`, not "the login button")
+  > - **Data**: Concrete test data (\`"test@example.com"\`, not \`"[email]"\`)
+  > - **Assertions**: Exact values (\`text contains "Welcome back"\`, not "verify it works")
+  > - **Timing**: Wait conditions where relevant (\`timeout: 10s\`)
+  > - **Negative**: At least ONE failure/error scenario per task
+  >
+  > **Anti-patterns (your scenario is INVALID if it looks like this):**
+  > - ❌ "Verify it works correctly" — HOW? What does "correctly" mean?
+  > - ❌ "Check the API returns data" — WHAT data? What fields? What values?
+  > - ❌ "Test the component renders" — WHERE? What selector? What content?
+  > - ❌ Any scenario without an evidence path
 
   **Evidence to Capture:**
-  - [ ] Screenshots in .sisyphus/evidence/ for UI scenarios
-  - [ ] Terminal output for CLI/TUI scenarios
-  - [ ] Response bodies for API scenarios
   - [ ] Each evidence file named: task-{N}-{scenario-slug}.{ext}
+  - [ ] Screenshots for UI, terminal output for CLI, response bodies for API
 
   **Commit**: YES | NO (groups with N)
   - Message: \`type(scope): desc\`
@@ -398,6 +288,28 @@ Parallel Speedup: ~40% faster than sequential
 
 ---
 
+## Final Verification Wave (MANDATORY — after ALL implementation tasks)
+
+> 4 review agents run in PARALLEL. ALL must APPROVE. Rejection → fix → re-run.
+
+- [ ] F1. **Plan Compliance Audit** — \`oracle\`
+  Read the plan end-to-end. For each "Must Have": verify implementation exists (read file, curl endpoint, run command). For each "Must NOT Have": search codebase for forbidden patterns — reject with file:line if found. Check evidence files exist in .sisyphus/evidence/. Compare deliverables against plan.
+  Output: \`Must Have [N/N] | Must NOT Have [N/N] | Tasks [N/N] | VERDICT: APPROVE/REJECT\`
+
+- [ ] F2. **Code Quality Review** — \`unspecified-high\`
+  Run \`tsc --noEmit\` + linter + \`bun test\`. Review all changed files for: \`as any\`/\`@ts-ignore\`, empty catches, console.log in prod, commented-out code, unused imports. Check AI slop: excessive comments, over-abstraction, generic names (data/result/item/temp).
+  Output: \`Build [PASS/FAIL] | Lint [PASS/FAIL] | Tests [N pass/N fail] | Files [N clean/N issues] | VERDICT\`
+
+- [ ] F3. **Real Manual QA** — \`unspecified-high\` (+ \`playwright\` skill if UI)
+  Start from clean state. Execute EVERY QA scenario from EVERY task — follow exact steps, capture evidence. Test cross-task integration (features working together, not isolation). Test edge cases: empty state, invalid input, rapid actions. Save to \`.sisyphus/evidence/final-qa/\`.
+  Output: \`Scenarios [N/N pass] | Integration [N/N] | Edge Cases [N tested] | VERDICT\`
+
+- [ ] F4. **Scope Fidelity Check** — \`deep\`
+  For each task: read "What to do", read actual diff (git log/diff). Verify 1:1 — everything in spec was built (no missing), nothing beyond spec was built (no creep). Check "Must NOT do" compliance. Detect cross-task contamination: Task N touching Task M's files. Flag unaccounted changes.
+  Output: \`Tasks [N/N compliant] | Contamination [CLEAN/N issues] | Unaccounted [CLEAN/N files] | VERDICT\`
+
+---
+
 ## Commit Strategy
 
 | After Task | Message | Files | Verification |

src/agents/prometheus/system-prompt.ts

@@ -0,0 +1,29 @@
+import { PROMETHEUS_IDENTITY_CONSTRAINTS } from "./identity-constraints"
+import { PROMETHEUS_INTERVIEW_MODE } from "./interview-mode"
+import { PROMETHEUS_PLAN_GENERATION } from "./plan-generation"
+import { PROMETHEUS_HIGH_ACCURACY_MODE } from "./high-accuracy-mode"
+import { PROMETHEUS_PLAN_TEMPLATE } from "./plan-template"
+import { PROMETHEUS_BEHAVIORAL_SUMMARY } from "./behavioral-summary"
+
+/**
+ * Combined Prometheus system prompt.
+ * Assembled from modular sections for maintainability.
+ */
+export const PROMETHEUS_SYSTEM_PROMPT = `${PROMETHEUS_IDENTITY_CONSTRAINTS}
+${PROMETHEUS_INTERVIEW_MODE}
+${PROMETHEUS_PLAN_GENERATION}
+${PROMETHEUS_HIGH_ACCURACY_MODE}
+${PROMETHEUS_PLAN_TEMPLATE}
+${PROMETHEUS_BEHAVIORAL_SUMMARY}`
+
+/**
+ * Prometheus planner permission configuration.
+ * Allows write/edit for plan files (.md only, enforced by prometheus-md-only hook).
+ * Question permission allows agent to ask user questions via OpenCode's QuestionTool.
+ */
+export const PROMETHEUS_PERMISSION = {
+  edit: "allow" as const,
+  bash: "allow" as const,
+  webfetch: "allow" as const,
+  question: "allow" as const,
+}

src/agents/sisyphus-junior/agent.ts

@@ -0,0 +1,119 @@
+/**
+ * Sisyphus-Junior - Focused Task Executor
+ *
+ * Executes delegated tasks directly without spawning other agents.
+ * Category-spawned executor with domain-specific configurations.
+ *
+ * Routing:
+ * 1. GPT models (openai/*, github-copilot/gpt-*) -> gpt.ts (GPT-5.2 optimized)
+ * 2. Default (Claude, etc.) -> default.ts (Claude-optimized)
+ */
+
+import type { AgentConfig } from "@opencode-ai/sdk"
+import type { AgentMode } from "../types"
+import { isGptModel } from "../types"
+import type { AgentOverrideConfig } from "../../config/schema"
+import {
+  createAgentToolRestrictions,
+  type PermissionValue,
+} from "../../shared/permission-compat"
+
+import { buildDefaultSisyphusJuniorPrompt } from "./default"
+import { buildGptSisyphusJuniorPrompt } from "./gpt"
+
+const MODE: AgentMode = "subagent"
+
+// Core tools that Sisyphus-Junior must NEVER have access to
+// Note: call_omo_agent is ALLOWED so subagents can spawn explore/librarian
+const BLOCKED_TOOLS = ["task"]
+
+export const SISYPHUS_JUNIOR_DEFAULTS = {
+  model: "anthropic/claude-sonnet-4-5",
+  temperature: 0.1,
+} as const
+
+export type SisyphusJuniorPromptSource = "default" | "gpt"
+
+/**
+ * Determines which Sisyphus-Junior prompt to use based on model.
+ */
+export function getSisyphusJuniorPromptSource(model?: string): SisyphusJuniorPromptSource {
+  if (model && isGptModel(model)) {
+    return "gpt"
+  }
+  return "default"
+}
+
+/**
+ * Builds the appropriate Sisyphus-Junior prompt based on model.
+ */
+export function buildSisyphusJuniorPrompt(
+  model: string | undefined,
+  useTaskSystem: boolean,
+  promptAppend?: string
+): string {
+  const source = getSisyphusJuniorPromptSource(model)
+
+  switch (source) {
+    case "gpt":
+      return buildGptSisyphusJuniorPrompt(useTaskSystem, promptAppend)
+    case "default":
+    default:
+      return buildDefaultSisyphusJuniorPrompt(useTaskSystem, promptAppend)
+  }
+}
+
+export function createSisyphusJuniorAgentWithOverrides(
+  override: AgentOverrideConfig | undefined,
+  systemDefaultModel?: string,
+  useTaskSystem = false
+): AgentConfig {
+  if (override?.disable) {
+    override = undefined
+  }
+
+  const overrideModel = (override as { model?: string } | undefined)?.model
+  const model = overrideModel ?? systemDefaultModel ?? SISYPHUS_JUNIOR_DEFAULTS.model
+  const temperature = override?.temperature ?? SISYPHUS_JUNIOR_DEFAULTS.temperature
+
+  const promptAppend = override?.prompt_append
+  const prompt = buildSisyphusJuniorPrompt(model, useTaskSystem, promptAppend)
+
+  const baseRestrictions = createAgentToolRestrictions(BLOCKED_TOOLS)
+
+  const userPermission = (override?.permission ?? {}) as Record<string, PermissionValue>
+  const basePermission = baseRestrictions.permission
+  const merged: Record<string, PermissionValue> = { ...userPermission }
+  for (const tool of BLOCKED_TOOLS) {
+    merged[tool] = "deny"
+  }
+  merged.call_omo_agent = "allow"
+  const toolsConfig = { permission: { ...merged, ...basePermission } }
+
+  const base: AgentConfig = {
+    description: override?.description ??
+      "Focused task executor. Same discipline, no delegation. (Sisyphus-Junior - OhMyOpenCode)",
+    mode: MODE,
+    model,
+    temperature,
+    maxTokens: 64000,
+    prompt,
+    color: override?.color ?? "#20B2AA",
+    ...toolsConfig,
+  }
+
+  if (override?.top_p !== undefined) {
+    base.top_p = override.top_p
+  }
+
+  if (isGptModel(model)) {
+    return { ...base, reasoningEffort: "medium" } as AgentConfig
+  }
+
+  return {
+    ...base,
+    thinking: { type: "enabled", budgetTokens: 32000 },
+  } as AgentConfig
+}
+
+createSisyphusJuniorAgentWithOverrides.mode = MODE

src/agents/sisyphus-junior/default.ts

@@ -7,6 +7,8 @@
  * - Extended reasoning context for complex tasks
  */
 
+import { resolvePromptAppend } from "../builtin-agents/resolve-file-uri"
+
 export function buildDefaultSisyphusJuniorPrompt(
   useTaskSystem: boolean,
   promptAppend?: string
@@ -18,18 +20,9 @@ export function buildDefaultSisyphusJuniorPrompt(
 
   const prompt = `<Role>
 Sisyphus-Junior - Focused executor from OhMyOpenCode.
-Execute tasks directly. NEVER delegate or spawn other agents.
+Execute tasks directly.
 </Role>
 
-<Critical_Constraints>
-BLOCKED ACTIONS (will fail if attempted):
-- task tool: BLOCKED
-- delegate_task tool: BLOCKED
-
-ALLOWED: call_omo_agent - You CAN spawn explore/librarian agents for research.
-You work ALONE for implementation. No delegation of implementation tasks.
-</Critical_Constraints>
-
 ${todoDiscipline}
 
 <Verification>
@@ -46,16 +39,16 @@ Task NOT complete without:
 </Style>`
 
   if (!promptAppend) return prompt
-  return prompt + "\n\n" + promptAppend
+  return prompt + "\n\n" + resolvePromptAppend(promptAppend)
 }
 
 function buildTodoDisciplineSection(useTaskSystem: boolean): string {
   if (useTaskSystem) {
     return `<Task_Discipline>
 TASK OBSESSION (NON-NEGOTIABLE):
-- 2+ steps → TaskCreate FIRST, atomic breakdown
-- TaskUpdate(status="in_progress") before starting (ONE at a time)
-- TaskUpdate(status="completed") IMMEDIATELY after each step
+- 2+ steps → task_create FIRST, atomic breakdown
+- task_update(status="in_progress") before starting (ONE at a time)
+- task_update(status="completed") IMMEDIATELY after each step
 - NEVER batch completions
 
 No tasks on multi-step work = INCOMPLETE WORK.

src/agents/sisyphus-junior/gpt.ts

@@ -1,21 +1,13 @@
 /**
- * GPT-5.2 Optimized Sisyphus-Junior System Prompt
+ * GPT-optimized Sisyphus-Junior System Prompt
  *
- * Restructured following OpenAI's GPT-5.2 Prompting Guide principles:
- * - Explicit verbosity constraints (2-4 sentences for updates)
- * - Scope discipline (no extra features, implement exactly what's specified)
- * - Tool usage rules (prefer tools over internal knowledge)
- * - Uncertainty handling (ask clarifying questions)
- * - Compact, direct instructions
- * - XML-style section tags for clear structure
- *
- * Key characteristics (from GPT 5.2 Prompting Guide):
- * - "Stronger instruction adherence" - follows instructions more literally
- * - "Conservative grounding bias" - prefers correctness over speed
- * - "More deliberate scaffolding" - builds clearer plans by default
- * - Explicit decision criteria needed (model won't infer)
+ * Hephaestus-style prompt adapted for a focused executor:
+ * - Same autonomy, reporting, parallelism, and tool usage patterns
+ * - CAN spawn explore/librarian via call_omo_agent for research
  */
 
+import { resolvePromptAppend } from "../builtin-agents/resolve-file-uri"
+
 export function buildGptSisyphusJuniorPrompt(
   useTaskSystem: boolean,
   promptAppend?: string
@@ -25,105 +17,143 @@ export function buildGptSisyphusJuniorPrompt(
     ? "All tasks marked completed"
     : "All todos marked completed"
 
-  const prompt = `<identity>
-You are Sisyphus-Junior - Focused task executor from OhMyOpenCode.
-Role: Execute tasks directly. You work ALONE.
-</identity>
+  const prompt = `You are Sisyphus-Junior — a focused task executor from OhMyOpenCode.
 
-<output_verbosity_spec>
-- Default: 2-4 sentences for status updates.
-- For progress: 1 sentence + current step.
-- AVOID long explanations; prefer compact bullets.
-- Do NOT rephrase the task unless semantics change.
-</output_verbosity_spec>
+## Identity
 
-<scope_and_design_constraints>
-- Implement EXACTLY and ONLY what is requested.
-- No extra features, no UX embellishments, no scope creep.
-- If any instruction is ambiguous, choose the simplest valid interpretation OR ask.
-- Do NOT invent new requirements.
-- Do NOT expand task boundaries beyond what's written.
-</scope_and_design_constraints>
+You execute tasks directly as a **Senior Engineer**. You do not guess. You verify. You do not stop early. You complete.
 
-<blocked_actions>
-BLOCKED (will fail if attempted):
-| Tool | Status |
-|------|--------|
-| task | BLOCKED |
-| delegate_task | BLOCKED |
+**KEEP GOING. SOLVE PROBLEMS. ASK ONLY WHEN TRULY IMPOSSIBLE.**
 
-ALLOWED:
-| Tool | Usage |
-|------|-------|
-| call_omo_agent | Spawn explore/librarian for research ONLY |
+When blocked: try a different approach → decompose the problem → challenge assumptions → explore how others solved it.
 
-You work ALONE for implementation. No delegation.
-</blocked_actions>
+### Do NOT Ask — Just Do
 
-<uncertainty_and_ambiguity>
-- If a task is ambiguous or underspecified:
-  - Ask 1-2 precise clarifying questions, OR
-  - State your interpretation explicitly and proceed with the simplest approach.
-- Never fabricate file paths, requirements, or behavior.
-- Prefer language like "Based on the request..." instead of absolute claims.
-</uncertainty_and_ambiguity>
+**FORBIDDEN:**
+- "Should I proceed with X?" → JUST DO IT.
+- "Do you want me to run tests?" → RUN THEM.
+- "I noticed Y, should I fix it?" → FIX IT OR NOTE IN FINAL MESSAGE.
+- Stopping after partial implementation → 100% OR NOTHING.
+
+**CORRECT:**
+- Keep going until COMPLETELY done
+- Run verification (lint, tests, build) WITHOUT asking
+- Make decisions. Course-correct only on CONCRETE failure
+- Note assumptions in final message, not as questions mid-work
+- Need context? Fire explore/librarian via call_omo_agent IMMEDIATELY — keep working while they search
+
+## Scope Discipline
+
+- Implement EXACTLY and ONLY what is requested
+- No extra features, no UX embellishments, no scope creep
+- If ambiguous, choose the simplest valid interpretation OR ask ONE precise question
+- Do NOT invent new requirements or expand task boundaries
+
+## Ambiguity Protocol (EXPLORE FIRST)
+
+| Situation | Action |
+|-----------|--------|
+| Single valid interpretation | Proceed immediately |
+| Missing info that MIGHT exist | **EXPLORE FIRST** — use tools (grep, rg, file reads, explore agents) to find it |
+| Multiple plausible interpretations | State your interpretation, proceed with simplest approach |
+| Truly impossible to proceed | Ask ONE precise question (LAST RESORT) |
 
 <tool_usage_rules>
-- ALWAYS use tools over internal knowledge for:
-  - File contents (use Read, not memory)
-  - Current project state (use lsp_diagnostics, glob)
-  - Verification (use Bash for tests/build)
-- Parallelize independent tool calls when possible.
+- Parallelize independent tool calls: multiple file reads, grep searches, agent fires — all at once
+- Explore/Librarian via call_omo_agent = background research. Fire them and keep working
+- After any file edit: restate what changed, where, and what validation follows
+- Prefer tools over guessing whenever you need specific data (files, configs, patterns)
+- ALWAYS use tools over internal knowledge for file contents, project state, and verification
 </tool_usage_rules>
 
 ${taskDiscipline}
 
-<verification_spec>
-Task NOT complete without evidence:
+## Progress Updates
+
+**Report progress proactively — the user should always know what you're doing and why.**
+
+When to update (MANDATORY):
+- **Before exploration**: "Checking the repo structure for [pattern]..."
+- **After discovery**: "Found the config in \`src/config/\`. The pattern uses factory functions."
+- **Before large edits**: "About to modify [files] — [what and why]."
+- **After edits**: "Updated [file] — [what changed]. Running verification."
+- **On blockers**: "Hit a snag with [issue] — trying [alternative] instead."
+
+Style:
+- A few sentences, friendly and concrete — explain in plain language so anyone can follow
+- Include at least one specific detail (file path, pattern found, decision made)
+- When explaining technical decisions, explain the WHY — not just what you did
+
+## Code Quality & Verification
+
+### Before Writing Code (MANDATORY)
+
+1. SEARCH existing codebase for similar patterns/styles
+2. Match naming, indentation, import styles, error handling conventions
+3. Default to ASCII. Add comments only for non-obvious blocks
+
+### After Implementation (MANDATORY — DO NOT SKIP)
+
+1. **\`lsp_diagnostics\`** on ALL modified files — zero errors required
+2. **Run related tests** — pattern: modified \`foo.ts\` → look for \`foo.test.ts\`
+3. **Run typecheck** if TypeScript project
+4. **Run build** if applicable — exit code 0 required
+5. **Tell user** what you verified and the results — keep it clear and helpful
+
 | Check | Tool | Expected |
 |-------|------|----------|
 | Diagnostics | lsp_diagnostics | ZERO errors on changed files |
 | Build | Bash | Exit code 0 (if applicable) |
-| Tracking | ${useTaskSystem ? "TaskUpdate" : "todowrite"} | ${verificationText} |
+| Tracking | ${useTaskSystem ? "task_update" : "todowrite"} | ${verificationText} |
 
 **No evidence = not complete.**
-</verification_spec>
 
-<style_spec>
-- Start immediately. No acknowledgments ("I'll...", "Let me...").
-- Match user's communication style.
-- Dense > verbose.
-- Use structured output (bullets, tables) over prose.
-</style_spec>`
+## Output Contract
+
+<output_contract>
+**Format:**
+- Default: 3-6 sentences or ≤5 bullets
+- Simple yes/no: ≤2 sentences
+- Complex multi-file: 1 overview paragraph + ≤5 tagged bullets (What, Where, Risks, Next, Open)
+
+**Style:**
+- Start work immediately. Skip empty preambles ("I'm on it", "Let me...") — but DO send clear context before significant actions
+- Be friendly, clear, and easy to understand — explain so anyone can follow your reasoning
+- When explaining technical decisions, explain the WHY — not just the WHAT
+</output_contract>
+
+## Failure Recovery
+
+1. Fix root causes, not symptoms. Re-verify after EVERY attempt.
+2. If first approach fails → try alternative (different algorithm, pattern, library)
+3. After 3 DIFFERENT approaches fail → STOP and report what you tried clearly`
 
   if (!promptAppend) return prompt
-  return prompt + "\n\n" + promptAppend
+  return prompt + "\n\n" + resolvePromptAppend(promptAppend)
 }
 
 function buildGptTaskDisciplineSection(useTaskSystem: boolean): string {
   if (useTaskSystem) {
-    return `<task_discipline_spec>
-TASK TRACKING (NON-NEGOTIABLE):
+    return `## Task Discipline (NON-NEGOTIABLE)
+
 | Trigger | Action |
 |---------|--------|
-| 2+ steps | TaskCreate FIRST, atomic breakdown |
-| Starting step | TaskUpdate(status="in_progress") - ONE at a time |
-| Completing step | TaskUpdate(status="completed") IMMEDIATELY |
+| 2+ steps | task_create FIRST, atomic breakdown |
+| Starting step | task_update(status="in_progress") — ONE at a time |
+| Completing step | task_update(status="completed") IMMEDIATELY |
 | Batching | NEVER batch completions |
 
-No tasks on multi-step work = INCOMPLETE WORK.
-</task_discipline_spec>`
+No tasks on multi-step work = INCOMPLETE WORK.`
   }
 
-  return `<todo_discipline_spec>
-TODO TRACKING (NON-NEGOTIABLE):
+  return `## Todo Discipline (NON-NEGOTIABLE)
+
 | Trigger | Action |
 |---------|--------|
 | 2+ steps | todowrite FIRST, atomic breakdown |
-| Starting step | Mark in_progress - ONE at a time |
+| Starting step | Mark in_progress — ONE at a time |
 | Completing step | Mark completed IMMEDIATELY |
 | Batching | NEVER batch completions |
 
-No todos on multi-step work = INCOMPLETE WORK.
-</todo_discipline_spec>`
+No todos on multi-step work = INCOMPLETE WORK.`
 }

src/agents/sisyphus-junior/index.test.ts

@@ -71,7 +71,7 @@ describe("createSisyphusJuniorAgentWithOverrides", () => {
       const result = createSisyphusJuniorAgentWithOverrides(override)
 
       // then
-      expect(result.prompt).toContain("You work ALONE")
+      expect(result.prompt).toContain("Sisyphus-Junior")
       expect(result.prompt).toContain("Extra instructions here")
     })
   })
@@ -138,18 +138,17 @@ describe("createSisyphusJuniorAgentWithOverrides", () => {
       const result = createSisyphusJuniorAgentWithOverrides(override)
 
       // then
-      expect(result.prompt).toContain("You work ALONE")
+      expect(result.prompt).toContain("Sisyphus-Junior")
       expect(result.prompt).not.toBe("Completely new prompt that replaces everything")
     })
   })
 
-  describe("tool safety (task/delegate_task blocked, call_omo_agent allowed)", () => {
-    test("task and delegate_task remain blocked, call_omo_agent is allowed via tools format", () => {
+  describe("tool safety (task blocked, call_omo_agent allowed)", () => {
+    test("task remains blocked, call_omo_agent is allowed via tools format", () => {
       // given
       const override = {
         tools: {
           task: true,
-          delegate_task: true,
           call_omo_agent: true,
           read: true,
         },
@@ -163,25 +162,22 @@ describe("createSisyphusJuniorAgentWithOverrides", () => {
       const permission = result.permission as Record<string, string> | undefined
       if (tools) {
         expect(tools.task).toBe(false)
-        expect(tools.delegate_task).toBe(false)
         // call_omo_agent is NOW ALLOWED for subagents to spawn explore/librarian
         expect(tools.call_omo_agent).toBe(true)
         expect(tools.read).toBe(true)
       }
       if (permission) {
         expect(permission.task).toBe("deny")
-        expect(permission.delegate_task).toBe("deny")
         // call_omo_agent is NOW ALLOWED for subagents to spawn explore/librarian
         expect(permission.call_omo_agent).toBe("allow")
       }
     })
 
-    test("task and delegate_task remain blocked when using permission format override", () => {
+    test("task remains blocked when using permission format override", () => {
       // given
       const override = {
         permission: {
           task: "allow",
-          delegate_task: "allow",
           call_omo_agent: "allow",
           read: "allow",
         },
@@ -190,24 +186,98 @@ describe("createSisyphusJuniorAgentWithOverrides", () => {
       // when
       const result = createSisyphusJuniorAgentWithOverrides(override as Parameters<typeof createSisyphusJuniorAgentWithOverrides>[0])
 
-      // then - task/delegate_task blocked, but call_omo_agent allowed for explore/librarian spawning
+      // then - task blocked, but call_omo_agent allowed for explore/librarian spawning
       const tools = result.tools as Record<string, boolean> | undefined
       const permission = result.permission as Record<string, string> | undefined
       if (tools) {
         expect(tools.task).toBe(false)
-        expect(tools.delegate_task).toBe(false)
         expect(tools.call_omo_agent).toBe(true)
       }
       if (permission) {
         expect(permission.task).toBe("deny")
-        expect(permission.delegate_task).toBe("deny")
         expect(permission.call_omo_agent).toBe("allow")
       }
     })
   })
 
+  describe("useTaskSystem integration", () => {
+    test("useTaskSystem=true produces Task_Discipline prompt for Claude", () => {
+      //#given
+      const override = { model: "anthropic/claude-sonnet-4-5" }
+
+      //#when
+      const result = createSisyphusJuniorAgentWithOverrides(override, undefined, true)
+
+      //#then
+      expect(result.prompt).toContain("task_create")
+      expect(result.prompt).toContain("task_update")
+      expect(result.prompt).not.toContain("todowrite")
+    })
+
+    test("useTaskSystem=true produces Task Discipline prompt for GPT", () => {
+      //#given
+      const override = { model: "openai/gpt-5.2" }
+
+      //#when
+      const result = createSisyphusJuniorAgentWithOverrides(override, undefined, true)
+
+      //#then
+      expect(result.prompt).toContain("Task Discipline")
+      expect(result.prompt).toContain("task_create")
+      expect(result.prompt).not.toContain("Todo Discipline")
+    })
+
+    test("useTaskSystem=false (default) produces Todo_Discipline prompt", () => {
+      //#given
+      const override = {}
+
+      //#when
+      const result = createSisyphusJuniorAgentWithOverrides(override)
+
+      //#then
+      expect(result.prompt).toContain("todowrite")
+      expect(result.prompt).not.toContain("task_create")
+    })
+
+    test("useTaskSystem=true includes task_create/task_update in Claude prompt", () => {
+      //#given
+      const override = { model: "anthropic/claude-sonnet-4-5" }
+
+      //#when
+      const result = createSisyphusJuniorAgentWithOverrides(override, undefined, true)
+
+      //#then
+      expect(result.prompt).toContain("task_create")
+      expect(result.prompt).toContain("task_update")
+    })
+
+    test("useTaskSystem=true includes task_create/task_update in GPT prompt", () => {
+      //#given
+      const override = { model: "openai/gpt-5.2" }
+
+      //#when
+      const result = createSisyphusJuniorAgentWithOverrides(override, undefined, true)
+
+      //#then
+      expect(result.prompt).toContain("task_create")
+      expect(result.prompt).toContain("task_update")
+    })
+
+    test("useTaskSystem=false uses todowrite instead of task_create", () => {
+      //#given
+      const override = { model: "anthropic/claude-sonnet-4-5" }
+
+      //#when
+      const result = createSisyphusJuniorAgentWithOverrides(override, undefined, false)
+
+      //#then
+      expect(result.prompt).toContain("todowrite")
+      expect(result.prompt).not.toContain("task_create")
+    })
+  })
+
   describe("prompt composition", () => {
-    test("base prompt contains discipline constraints", () => {
+    test("base prompt contains identity", () => {
       // given
       const override = {}
 
@@ -216,10 +286,10 @@ describe("createSisyphusJuniorAgentWithOverrides", () => {
 
       // then
       expect(result.prompt).toContain("Sisyphus-Junior")
-      expect(result.prompt).toContain("You work ALONE")
+      expect(result.prompt).toContain("Execute tasks directly")
     })
 
-    test("Claude model uses default prompt with BLOCKED ACTIONS section", () => {
+    test("Claude model uses default prompt with discipline section", () => {
       // given
       const override = { model: "anthropic/claude-sonnet-4-5" }
 
@@ -227,11 +297,11 @@ describe("createSisyphusJuniorAgentWithOverrides", () => {
       const result = createSisyphusJuniorAgentWithOverrides(override)
 
       // then
-      expect(result.prompt).toContain("BLOCKED ACTIONS")
-      expect(result.prompt).not.toContain("<blocked_actions>")
+      expect(result.prompt).toContain("<Role>")
+      expect(result.prompt).toContain("todowrite")
     })
 
-    test("GPT model uses GPT-optimized prompt with blocked_actions section", () => {
+    test("GPT model uses GPT-optimized prompt with Hephaestus-style sections", () => {
       // given
       const override = { model: "openai/gpt-5.2" }
 
@@ -239,9 +309,9 @@ describe("createSisyphusJuniorAgentWithOverrides", () => {
       const result = createSisyphusJuniorAgentWithOverrides(override)
 
       // then
-      expect(result.prompt).toContain("<blocked_actions>")
-      expect(result.prompt).toContain("<output_verbosity_spec>")
-      expect(result.prompt).toContain("<scope_and_design_constraints>")
+      expect(result.prompt).toContain("Scope Discipline")
+      expect(result.prompt).toContain("<tool_usage_rules>")
+      expect(result.prompt).toContain("Progress Updates")
     })
 
     test("prompt_append is added after base prompt", () => {
@@ -252,7 +322,7 @@ describe("createSisyphusJuniorAgentWithOverrides", () => {
       const result = createSisyphusJuniorAgentWithOverrides(override)
 
       // then
-      const baseEndIndex = result.prompt!.indexOf("Dense > verbose.")
+      const baseEndIndex = result.prompt!.indexOf("</Style>")
       const appendIndex = result.prompt!.indexOf("CUSTOM_MARKER_FOR_TEST")
       expect(baseEndIndex).not.toBe(-1)
       expect(appendIndex).toBeGreaterThan(baseEndIndex)
@@ -307,7 +377,7 @@ describe("getSisyphusJuniorPromptSource", () => {
 })
 
 describe("buildSisyphusJuniorPrompt", () => {
-  test("GPT model prompt contains GPT-5.2 specific sections", () => {
+  test("GPT model prompt contains Hephaestus-style sections", () => {
     // given
     const model = "openai/gpt-5.2"
 
@@ -315,10 +385,10 @@ describe("buildSisyphusJuniorPrompt", () => {
     const prompt = buildSisyphusJuniorPrompt(model, false)
 
     // then
-    expect(prompt).toContain("<identity>")
-    expect(prompt).toContain("<output_verbosity_spec>")
-    expect(prompt).toContain("<scope_and_design_constraints>")
+    expect(prompt).toContain("## Identity")
+    expect(prompt).toContain("Scope Discipline")
     expect(prompt).toContain("<tool_usage_rules>")
+    expect(prompt).toContain("Progress Updates")
   })
 
   test("Claude model prompt contains Claude-specific sections", () => {
@@ -330,11 +400,11 @@ describe("buildSisyphusJuniorPrompt", () => {
 
     // then
     expect(prompt).toContain("<Role>")
-    expect(prompt).toContain("<Critical_Constraints>")
-    expect(prompt).toContain("BLOCKED ACTIONS")
+    expect(prompt).toContain("<Todo_Discipline>")
+    expect(prompt).toContain("todowrite")
   })
 
-  test("useTaskSystem=true includes Task_Discipline for GPT", () => {
+  test("useTaskSystem=true includes Task Discipline for GPT", () => {
     // given
     const model = "openai/gpt-5.2"
 
@@ -342,8 +412,8 @@ describe("buildSisyphusJuniorPrompt", () => {
     const prompt = buildSisyphusJuniorPrompt(model, true)
 
     // then
-    expect(prompt).toContain("<task_discipline_spec>")
-    expect(prompt).toContain("TaskCreate")
+    expect(prompt).toContain("Task Discipline")
+    expect(prompt).toContain("task_create")
   })
 
   test("useTaskSystem=false includes Todo_Discipline for Claude", () => {

src/agents/sisyphus-junior/index.ts

@@ -1,121 +1,10 @@
-/**
- * Sisyphus-Junior - Focused Task Executor
- *
- * Executes delegated tasks directly without spawning other agents.
- * Category-spawned executor with domain-specific configurations.
- *
- * Routing:
- * 1. GPT models (openai/*, github-copilot/gpt-*) -> gpt.ts (GPT-5.2 optimized)
- * 2. Default (Claude, etc.) -> default.ts (Claude-optimized)
- */
-
-import type { AgentConfig } from "@opencode-ai/sdk"
-import type { AgentMode } from "../types"
-import { isGptModel } from "../types"
-import type { AgentOverrideConfig } from "../../config/schema"
-import {
-  createAgentToolRestrictions,
-  type PermissionValue,
-} from "../../shared/permission-compat"
-
-import { buildDefaultSisyphusJuniorPrompt } from "./default"
-import { buildGptSisyphusJuniorPrompt } from "./gpt"
-
 export { buildDefaultSisyphusJuniorPrompt } from "./default"
 export { buildGptSisyphusJuniorPrompt } from "./gpt"
 
-const MODE: AgentMode = "subagent"
-
-// Core tools that Sisyphus-Junior must NEVER have access to
-// Note: call_omo_agent is ALLOWED so subagents can spawn explore/librarian
-const BLOCKED_TOOLS = ["task", "delegate_task"]
-
-export const SISYPHUS_JUNIOR_DEFAULTS = {
-  model: "anthropic/claude-sonnet-4-5",
-  temperature: 0.1,
-} as const
-
-export type SisyphusJuniorPromptSource = "default" | "gpt"
-
-/**
- * Determines which Sisyphus-Junior prompt to use based on model.
- */
-export function getSisyphusJuniorPromptSource(model?: string): SisyphusJuniorPromptSource {
-  if (model && isGptModel(model)) {
-    return "gpt"
-  }
-  return "default"
-}
-
-/**
- * Builds the appropriate Sisyphus-Junior prompt based on model.
- */
-export function buildSisyphusJuniorPrompt(
-  model: string | undefined,
-  useTaskSystem: boolean,
-  promptAppend?: string
-): string {
-  const source = getSisyphusJuniorPromptSource(model)
-
-  switch (source) {
-    case "gpt":
-      return buildGptSisyphusJuniorPrompt(useTaskSystem, promptAppend)
-    case "default":
-    default:
-      return buildDefaultSisyphusJuniorPrompt(useTaskSystem, promptAppend)
-  }
-}
-
-export function createSisyphusJuniorAgentWithOverrides(
-  override: AgentOverrideConfig | undefined,
-  systemDefaultModel?: string,
-  useTaskSystem = false
-): AgentConfig {
-  if (override?.disable) {
-    override = undefined
-  }
-
-  const model = override?.model ?? systemDefaultModel ?? SISYPHUS_JUNIOR_DEFAULTS.model
-  const temperature = override?.temperature ?? SISYPHUS_JUNIOR_DEFAULTS.temperature
-
-  const promptAppend = override?.prompt_append
-  const prompt = buildSisyphusJuniorPrompt(model, useTaskSystem, promptAppend)
-
-  const baseRestrictions = createAgentToolRestrictions(BLOCKED_TOOLS)
-
-  const userPermission = (override?.permission ?? {}) as Record<string, PermissionValue>
-  const basePermission = baseRestrictions.permission
-  const merged: Record<string, PermissionValue> = { ...userPermission }
-  for (const tool of BLOCKED_TOOLS) {
-    merged[tool] = "deny"
-  }
-  merged.call_omo_agent = "allow"
-  const toolsConfig = { permission: { ...merged, ...basePermission } }
-
-  const base: AgentConfig = {
-    description: override?.description ??
-      "Focused task executor. Same discipline, no delegation. (Sisyphus-Junior - OhMyOpenCode)",
-    mode: MODE,
-    model,
-    temperature,
-    maxTokens: 64000,
-    prompt,
-    color: override?.color ?? "#20B2AA",
-    ...toolsConfig,
-  }
-
-  if (override?.top_p !== undefined) {
-    base.top_p = override.top_p
-  }
-
-  if (isGptModel(model)) {
-    return { ...base, reasoningEffort: "medium" } as AgentConfig
-  }
-
-  return {
-    ...base,
-    thinking: { type: "enabled", budgetTokens: 32000 },
-  } as AgentConfig
-}
-
-createSisyphusJuniorAgentWithOverrides.mode = MODE
+export {
+  SISYPHUS_JUNIOR_DEFAULTS,
+  getSisyphusJuniorPromptSource,
+  buildSisyphusJuniorPrompt,
+  createSisyphusJuniorAgentWithOverrides,
+} from "./agent"
+export type { SisyphusJuniorPromptSource } from "./agent"

src/agents/sisyphus.ts

@@ -1,15 +1,20 @@
-import type { AgentConfig } from "@opencode-ai/sdk"
-import type { AgentMode, AgentPromptMetadata } from "./types"
-import { isGptModel } from "./types"
+import type { AgentConfig } from "@opencode-ai/sdk";
+import type { AgentMode, AgentPromptMetadata } from "./types";
+import { isGptModel } from "./types";
 
-const MODE: AgentMode = "primary"
+const MODE: AgentMode = "primary";
 export const SISYPHUS_PROMPT_METADATA: AgentPromptMetadata = {
   category: "utility",
   cost: "EXPENSIVE",
   promptAlias: "Sisyphus",
   triggers: [],
-}
-import type { AvailableAgent, AvailableTool, AvailableSkill, AvailableCategory } from "./dynamic-agent-prompt-builder"
+};
+import type {
+  AvailableAgent,
+  AvailableTool,
+  AvailableSkill,
+  AvailableCategory,
+} from "./dynamic-agent-prompt-builder";
 import {
   buildKeyTriggersSection,
   buildToolSelectionTable,
@@ -21,7 +26,7 @@ import {
   buildHardBlocksSection,
   buildAntiPatternsSection,
   categorizeTools,
-} from "./dynamic-agent-prompt-builder"
+} from "./dynamic-agent-prompt-builder";
 
 function buildTaskManagementSection(useTaskSystem: boolean): string {
   if (useTaskSystem) {
@@ -80,7 +85,7 @@ I want to make sure I understand correctly.
 
 Should I proceed with [recommendation], or would you prefer differently?
 \`\`\`
-</Task_Management>`
+</Task_Management>`;
   }
 
   return `<Task_Management>
@@ -138,7 +143,7 @@ I want to make sure I understand correctly.
 
 Should I proceed with [recommendation], or would you prefer differently?
 \`\`\`
-</Task_Management>`
+</Task_Management>`;
 }
 
 function buildDynamicSisyphusPrompt(
@@ -146,21 +151,28 @@ function buildDynamicSisyphusPrompt(
   availableTools: AvailableTool[] = [],
   availableSkills: AvailableSkill[] = [],
   availableCategories: AvailableCategory[] = [],
-  useTaskSystem = false
+  useTaskSystem = false,
 ): string {
-  const keyTriggers = buildKeyTriggersSection(availableAgents, availableSkills)
-  const toolSelection = buildToolSelectionTable(availableAgents, availableTools, availableSkills)
-  const exploreSection = buildExploreSection(availableAgents)
-  const librarianSection = buildLibrarianSection(availableAgents)
-  const categorySkillsGuide = buildCategorySkillsDelegationGuide(availableCategories, availableSkills)
-  const delegationTable = buildDelegationTable(availableAgents)
-  const oracleSection = buildOracleSection(availableAgents)
-  const hardBlocks = buildHardBlocksSection()
-  const antiPatterns = buildAntiPatternsSection()
-  const taskManagementSection = buildTaskManagementSection(useTaskSystem)
+  const keyTriggers = buildKeyTriggersSection(availableAgents, availableSkills);
+  const toolSelection = buildToolSelectionTable(
+    availableAgents,
+    availableTools,
+    availableSkills,
+  );
+  const exploreSection = buildExploreSection(availableAgents);
+  const librarianSection = buildLibrarianSection(availableAgents);
+  const categorySkillsGuide = buildCategorySkillsDelegationGuide(
+    availableCategories,
+    availableSkills,
+  );
+  const delegationTable = buildDelegationTable(availableAgents);
+  const oracleSection = buildOracleSection(availableAgents);
+  const hardBlocks = buildHardBlocksSection();
+  const antiPatterns = buildAntiPatternsSection();
+  const taskManagementSection = buildTaskManagementSection(useTaskSystem);
   const todoHookNote = useTaskSystem
     ? "YOUR TASK CREATION WOULD BE TRACKED BY HOOK([SYSTEM REMINDER - TASK CONTINUATION])"
-    : "YOUR TODO CREATION WOULD BE TRACKED BY HOOK([SYSTEM REMINDER - TODO CONTINUATION])"
+    : "YOUR TODO CREATION WOULD BE TRACKED BY HOOK([SYSTEM REMINDER - TODO CONTINUATION])";
 
   return `<Role>
 You are "Sisyphus" - Powerful AI Agent with orchestration capabilities from OhMyOpenCode.
@@ -214,8 +226,8 @@ ${keyTriggers}
 
 **Delegation Check (MANDATORY before acting directly):**
 1. Is there a specialized agent that perfectly matches this request?
-2. If not, is there a \`delegate_task\` category best describes this task? (visual-engineering, ultrabrain, quick etc.) What skills are available to equip the agent with?
-  - MUST FIND skills to use, for: \`delegate_task(load_skills=[{skill1}, ...])\` MUST PASS SKILL AS DELEGATE TASK PARAMETER.
+2. If not, is there a \`task\` category best describes this task? (visual-engineering, ultrabrain, quick etc.) What skills are available to equip the agent with?
+  - MUST FIND skills to use, for: \`task(load_skills=[{skill1}, ...])\` MUST PASS SKILL AS TASK PARAMETER.
 3. Can I do it myself for the best result, FOR SURE? REALLY, REALLY, THERE IS NO APPROPRIATE CATEGORIES TO WORK WITH?
 
 **Default Bias: DELEGATE. WORK YOURSELF ONLY WHEN IT IS SUPER SIMPLE.**
@@ -275,24 +287,30 @@ ${librarianSection}
 
 \`\`\`typescript
 // CORRECT: Always background, always parallel
-// Prompt structure: [CONTEXT: what I'm doing] + [GOAL: what I'm trying to achieve] + [QUESTION: what I need to know] + [REQUEST: what to find]
+// Prompt structure (each field should be substantive, not a single sentence):
+//   [CONTEXT]: What task I'm working on, which files/modules are involved, and what approach I'm taking
+//   [GOAL]: The specific outcome I need — what decision or action the results will unblock
+//   [DOWNSTREAM]: How I will use the results — what I'll build/decide based on what's found
+//   [REQUEST]: Concrete search instructions — what to find, what format to return, and what to SKIP
+
 // Contextual Grep (internal)
-delegate_task(subagent_type="explore", run_in_background=true, load_skills=[], prompt="I'm implementing user authentication for our API. I need to understand how auth is currently structured in this codebase. Find existing auth implementations, patterns, and where credentials are validated.")
-delegate_task(subagent_type="explore", run_in_background=true, load_skills=[], prompt="I'm adding error handling to the auth flow. I want to follow existing project conventions for consistency. Find how errors are handled elsewhere - patterns, custom error classes, and response formats used.")
+task(subagent_type="explore", run_in_background=true, load_skills=[], description="Find auth implementations", prompt="I'm implementing JWT auth for the REST API in src/api/routes/. I need to match existing auth conventions so my code fits seamlessly. I'll use this to decide middleware structure and token flow. Find: auth middleware, login/signup handlers, token generation, credential validation. Focus on src/ — skip tests. Return file paths with pattern descriptions.")
+task(subagent_type="explore", run_in_background=true, load_skills=[], description="Find error handling patterns", prompt="I'm adding error handling to the auth flow and need to follow existing error conventions exactly. I'll use this to structure my error responses and pick the right base class. Find: custom Error subclasses, error response format (JSON shape), try/catch patterns in handlers, global error middleware. Skip test files. Return the error class hierarchy and response format.")
+
 // Reference Grep (external)
-delegate_task(subagent_type="librarian", run_in_background=true, load_skills=[], prompt="I'm implementing JWT-based auth and need to ensure security best practices. Find official JWT documentation and security recommendations - token expiration, refresh strategies, and common vulnerabilities to avoid.")
-delegate_task(subagent_type="librarian", run_in_background=true, load_skills=[], prompt="I'm building Express middleware for auth and want production-quality patterns. Find how established Express apps handle authentication - middleware structure, session management, and error handling examples.")
+task(subagent_type="librarian", run_in_background=true, load_skills=[], description="Find JWT security docs", prompt="I'm implementing JWT auth and need current security best practices to choose token storage (httpOnly cookies vs localStorage) and set expiration policy. Find: OWASP auth guidelines, recommended token lifetimes, refresh token rotation strategies, common JWT vulnerabilities. Skip 'what is JWT' tutorials — production security guidance only.")
+task(subagent_type="librarian", run_in_background=true, load_skills=[], description="Find Express auth patterns", prompt="I'm building Express auth middleware and need production-quality patterns to structure my middleware chain. Find how established Express apps (1000+ stars) handle: middleware ordering, token refresh, role-based access control, auth error propagation. Skip basic tutorials — I need battle-tested patterns with proper error handling.")
 // Continue working immediately. Collect with background_output when needed.
 
 // WRONG: Sequential or blocking
-result = delegate_task(..., run_in_background=false)  // Never wait synchronously for explore/librarian
+result = task(..., run_in_background=false)  // Never wait synchronously for explore/librarian
 \`\`\`
 
 ### Background Result Collection:
 1. Launch parallel agents → receive task_ids
 2. Continue immediate work
 3. When results needed: \`background_output(task_id="...")\`
-4. BEFORE final answer: \`background_cancel(all=true)\`
+4. Before final answer: cancel disposable tasks (explore, librarian) individually via \`background_cancel(taskId="...")\`. Always wait for Oracle — collect its result via \`background_output\` before answering.
 
 ### Search Stop Conditions
 
@@ -309,6 +327,7 @@ STOP searching when:
 ## Phase 2B - Implementation
 
 ### Pre-Implementation:
+0. Find relevant skills that you can load, and load them IMMEDIATELY.
 1. If task has 2+ steps → Create todo list IMMEDIATELY, IN SUPER DETAIL. No announcements—just create it.
 2. Mark current task \`in_progress\` before starting
 3. Mark \`completed\` as soon as done (don't batch) - OBSESSIVELY TRACK YOUR WORK USING TODO TOOLS
@@ -340,7 +359,7 @@ AFTER THE WORK YOU DELEGATED SEEMS DONE, ALWAYS VERIFY THE RESULTS AS FOLLOWING:
 
 ### Session Continuity (MANDATORY)
 
-Every \`delegate_task()\` output includes a session_id. **USE IT.**
+Every \`task()\` output includes a session_id. **USE IT.**
 
 **ALWAYS continue when:**
 | Scenario | Action |
@@ -358,10 +377,10 @@ Every \`delegate_task()\` output includes a session_id. **USE IT.**
 
 \`\`\`typescript
 // WRONG: Starting fresh loses all context
-delegate_task(category="quick", load_skills=[], run_in_background=false, prompt="Fix the type error in auth.ts...")
+task(category="quick", load_skills=[], run_in_background=false, description="Fix type error", prompt="Fix the type error in auth.ts...")
 
 // CORRECT: Resume preserves everything
-delegate_task(session_id="ses_abc123", prompt="Fix: Type error on line 42")
+task(session_id="ses_abc123", load_skills=[], run_in_background=false, description="Fix type error", prompt="Fix: Type error on line 42")
 \`\`\`
 
 **After EVERY delegation, STORE the session_id for potential continuation.**
@@ -430,8 +449,9 @@ If verification fails:
 3. Report: "Done. Note: found N pre-existing lint errors unrelated to my changes."
 
 ### Before Delivering Final Answer:
-- Cancel ALL running background tasks: \`background_cancel(all=true)\`
-- This conserves resources and ensures clean workflow completion
+- Cancel disposable background tasks (explore, librarian) individually via \`background_cancel(taskId="...")\`
+- **Always wait for Oracle**: Oracle takes 20+ min by design and always provides valuable independent analysis from a different angle — even when you already have enough context. Collect Oracle results via \`background_output\` before answering.
+- When Oracle is running, cancel disposable tasks individually instead of using \`background_cancel(all=true)\`.
 </Behavior_Instructions>
 
 ${oracleSection}
@@ -491,7 +511,7 @@ ${antiPatterns}
 - Prefer small, focused changes over large refactors
 - When uncertain about scope, ask
 </Constraints>
-`
+`;
 }
 
 export function createSisyphusAgent(
@@ -500,16 +520,25 @@ export function createSisyphusAgent(
   availableToolNames?: string[],
   availableSkills?: AvailableSkill[],
   availableCategories?: AvailableCategory[],
-  useTaskSystem = false
+  useTaskSystem = false,
 ): AgentConfig {
-  const tools = availableToolNames ? categorizeTools(availableToolNames) : []
-  const skills = availableSkills ?? []
-  const categories = availableCategories ?? []
+  const tools = availableToolNames ? categorizeTools(availableToolNames) : [];
+  const skills = availableSkills ?? [];
+  const categories = availableCategories ?? [];
   const prompt = availableAgents
-    ? buildDynamicSisyphusPrompt(availableAgents, tools, skills, categories, useTaskSystem)
-    : buildDynamicSisyphusPrompt([], tools, skills, categories, useTaskSystem)
+    ? buildDynamicSisyphusPrompt(
+        availableAgents,
+        tools,
+        skills,
+        categories,
+        useTaskSystem,
+      )
+    : buildDynamicSisyphusPrompt([], tools, skills, categories, useTaskSystem);
 
-  const permission = { question: "allow", call_omo_agent: "deny" } as AgentConfig["permission"]
+  const permission = {
+    question: "allow",
+    call_omo_agent: "deny",
+  } as AgentConfig["permission"];
   const base = {
     description:
       "Powerful AI orchestrator. Plans obsessively with todos, assesses search complexity before exploration, delegates strategically via category+skills combinations. Uses explore for internal code (parallel-friendly), librarian for external docs. (Sisyphus - OhMyOpenCode)",
@@ -519,12 +548,12 @@ export function createSisyphusAgent(
     prompt,
     color: "#00CED1",
     permission,
-  }
+  };
 
   if (isGptModel(model)) {
-    return { ...base, reasoningEffort: "medium" }
+    return { ...base, reasoningEffort: "medium" };
   }
 
-  return { ...base, thinking: { type: "enabled", budgetTokens: 32000 } }
+  return { ...base, thinking: { type: "enabled", budgetTokens: 32000 } };
 }
-createSisyphusAgent.mode = MODE
+createSisyphusAgent.mode = MODE;

src/agents/types.test.ts

@@ -0,0 +1,49 @@
+import { describe, test, expect } from "bun:test";
+import { isGptModel } from "./types";
+
+describe("isGptModel", () => {
+  test("standard openai provider models", () => {
+    expect(isGptModel("openai/gpt-5.2")).toBe(true);
+    expect(isGptModel("openai/gpt-4o")).toBe(true);
+    expect(isGptModel("openai/o1")).toBe(true);
+    expect(isGptModel("openai/o3-mini")).toBe(true);
+  });
+
+  test("github copilot gpt models", () => {
+    expect(isGptModel("github-copilot/gpt-5.2")).toBe(true);
+    expect(isGptModel("github-copilot/gpt-4o")).toBe(true);
+  });
+
+  test("litellm proxied gpt models", () => {
+    expect(isGptModel("litellm/gpt-5.2")).toBe(true);
+    expect(isGptModel("litellm/gpt-4o")).toBe(true);
+    expect(isGptModel("litellm/o1")).toBe(true);
+    expect(isGptModel("litellm/o3-mini")).toBe(true);
+    expect(isGptModel("litellm/o4-mini")).toBe(true);
+  });
+
+  test("other proxied gpt models", () => {
+    expect(isGptModel("ollama/gpt-4o")).toBe(true);
+    expect(isGptModel("custom-provider/gpt-5.2")).toBe(true);
+  });
+
+  test("gpt4 prefix without hyphen (legacy naming)", () => {
+    expect(isGptModel("litellm/gpt4o")).toBe(true);
+    expect(isGptModel("ollama/gpt4")).toBe(true);
+  });
+
+  test("claude models are not gpt", () => {
+    expect(isGptModel("anthropic/claude-opus-4-6")).toBe(false);
+    expect(isGptModel("anthropic/claude-sonnet-4-5")).toBe(false);
+    expect(isGptModel("litellm/anthropic.claude-opus-4-5")).toBe(false);
+  });
+
+  test("gemini models are not gpt", () => {
+    expect(isGptModel("google/gemini-3-pro")).toBe(false);
+    expect(isGptModel("litellm/gemini-3-pro")).toBe(false);
+  });
+
+  test("opencode provider is not gpt", () => {
+    expect(isGptModel("opencode/claude-opus-4-6")).toBe(false);
+  });
+});

src/agents/types.ts

@@ -66,8 +66,18 @@ export interface AgentPromptMetadata {
   keyTrigger?: string
 }
 
+function extractModelName(model: string): string {
+  return model.includes("/") ? model.split("/").pop() ?? model : model
+}
+
+const GPT_MODEL_PREFIXES = ["gpt-", "gpt4", "o1", "o3", "o4"]
+
 export function isGptModel(model: string): boolean {
-  return model.startsWith("openai/") || model.startsWith("github-copilot/gpt-")
+  if (model.startsWith("openai/") || model.startsWith("github-copilot/gpt-"))
+    return true
+
+  const modelName = extractModelName(model).toLowerCase()
+  return GPT_MODEL_PREFIXES.some((prefix) => modelName.startsWith(prefix))
 }
 
 export type BuiltinAgentName =

src/agents/utils.test.ts

@@ -1,19 +1,21 @@
+/// <reference types="bun-types" />
+
 import { describe, test, expect, beforeEach, afterEach, spyOn } from "bun:test"
-import { createBuiltinAgents } from "./utils"
+import { createBuiltinAgents } from "./builtin-agents"
 import type { AgentConfig } from "@opencode-ai/sdk"
 import { clearSkillCache } from "../features/opencode-skill-loader/skill-content"
 import * as connectedProvidersCache from "../shared/connected-providers-cache"
 import * as modelAvailability from "../shared/model-availability"
 import * as shared from "../shared"
 
-const TEST_DEFAULT_MODEL = "anthropic/claude-opus-4-5"
+const TEST_DEFAULT_MODEL = "anthropic/claude-opus-4-6"
 
 describe("createBuiltinAgents with model overrides", () => {
   test("Sisyphus with default model has thinking config when all models available", async () => {
     // #given
     const fetchSpy = spyOn(shared, "fetchAvailableModels").mockResolvedValue(
       new Set([
-        "anthropic/claude-opus-4-5",
+        "anthropic/claude-opus-4-6",
         "kimi-for-coding/k2p5",
         "opencode/kimi-k2.5-free",
         "zai-coding-plan/glm-4.7",
@@ -26,7 +28,7 @@ describe("createBuiltinAgents with model overrides", () => {
       const agents = await createBuiltinAgents([], {}, undefined, TEST_DEFAULT_MODEL, undefined, undefined, [], {})
 
       // #then
-      expect(agents.sisyphus.model).toBe("anthropic/claude-opus-4-5")
+      expect(agents.sisyphus.model).toBe("anthropic/claude-opus-4-6")
       expect(agents.sisyphus.thinking).toEqual({ type: "enabled", budgetTokens: 32000 })
       expect(agents.sisyphus.reasoningEffort).toBeUndefined()
     } finally {
@@ -41,7 +43,7 @@ describe("createBuiltinAgents with model overrides", () => {
     }
 
     // #when
-    const agents = await createBuiltinAgents([], overrides, undefined, TEST_DEFAULT_MODEL)
+    const agents = await createBuiltinAgents([], overrides, undefined, TEST_DEFAULT_MODEL, undefined, undefined, [], undefined, undefined)
 
     // #then
     expect(agents.sisyphus.model).toBe("github-copilot/gpt-5.2")
@@ -79,9 +81,75 @@ describe("createBuiltinAgents with model overrides", () => {
     }
   })
 
+  test("user config model takes priority over uiSelectedModel for sisyphus", async () => {
+    // #given
+    const fetchSpy = spyOn(shared, "fetchAvailableModels").mockResolvedValue(
+      new Set(["openai/gpt-5.2", "anthropic/claude-sonnet-4-5"])
+    )
+    const uiSelectedModel = "openai/gpt-5.2"
+    const overrides = {
+      sisyphus: { model: "google/antigravity-claude-opus-4-5-thinking" },
+    }
+
+    try {
+      // #when
+      const agents = await createBuiltinAgents(
+        [],
+        overrides,
+        undefined,
+        TEST_DEFAULT_MODEL,
+        undefined,
+        undefined,
+        [],
+        undefined,
+        undefined,
+        uiSelectedModel
+      )
+
+      // #then
+      expect(agents.sisyphus).toBeDefined()
+      expect(agents.sisyphus.model).toBe("google/antigravity-claude-opus-4-5-thinking")
+    } finally {
+      fetchSpy.mockRestore()
+    }
+  })
+
+  test("user config model takes priority over uiSelectedModel for atlas", async () => {
+    // #given
+    const fetchSpy = spyOn(shared, "fetchAvailableModels").mockResolvedValue(
+      new Set(["openai/gpt-5.2", "anthropic/claude-sonnet-4-5"])
+    )
+    const uiSelectedModel = "openai/gpt-5.2"
+    const overrides = {
+      atlas: { model: "google/antigravity-claude-opus-4-5-thinking" },
+    }
+
+    try {
+      // #when
+      const agents = await createBuiltinAgents(
+        [],
+        overrides,
+        undefined,
+        TEST_DEFAULT_MODEL,
+        undefined,
+        undefined,
+        [],
+        undefined,
+        undefined,
+        uiSelectedModel
+      )
+
+      // #then
+      expect(agents.atlas).toBeDefined()
+      expect(agents.atlas.model).toBe("google/antigravity-claude-opus-4-5-thinking")
+    } finally {
+      fetchSpy.mockRestore()
+    }
+  })
+
   test("Sisyphus is created on first run when no availableModels or cache exist", async () => {
     // #given
-    const systemDefaultModel = "anthropic/claude-opus-4-5"
+    const systemDefaultModel = "anthropic/claude-opus-4-6"
     const cacheSpy = spyOn(connectedProvidersCache, "readConnectedProvidersCache").mockReturnValue(null)
     const fetchSpy = spyOn(shared, "fetchAvailableModels").mockResolvedValue(new Set())
 
@@ -91,7 +159,7 @@ describe("createBuiltinAgents with model overrides", () => {
 
       // #then
       expect(agents.sisyphus).toBeDefined()
-      expect(agents.sisyphus.model).toBe("anthropic/claude-opus-4-5")
+      expect(agents.sisyphus.model).toBe("anthropic/claude-opus-4-6")
     } finally {
       cacheSpy.mockRestore()
       fetchSpy.mockRestore()
@@ -103,7 +171,7 @@ describe("createBuiltinAgents with model overrides", () => {
      const cacheSpy = spyOn(connectedProvidersCache, "readConnectedProvidersCache").mockReturnValue(["openai"])
 
      // #when
-     const agents = await createBuiltinAgents([], {}, undefined, TEST_DEFAULT_MODEL)
+     const agents = await createBuiltinAgents([], {}, undefined, TEST_DEFAULT_MODEL, undefined, undefined, [], undefined, undefined)
 
      // #then - oracle resolves via connected cache fallback to openai/gpt-5.2 (not system default)
      expect(agents.oracle.model).toBe("openai/gpt-5.2")
@@ -132,7 +200,7 @@ describe("createBuiltinAgents with model overrides", () => {
     }
 
     // #when
-    const agents = await createBuiltinAgents([], overrides, undefined, TEST_DEFAULT_MODEL)
+    const agents = await createBuiltinAgents([], overrides, undefined, TEST_DEFAULT_MODEL, undefined, undefined, [], undefined, undefined)
 
     // #then
     expect(agents.oracle.model).toBe("openai/gpt-5.2")
@@ -148,7 +216,7 @@ describe("createBuiltinAgents with model overrides", () => {
     }
 
     // #when
-    const agents = await createBuiltinAgents([], overrides, undefined, TEST_DEFAULT_MODEL)
+    const agents = await createBuiltinAgents([], overrides, undefined, TEST_DEFAULT_MODEL, undefined, undefined, [], undefined, undefined)
 
     // #then
     expect(agents.oracle.model).toBe("anthropic/claude-sonnet-4")
@@ -164,12 +232,241 @@ describe("createBuiltinAgents with model overrides", () => {
      }
 
      // #when
-     const agents = await createBuiltinAgents([], overrides, undefined, TEST_DEFAULT_MODEL)
+     const agents = await createBuiltinAgents([], overrides, undefined, TEST_DEFAULT_MODEL, undefined, undefined, [], undefined, undefined)
 
      // #then
      expect(agents.sisyphus.model).toBe("github-copilot/gpt-5.2")
      expect(agents.sisyphus.temperature).toBe(0.5)
    })
+
+  test("createBuiltinAgents excludes disabled skills from availableSkills", async () => {
+    // #given
+    const disabledSkills = new Set(["playwright"])
+
+    // #when
+    const agents = await createBuiltinAgents([], {}, undefined, TEST_DEFAULT_MODEL, undefined, undefined, [], undefined, undefined, undefined, disabledSkills)
+
+    // #then
+    expect(agents.sisyphus.prompt).not.toContain("playwright")
+    expect(agents.sisyphus.prompt).toContain("frontend-ui-ux")
+    expect(agents.sisyphus.prompt).toContain("git-master")
+  })
+
+  test("includes custom agents in orchestrator prompts when provided via config", async () => {
+    // #given
+    const fetchSpy = spyOn(shared, "fetchAvailableModels").mockResolvedValue(
+      new Set([
+        "anthropic/claude-opus-4-6",
+        "kimi-for-coding/k2p5",
+        "opencode/kimi-k2.5-free",
+        "zai-coding-plan/glm-4.7",
+        "opencode/glm-4.7-free",
+        "openai/gpt-5.2",
+      ])
+    )
+
+    const customAgentSummaries = [
+      {
+        name: "researcher",
+        description: "Research agent for deep analysis",
+        hidden: false,
+      },
+    ]
+
+    try {
+      // #when
+      const agents = await createBuiltinAgents(
+        [],
+        {},
+        undefined,
+        TEST_DEFAULT_MODEL,
+        undefined,
+        undefined,
+        [],
+        customAgentSummaries
+      )
+
+      // #then
+      expect(agents.sisyphus.prompt).toContain("researcher")
+      expect(agents.hephaestus.prompt).toContain("researcher")
+      expect(agents.atlas.prompt).toContain("researcher")
+    } finally {
+      fetchSpy.mockRestore()
+    }
+  })
+
+  test("excludes hidden custom agents from orchestrator prompts", async () => {
+    // #given
+    const fetchSpy = spyOn(shared, "fetchAvailableModels").mockResolvedValue(
+      new Set(["anthropic/claude-opus-4-6", "openai/gpt-5.2"])
+    )
+
+    const customAgentSummaries = [
+      {
+        name: "hidden-agent",
+        description: "Should never show",
+        hidden: true,
+      },
+    ]
+
+    try {
+      // #when
+      const agents = await createBuiltinAgents(
+        [],
+        {},
+        undefined,
+        TEST_DEFAULT_MODEL,
+        undefined,
+        undefined,
+        [],
+        customAgentSummaries
+      )
+
+      // #then
+      expect(agents.sisyphus.prompt).not.toContain("hidden-agent")
+      expect(agents.hephaestus.prompt).not.toContain("hidden-agent")
+      expect(agents.atlas.prompt).not.toContain("hidden-agent")
+    } finally {
+      fetchSpy.mockRestore()
+    }
+  })
+
+  test("excludes disabled custom agents from orchestrator prompts", async () => {
+    // #given
+    const fetchSpy = spyOn(shared, "fetchAvailableModels").mockResolvedValue(
+      new Set(["anthropic/claude-opus-4-6", "openai/gpt-5.2"])
+    )
+
+    const customAgentSummaries = [
+      {
+        name: "disabled-agent",
+        description: "Should never show",
+        disabled: true,
+      },
+    ]
+
+    try {
+      // #when
+      const agents = await createBuiltinAgents(
+        [],
+        {},
+        undefined,
+        TEST_DEFAULT_MODEL,
+        undefined,
+        undefined,
+        [],
+        customAgentSummaries
+      )
+
+      // #then
+      expect(agents.sisyphus.prompt).not.toContain("disabled-agent")
+      expect(agents.hephaestus.prompt).not.toContain("disabled-agent")
+      expect(agents.atlas.prompt).not.toContain("disabled-agent")
+    } finally {
+      fetchSpy.mockRestore()
+    }
+  })
+
+  test("excludes custom agents when disabledAgents contains their name (case-insensitive)", async () => {
+    // #given
+    const fetchSpy = spyOn(shared, "fetchAvailableModels").mockResolvedValue(
+      new Set(["anthropic/claude-opus-4-6", "openai/gpt-5.2"])
+    )
+
+    const disabledAgents = ["ReSeArChEr"]
+    const customAgentSummaries = [
+      {
+        name: "researcher",
+        description: "Should never show",
+      },
+    ]
+
+    try {
+      // #when
+      const agents = await createBuiltinAgents(
+        disabledAgents,
+        {},
+        undefined,
+        TEST_DEFAULT_MODEL,
+        undefined,
+        undefined,
+        [],
+        customAgentSummaries
+      )
+
+      // #then
+      expect(agents.sisyphus.prompt).not.toContain("researcher")
+      expect(agents.hephaestus.prompt).not.toContain("researcher")
+      expect(agents.atlas.prompt).not.toContain("researcher")
+    } finally {
+      fetchSpy.mockRestore()
+    }
+  })
+
+  test("deduplicates custom agents case-insensitively", async () => {
+    // #given
+    const fetchSpy = spyOn(shared, "fetchAvailableModels").mockResolvedValue(
+      new Set(["anthropic/claude-opus-4-6", "openai/gpt-5.2"])
+    )
+
+    const customAgentSummaries = [
+      { name: "Researcher", description: "First" },
+      { name: "researcher", description: "Second" },
+    ]
+
+    try {
+      // #when
+      const agents = await createBuiltinAgents(
+        [],
+        {},
+        undefined,
+        TEST_DEFAULT_MODEL,
+        undefined,
+        undefined,
+        [],
+        customAgentSummaries
+      )
+
+      // #then
+      const matches = (agents.sisyphus?.prompt ?? "").match(/Custom agent: researcher/gi) ?? []
+      expect(matches.length).toBe(1)
+    } finally {
+      fetchSpy.mockRestore()
+    }
+  })
+
+  test("sanitizes custom agent strings for markdown tables", async () => {
+    // #given
+    const fetchSpy = spyOn(shared, "fetchAvailableModels").mockResolvedValue(
+      new Set(["anthropic/claude-opus-4-6", "openai/gpt-5.2"])
+    )
+
+    const customAgentSummaries = [
+      {
+        name: "table-agent",
+        description: "Line1\nAlpha | Beta",
+      },
+    ]
+
+    try {
+      // #when
+      const agents = await createBuiltinAgents(
+        [],
+        {},
+        undefined,
+        TEST_DEFAULT_MODEL,
+        undefined,
+        undefined,
+        [],
+        customAgentSummaries
+      )
+
+      // #then
+      expect(agents.sisyphus.prompt).toContain("Line1 Alpha \\| Beta")
+    } finally {
+      fetchSpy.mockRestore()
+    }
+  })
 })
 
 describe("createBuiltinAgents without systemDefaultModel", () => {
@@ -205,7 +502,7 @@ describe("createBuiltinAgents without systemDefaultModel", () => {
     ])
     const fetchSpy = spyOn(shared, "fetchAvailableModels").mockResolvedValue(
       new Set([
-        "anthropic/claude-opus-4-5",
+        "anthropic/claude-opus-4-6",
         "kimi-for-coding/k2p5",
         "opencode/kimi-k2.5-free",
         "zai-coding-plan/glm-4.7",
@@ -219,7 +516,7 @@ describe("createBuiltinAgents without systemDefaultModel", () => {
 
       // #then
       expect(agents.sisyphus).toBeDefined()
-      expect(agents.sisyphus.model).toBe("anthropic/claude-opus-4-5")
+      expect(agents.sisyphus.model).toBe("anthropic/claude-opus-4-6")
     } finally {
       cacheSpy.mockRestore()
       fetchSpy.mockRestore()
@@ -227,12 +524,41 @@ describe("createBuiltinAgents without systemDefaultModel", () => {
   })
 })
 
-describe("createBuiltinAgents with requiresModel gating", () => {
-  test("hephaestus is not created when gpt-5.2-codex is unavailable", async () => {
+describe("createBuiltinAgents with requiresProvider gating (hephaestus)", () => {
+  test("hephaestus is created when provider-models cache connected list includes required provider", async () => {
     // #given
+    const connectedCacheSpy = spyOn(connectedProvidersCache, "readConnectedProvidersCache").mockReturnValue(["anthropic"])
+    const providerModelsSpy = spyOn(connectedProvidersCache, "readProviderModelsCache").mockReturnValue({
+      connected: ["openai"],
+      models: {},
+      updatedAt: new Date().toISOString(),
+    })
+    const fetchSpy = spyOn(shared, "fetchAvailableModels").mockImplementation(async (_, options) => {
+      const providers = options?.connectedProviders ?? []
+      return providers.includes("openai")
+        ? new Set(["openai/gpt-5.3-codex"])
+        : new Set(["anthropic/claude-opus-4-6"])
+    })
+
+    try {
+      // #when
+      const agents = await createBuiltinAgents([], {}, undefined, TEST_DEFAULT_MODEL, undefined, undefined, [], {})
+
+      // #then
+      expect(agents.hephaestus).toBeDefined()
+    } finally {
+      connectedCacheSpy.mockRestore()
+      providerModelsSpy.mockRestore()
+      fetchSpy.mockRestore()
+    }
+  })
+
+  test("hephaestus is not created when no required provider is connected", async () => {
+    // #given - only anthropic models available, not in hephaestus requiresProvider
     const fetchSpy = spyOn(shared, "fetchAvailableModels").mockResolvedValue(
-      new Set(["anthropic/claude-opus-4-5"])
+      new Set(["anthropic/claude-opus-4-6"])
     )
+    const cacheSpy = spyOn(connectedProvidersCache, "readConnectedProvidersCache").mockReturnValue(["anthropic"])
 
     try {
       // #when
@@ -242,13 +568,48 @@ describe("createBuiltinAgents with requiresModel gating", () => {
       expect(agents.hephaestus).toBeUndefined()
     } finally {
       fetchSpy.mockRestore()
+      cacheSpy.mockRestore()
     }
   })
 
-  test("hephaestus is created when gpt-5.2-codex is available", async () => {
-    // #given
+  test("hephaestus is created when openai provider is connected", async () => {
+    // #given - openai provider has models available
     const fetchSpy = spyOn(shared, "fetchAvailableModels").mockResolvedValue(
-      new Set(["openai/gpt-5.2-codex"])
+      new Set(["openai/gpt-5.3-codex"])
+    )
+
+    try {
+      // #when
+      const agents = await createBuiltinAgents([], {}, undefined, TEST_DEFAULT_MODEL, undefined, undefined, [], {})
+
+      // #then
+      expect(agents.hephaestus).toBeDefined()
+    } finally {
+      fetchSpy.mockRestore()
+    }
+  })
+
+  test("hephaestus is created when github-copilot provider is connected", async () => {
+    // #given - github-copilot provider has models available
+    const fetchSpy = spyOn(shared, "fetchAvailableModels").mockResolvedValue(
+      new Set(["github-copilot/gpt-5.3-codex"])
+    )
+
+    try {
+      // #when
+      const agents = await createBuiltinAgents([], {}, undefined, TEST_DEFAULT_MODEL, undefined, undefined, [], {})
+
+      // #then
+      expect(agents.hephaestus).toBeDefined()
+    } finally {
+      fetchSpy.mockRestore()
+    }
+  })
+
+  test("hephaestus is created when opencode provider is connected", async () => {
+    // #given - opencode provider has models available
+    const fetchSpy = spyOn(shared, "fetchAvailableModels").mockResolvedValue(
+      new Set(["opencode/gpt-5.3-codex"])
     )
 
     try {
@@ -273,20 +634,20 @@ describe("createBuiltinAgents with requiresModel gating", () => {
 
       // #then
       expect(agents.hephaestus).toBeDefined()
-      expect(agents.hephaestus.model).toBe("openai/gpt-5.2-codex")
+      expect(agents.hephaestus.model).toBe("openai/gpt-5.3-codex")
     } finally {
       cacheSpy.mockRestore()
       fetchSpy.mockRestore()
     }
   })
 
-  test("hephaestus is created when explicit config provided even if model unavailable", async () => {
+  test("hephaestus is created when explicit config provided even if provider unavailable", async () => {
     // #given
     const fetchSpy = spyOn(shared, "fetchAvailableModels").mockResolvedValue(
-      new Set(["anthropic/claude-opus-4-5"])
+      new Set(["anthropic/claude-opus-4-6"])
     )
     const overrides = {
-      hephaestus: { model: "anthropic/claude-opus-4-5" },
+      hephaestus: { model: "anthropic/claude-opus-4-6" },
     }
 
     try {
@@ -305,7 +666,7 @@ describe("createBuiltinAgents with requiresAnyModel gating (sisyphus)", () => {
   test("sisyphus is created when at least one fallback model is available", async () => {
     // #given
     const fetchSpy = spyOn(shared, "fetchAvailableModels").mockResolvedValue(
-      new Set(["anthropic/claude-opus-4-5"])
+      new Set(["anthropic/claude-opus-4-6"])
     )
 
     try {
@@ -330,7 +691,7 @@ describe("createBuiltinAgents with requiresAnyModel gating (sisyphus)", () => {
 
       // #then
       expect(agents.sisyphus).toBeDefined()
-      expect(agents.sisyphus.model).toBe("anthropic/claude-opus-4-5")
+      expect(agents.sisyphus.model).toBe("anthropic/claude-opus-4-6")
     } finally {
       cacheSpy.mockRestore()
       fetchSpy.mockRestore()
@@ -341,7 +702,7 @@ describe("createBuiltinAgents with requiresAnyModel gating (sisyphus)", () => {
     // #given
     const fetchSpy = spyOn(shared, "fetchAvailableModels").mockResolvedValue(new Set())
     const overrides = {
-      sisyphus: { model: "anthropic/claude-opus-4-5" },
+      sisyphus: { model: "anthropic/claude-opus-4-6" },
     }
 
     try {
@@ -355,11 +716,12 @@ describe("createBuiltinAgents with requiresAnyModel gating (sisyphus)", () => {
     }
   })
 
-  test("sisyphus is not created when no fallback model is available (unrelated model only)", async () => {
+  test("sisyphus is not created when no fallback model is available and provider not connected", async () => {
     // #given - only openai/gpt-5.2 available, not in sisyphus fallback chain
     const fetchSpy = spyOn(shared, "fetchAvailableModels").mockResolvedValue(
       new Set(["openai/gpt-5.2"])
     )
+    const cacheSpy = spyOn(connectedProvidersCache, "readConnectedProvidersCache").mockReturnValue([])
 
     try {
       // #when
@@ -369,13 +731,66 @@ describe("createBuiltinAgents with requiresAnyModel gating (sisyphus)", () => {
       expect(agents.sisyphus).toBeUndefined()
     } finally {
       fetchSpy.mockRestore()
+      cacheSpy.mockRestore()
+    }
+  })
+
+  test("sisyphus uses user-configured plugin model even when not in cache or fallback chain", async () => {
+    // #given - user configures a model from a plugin provider (like antigravity)
+    // that is NOT in the availableModels cache and NOT in the fallback chain
+    const fetchSpy = spyOn(shared, "fetchAvailableModels").mockResolvedValue(
+      new Set(["openai/gpt-5.2"])
+    )
+    const cacheSpy = spyOn(connectedProvidersCache, "readConnectedProvidersCache").mockReturnValue(
+      ["openai"]
+    )
+    const overrides = {
+      sisyphus: { model: "google/antigravity-claude-opus-4-5-thinking" },
+    }
+
+    try {
+      // #when
+      const agents = await createBuiltinAgents([], overrides, undefined, TEST_DEFAULT_MODEL, undefined, undefined, [], {})
+
+      // #then
+      expect(agents.sisyphus).toBeDefined()
+      expect(agents.sisyphus.model).toBe("google/antigravity-claude-opus-4-5-thinking")
+    } finally {
+      fetchSpy.mockRestore()
+      cacheSpy.mockRestore()
+    }
+  })
+
+  test("sisyphus uses user-configured plugin model when availableModels is empty but cache exists", async () => {
+    // #given - connected providers cache exists but models cache is empty
+    // This reproduces the exact scenario where provider-models.json has models: {}
+    const fetchSpy = spyOn(shared, "fetchAvailableModels").mockResolvedValue(
+      new Set()
+    )
+    const cacheSpy = spyOn(connectedProvidersCache, "readConnectedProvidersCache").mockReturnValue(
+      ["google", "openai", "opencode"]
+    )
+    const overrides = {
+      sisyphus: { model: "google/antigravity-claude-opus-4-5-thinking" },
+    }
+
+    try {
+      // #when
+      const agents = await createBuiltinAgents([], overrides, undefined, TEST_DEFAULT_MODEL, undefined, undefined, [], {})
+
+      // #then
+      expect(agents.sisyphus).toBeDefined()
+      expect(agents.sisyphus.model).toBe("google/antigravity-claude-opus-4-5-thinking")
+    } finally {
+      fetchSpy.mockRestore()
+      cacheSpy.mockRestore()
     }
   })
 })
 
 describe("buildAgent with category and skills", () => {
-  const { buildAgent } = require("./utils")
-  const TEST_MODEL = "anthropic/claude-opus-4-5"
+  const { buildAgent } = require("./agent-builder")
+  const TEST_MODEL = "anthropic/claude-opus-4-6"
 
   beforeEach(() => {
     clearSkillCache()
@@ -521,7 +936,7 @@ describe("buildAgent with category and skills", () => {
     const agent = buildAgent(source["test-agent"], TEST_MODEL)
 
     // #then - category's built-in model and skills are applied
-    expect(agent.model).toBe("openai/gpt-5.2-codex")
+    expect(agent.model).toBe("openai/gpt-5.3-codex")
     expect(agent.variant).toBe("xhigh")
     expect(agent.prompt).toContain("Role: Designer-Turned-Developer")
     expect(agent.prompt).toContain("Task description")
@@ -634,9 +1049,9 @@ describe("override.category expansion in createBuiltinAgents", () => {
     // #when
     const agents = await createBuiltinAgents([], overrides, undefined, TEST_DEFAULT_MODEL)
 
-    // #then - ultrabrain category: model=openai/gpt-5.2-codex, variant=xhigh
+    // #then - ultrabrain category: model=openai/gpt-5.3-codex, variant=xhigh
     expect(agents.oracle).toBeDefined()
-    expect(agents.oracle.model).toBe("openai/gpt-5.2-codex")
+    expect(agents.oracle.model).toBe("openai/gpt-5.3-codex")
     expect(agents.oracle.variant).toBe("xhigh")
   })
 
@@ -703,9 +1118,9 @@ describe("override.category expansion in createBuiltinAgents", () => {
     // #when
     const agents = await createBuiltinAgents([], overrides, undefined, TEST_DEFAULT_MODEL)
 
-    // #then - ultrabrain category: model=openai/gpt-5.2-codex, variant=xhigh
+    // #then - ultrabrain category: model=openai/gpt-5.3-codex, variant=xhigh
     expect(agents.sisyphus).toBeDefined()
-    expect(agents.sisyphus.model).toBe("openai/gpt-5.2-codex")
+    expect(agents.sisyphus.model).toBe("openai/gpt-5.3-codex")
     expect(agents.sisyphus.variant).toBe("xhigh")
   })
 
@@ -718,9 +1133,9 @@ describe("override.category expansion in createBuiltinAgents", () => {
     // #when
     const agents = await createBuiltinAgents([], overrides, undefined, TEST_DEFAULT_MODEL)
 
-    // #then - ultrabrain category: model=openai/gpt-5.2-codex, variant=xhigh
+    // #then - ultrabrain category: model=openai/gpt-5.3-codex, variant=xhigh
     expect(agents.atlas).toBeDefined()
-    expect(agents.atlas.model).toBe("openai/gpt-5.2-codex")
+    expect(agents.atlas.model).toBe("openai/gpt-5.3-codex")
     expect(agents.atlas.variant).toBe("xhigh")
   })
 
@@ -740,6 +1155,52 @@ describe("override.category expansion in createBuiltinAgents", () => {
   })
 })
 
+describe("agent override tools migration", () => {
+  test("tools: { x: false } is migrated to permission: { x: deny }", async () => {
+    // #given
+    const overrides = {
+      explore: { tools: { "jetbrains_*": false } } as any,
+    }
+
+    // #when
+    const agents = await createBuiltinAgents([], overrides, undefined, TEST_DEFAULT_MODEL)
+
+    // #then
+    expect(agents.explore).toBeDefined()
+    const permission = agents.explore.permission as Record<string, string>
+    expect(permission["jetbrains_*"]).toBe("deny")
+  })
+
+  test("tools: { x: true } is migrated to permission: { x: allow }", async () => {
+    // #given
+    const overrides = {
+      librarian: { tools: { "jetbrains_get_*": true } } as any,
+    }
+
+    // #when
+    const agents = await createBuiltinAgents([], overrides, undefined, TEST_DEFAULT_MODEL)
+
+    // #then
+    expect(agents.librarian).toBeDefined()
+    const permission = agents.librarian.permission as Record<string, string>
+    expect(permission["jetbrains_get_*"]).toBe("allow")
+  })
+
+  test("tools config is removed after migration", async () => {
+    // #given
+    const overrides = {
+      explore: { tools: { "some_tool": false } } as any,
+    }
+
+    // #when
+    const agents = await createBuiltinAgents([], overrides, undefined, TEST_DEFAULT_MODEL)
+
+    // #then
+    expect(agents.explore).toBeDefined()
+    expect((agents.explore as any).tools).toBeUndefined()
+  })
+})
+
 describe("Deadlock prevention - fetchAvailableModels must not receive client", () => {
    test("createBuiltinAgents should call fetchAvailableModels with undefined client to prevent deadlock", async () => {
      // #given - This test ensures we don't regress on issue #1301
@@ -776,4 +1237,29 @@ describe("Deadlock prevention - fetchAvailableModels must not receive client", (
      fetchSpy.mockRestore?.()
      cacheSpy.mockRestore?.()
    })
+  test("Hephaestus variant override respects user config over hardcoded default", async () => {
+    // #given - user provides variant in config
+    const overrides = {
+      hephaestus: { variant: "high" },
+    }
+
+    // #when
+    const agents = await createBuiltinAgents([], overrides, undefined, TEST_DEFAULT_MODEL)
+
+    // #then - user variant takes precedence over hardcoded "medium"
+    expect(agents.hephaestus).toBeDefined()
+    expect(agents.hephaestus.variant).toBe("high")
+  })
+
+  test("Hephaestus uses default variant when no user override provided", async () => {
+    // #given - no variant override in config
+    const overrides = {}
+
+    // #when
+    const agents = await createBuiltinAgents([], overrides, undefined, TEST_DEFAULT_MODEL)
+
+    // #then - default "medium" variant is applied
+    expect(agents.hephaestus).toBeDefined()
+    expect(agents.hephaestus.variant).toBe("medium")
+  })
 })

src/agents/utils.ts

@@ -1,482 +0,0 @@
-import type { AgentConfig } from "@opencode-ai/sdk"
-import type { BuiltinAgentName, AgentOverrideConfig, AgentOverrides, AgentFactory, AgentPromptMetadata } from "./types"
-import type { CategoriesConfig, CategoryConfig, GitMasterConfig } from "../config/schema"
-import { createSisyphusAgent } from "./sisyphus"
-import { createOracleAgent, ORACLE_PROMPT_METADATA } from "./oracle"
-import { createLibrarianAgent, LIBRARIAN_PROMPT_METADATA } from "./librarian"
-import { createExploreAgent, EXPLORE_PROMPT_METADATA } from "./explore"
-import { createMultimodalLookerAgent, MULTIMODAL_LOOKER_PROMPT_METADATA } from "./multimodal-looker"
-import { createMetisAgent, metisPromptMetadata } from "./metis"
-import { createAtlasAgent, atlasPromptMetadata } from "./atlas"
-import { createMomusAgent, momusPromptMetadata } from "./momus"
-import { createHephaestusAgent } from "./hephaestus"
-import type { AvailableAgent, AvailableCategory, AvailableSkill } from "./dynamic-agent-prompt-builder"
-import { deepMerge, fetchAvailableModels, resolveModelPipeline, AGENT_MODEL_REQUIREMENTS, readConnectedProvidersCache, isModelAvailable, isAnyFallbackModelAvailable } from "../shared"
-import { DEFAULT_CATEGORIES, CATEGORY_DESCRIPTIONS } from "../tools/delegate-task/constants"
-import { resolveMultipleSkills } from "../features/opencode-skill-loader/skill-content"
-import { createBuiltinSkills } from "../features/builtin-skills"
-import type { LoadedSkill, SkillScope } from "../features/opencode-skill-loader/types"
-import type { BrowserAutomationProvider } from "../config/schema"
-
-type AgentSource = AgentFactory | AgentConfig
-
-const agentSources: Record<BuiltinAgentName, AgentSource> = {
-  sisyphus: createSisyphusAgent,
-  hephaestus: createHephaestusAgent,
-  oracle: createOracleAgent,
-  librarian: createLibrarianAgent,
-  explore: createExploreAgent,
-  "multimodal-looker": createMultimodalLookerAgent,
-  metis: createMetisAgent,
-  momus: createMomusAgent,
-  // Note: Atlas is handled specially in createBuiltinAgents()
-  // because it needs OrchestratorContext, not just a model string
-  atlas: createAtlasAgent as unknown as AgentFactory,
-}
-
-/**
- * Metadata for each agent, used to build Sisyphus's dynamic prompt sections
- * (Delegation Table, Tool Selection, Key Triggers, etc.)
- */
-const agentMetadata: Partial<Record<BuiltinAgentName, AgentPromptMetadata>> = {
-  oracle: ORACLE_PROMPT_METADATA,
-  librarian: LIBRARIAN_PROMPT_METADATA,
-  explore: EXPLORE_PROMPT_METADATA,
-  "multimodal-looker": MULTIMODAL_LOOKER_PROMPT_METADATA,
-  metis: metisPromptMetadata,
-  momus: momusPromptMetadata,
-  atlas: atlasPromptMetadata,
-}
-
-function isFactory(source: AgentSource): source is AgentFactory {
-  return typeof source === "function"
-}
-
-export function buildAgent(
-  source: AgentSource,
-  model: string,
-  categories?: CategoriesConfig,
-  gitMasterConfig?: GitMasterConfig,
-  browserProvider?: BrowserAutomationProvider
-): AgentConfig {
-  const base = isFactory(source) ? source(model) : source
-  const categoryConfigs: Record<string, CategoryConfig> = categories
-    ? { ...DEFAULT_CATEGORIES, ...categories }
-    : DEFAULT_CATEGORIES
-
-  const agentWithCategory = base as AgentConfig & { category?: string; skills?: string[]; variant?: string }
-  if (agentWithCategory.category) {
-    const categoryConfig = categoryConfigs[agentWithCategory.category]
-    if (categoryConfig) {
-      if (!base.model) {
-        base.model = categoryConfig.model
-      }
-      if (base.temperature === undefined && categoryConfig.temperature !== undefined) {
-        base.temperature = categoryConfig.temperature
-      }
-      if (base.variant === undefined && categoryConfig.variant !== undefined) {
-        base.variant = categoryConfig.variant
-      }
-    }
-  }
-
-  if (agentWithCategory.skills?.length) {
-    const { resolved } = resolveMultipleSkills(agentWithCategory.skills, { gitMasterConfig, browserProvider })
-    if (resolved.size > 0) {
-      const skillContent = Array.from(resolved.values()).join("\n\n")
-      base.prompt = skillContent + (base.prompt ? "\n\n" + base.prompt : "")
-    }
-  }
-
-  return base
-}
-
-/**
- * Creates OmO-specific environment context (time, timezone, locale).
- * Note: Working directory, platform, and date are already provided by OpenCode's system.ts,
- * so we only include fields that OpenCode doesn't provide to avoid duplication.
- * See: https://github.com/code-yeongyu/oh-my-opencode/issues/379
- */
-export function createEnvContext(): string {
-  const now = new Date()
-  const timezone = Intl.DateTimeFormat().resolvedOptions().timeZone
-  const locale = Intl.DateTimeFormat().resolvedOptions().locale
-
-  const dateStr = now.toLocaleDateString(locale, {
-    weekday: "short",
-    year: "numeric",
-    month: "short",
-    day: "numeric",
-  })
-
-  const timeStr = now.toLocaleTimeString(locale, {
-    hour: "2-digit",
-    minute: "2-digit",
-    second: "2-digit",
-    hour12: true,
-  })
-
-  return `
-<omo-env>
-  Current date: ${dateStr}
-  Current time: ${timeStr}
-  Timezone: ${timezone}
-  Locale: ${locale}
-</omo-env>`
-}
-
-/**
- * Expands a category reference from an agent override into concrete config properties.
- * Category properties are applied unconditionally (overwriting factory defaults),
- * because the user's chosen category should take priority over factory base values.
- * Direct override properties applied later via mergeAgentConfig() will supersede these.
- */
-function applyCategoryOverride(
-  config: AgentConfig,
-  categoryName: string,
-  mergedCategories: Record<string, CategoryConfig>
-): AgentConfig {
-  const categoryConfig = mergedCategories[categoryName]
-  if (!categoryConfig) return config
-
-  const result = { ...config } as AgentConfig & Record<string, unknown>
-  if (categoryConfig.model) result.model = categoryConfig.model
-  if (categoryConfig.variant !== undefined) result.variant = categoryConfig.variant
-  if (categoryConfig.temperature !== undefined) result.temperature = categoryConfig.temperature
-  if (categoryConfig.reasoningEffort !== undefined) result.reasoningEffort = categoryConfig.reasoningEffort
-  if (categoryConfig.textVerbosity !== undefined) result.textVerbosity = categoryConfig.textVerbosity
-  if (categoryConfig.thinking !== undefined) result.thinking = categoryConfig.thinking
-  if (categoryConfig.top_p !== undefined) result.top_p = categoryConfig.top_p
-  if (categoryConfig.maxTokens !== undefined) result.maxTokens = categoryConfig.maxTokens
-
-  return result as AgentConfig
-}
-
-function applyModelResolution(input: {
-  uiSelectedModel?: string
-  userModel?: string
-  requirement?: { fallbackChain?: { providers: string[]; model: string; variant?: string }[] }
-  availableModels: Set<string>
-  systemDefaultModel?: string
-}) {
-  const { uiSelectedModel, userModel, requirement, availableModels, systemDefaultModel } = input
-  return resolveModelPipeline({
-    intent: { uiSelectedModel, userModel },
-    constraints: { availableModels },
-    policy: { fallbackChain: requirement?.fallbackChain, systemDefaultModel },
-  })
-}
-
-function getFirstFallbackModel(requirement?: {
-  fallbackChain?: { providers: string[]; model: string; variant?: string }[]
-}) {
-  const entry = requirement?.fallbackChain?.[0]
-  if (!entry || entry.providers.length === 0) return undefined
-  return {
-    model: `${entry.providers[0]}/${entry.model}`,
-    provenance: "provider-fallback" as const,
-    variant: entry.variant,
-  }
-}
-
-function applyEnvironmentContext(config: AgentConfig, directory?: string): AgentConfig {
-  if (!directory || !config.prompt) return config
-  const envContext = createEnvContext()
-  return { ...config, prompt: config.prompt + envContext }
-}
-
-function applyOverrides(
-  config: AgentConfig,
-  override: AgentOverrideConfig | undefined,
-  mergedCategories: Record<string, CategoryConfig>
-): AgentConfig {
-  let result = config
-  const overrideCategory = (override as Record<string, unknown> | undefined)?.category as string | undefined
-  if (overrideCategory) {
-    result = applyCategoryOverride(result, overrideCategory, mergedCategories)
-  }
-
-  if (override) {
-    result = mergeAgentConfig(result, override)
-  }
-
-  return result
-}
-
-function mergeAgentConfig(
-  base: AgentConfig,
-  override: AgentOverrideConfig
-): AgentConfig {
-  const { prompt_append, ...rest } = override
-  const merged = deepMerge(base, rest as Partial<AgentConfig>)
-
-  if (prompt_append && merged.prompt) {
-    merged.prompt = merged.prompt + "\n" + prompt_append
-  }
-
-  return merged
-}
-
-function mapScopeToLocation(scope: SkillScope): AvailableSkill["location"] {
-  if (scope === "user" || scope === "opencode") return "user"
-  if (scope === "project" || scope === "opencode-project") return "project"
-  return "plugin"
-}
-
-export async function createBuiltinAgents(
-  disabledAgents: string[] = [],
-  agentOverrides: AgentOverrides = {},
-  directory?: string,
-  systemDefaultModel?: string,
-  categories?: CategoriesConfig,
-  gitMasterConfig?: GitMasterConfig,
-  discoveredSkills: LoadedSkill[] = [],
-  client?: any,
-  browserProvider?: BrowserAutomationProvider,
-  uiSelectedModel?: string
-): Promise<Record<string, AgentConfig>> {
-  const connectedProviders = readConnectedProvidersCache()
-  // IMPORTANT: Do NOT pass client to fetchAvailableModels during plugin initialization.
-  // This function is called from config handler, and calling client API causes deadlock.
-  // See: https://github.com/code-yeongyu/oh-my-opencode/issues/1301
-  const availableModels = await fetchAvailableModels(undefined, {
-    connectedProviders: connectedProviders ?? undefined,
-  })
-  const isFirstRunNoCache =
-    availableModels.size === 0 && (!connectedProviders || connectedProviders.length === 0)
-
-  const result: Record<string, AgentConfig> = {}
-  const availableAgents: AvailableAgent[] = []
-
-  const mergedCategories = categories
-    ? { ...DEFAULT_CATEGORIES, ...categories }
-    : DEFAULT_CATEGORIES
-
-  const availableCategories: AvailableCategory[] = Object.entries(mergedCategories).map(([name]) => ({
-    name,
-    description: categories?.[name]?.description ?? CATEGORY_DESCRIPTIONS[name] ?? "General tasks",
-  }))
-
-  const builtinSkills = createBuiltinSkills({ browserProvider })
-  const builtinSkillNames = new Set(builtinSkills.map(s => s.name))
-
-  const builtinAvailable: AvailableSkill[] = builtinSkills.map((skill) => ({
-    name: skill.name,
-    description: skill.description,
-    location: "plugin" as const,
-  }))
-
-  const discoveredAvailable: AvailableSkill[] = discoveredSkills
-    .filter(s => !builtinSkillNames.has(s.name))
-    .map((skill) => ({
-      name: skill.name,
-      description: skill.definition.description ?? "",
-      location: mapScopeToLocation(skill.scope),
-    }))
-
-  const availableSkills: AvailableSkill[] = [...builtinAvailable, ...discoveredAvailable]
-
-  // Collect general agents first (for availableAgents), but don't add to result yet
-  const pendingAgentConfigs: Map<string, AgentConfig> = new Map()
-
-   for (const [name, source] of Object.entries(agentSources)) {
-     const agentName = name as BuiltinAgentName
-
-     if (agentName === "sisyphus") continue
-     if (agentName === "hephaestus") continue
-     if (agentName === "atlas") continue
-     if (disabledAgents.some((name) => name.toLowerCase() === agentName.toLowerCase())) continue
-
-     const override = agentOverrides[agentName]
-       ?? Object.entries(agentOverrides).find(([key]) => key.toLowerCase() === agentName.toLowerCase())?.[1]
-     const requirement = AGENT_MODEL_REQUIREMENTS[agentName]
-     
-     // Check if agent requires a specific model
-     if (requirement?.requiresModel && availableModels) {
-       if (!isModelAvailable(requirement.requiresModel, availableModels)) {
-         continue
-       }
-     }
-     
-     const isPrimaryAgent = isFactory(source) && source.mode === "primary"
-     
-    const resolution = applyModelResolution({
-      uiSelectedModel: isPrimaryAgent ? uiSelectedModel : undefined,
-      userModel: override?.model,
-      requirement,
-      availableModels,
-      systemDefaultModel,
-    })
-    if (!resolution) continue
-    const { model, variant: resolvedVariant } = resolution
-
-    let config = buildAgent(source, model, mergedCategories, gitMasterConfig, browserProvider)
-    
-    // Apply resolved variant from model fallback chain
-    if (resolvedVariant) {
-      config = { ...config, variant: resolvedVariant }
-    }
-
-    // Expand override.category into concrete properties (higher priority than factory/resolved)
-    const overrideCategory = (override as Record<string, unknown> | undefined)?.category as string | undefined
-    if (overrideCategory) {
-      config = applyCategoryOverride(config, overrideCategory, mergedCategories)
-    }
-
-    if (agentName === "librarian") {
-      config = applyEnvironmentContext(config, directory)
-    }
-
-    config = applyOverrides(config, override, mergedCategories)
-
-    // Store for later - will be added after sisyphus and hephaestus
-    pendingAgentConfigs.set(name, config)
-
-    const metadata = agentMetadata[agentName]
-    if (metadata) {
-      availableAgents.push({
-        name: agentName,
-        description: config.description ?? "",
-        metadata,
-      })
-    }
-  }
-
-   const sisyphusOverride = agentOverrides["sisyphus"]
-   const sisyphusRequirement = AGENT_MODEL_REQUIREMENTS["sisyphus"]
-   const hasSisyphusExplicitConfig = sisyphusOverride !== undefined
-   const meetsSisyphusAnyModelRequirement =
-     !sisyphusRequirement?.requiresAnyModel ||
-     hasSisyphusExplicitConfig ||
-     isFirstRunNoCache ||
-     isAnyFallbackModelAvailable(sisyphusRequirement.fallbackChain, availableModels)
-
-   if (!disabledAgents.includes("sisyphus") && meetsSisyphusAnyModelRequirement) {
-    let sisyphusResolution = applyModelResolution({
-      uiSelectedModel,
-      userModel: sisyphusOverride?.model,
-      requirement: sisyphusRequirement,
-      availableModels,
-      systemDefaultModel,
-    })
-
-    if (isFirstRunNoCache && !sisyphusOverride?.model && !uiSelectedModel) {
-      sisyphusResolution = getFirstFallbackModel(sisyphusRequirement)
-    }
-
-    if (sisyphusResolution) {
-      const { model: sisyphusModel, variant: sisyphusResolvedVariant } = sisyphusResolution
-
-      let sisyphusConfig = createSisyphusAgent(
-        sisyphusModel,
-        availableAgents,
-        undefined,
-        availableSkills,
-        availableCategories
-      )
-      
-      if (sisyphusResolvedVariant) {
-        sisyphusConfig = { ...sisyphusConfig, variant: sisyphusResolvedVariant }
-      }
-
-      sisyphusConfig = applyOverrides(sisyphusConfig, sisyphusOverride, mergedCategories)
-      sisyphusConfig = applyEnvironmentContext(sisyphusConfig, directory)
-
-      result["sisyphus"] = sisyphusConfig
-    }
-   }
-
-  if (!disabledAgents.includes("hephaestus")) {
-    const hephaestusOverride = agentOverrides["hephaestus"]
-    const hephaestusRequirement = AGENT_MODEL_REQUIREMENTS["hephaestus"]
-    const hasHephaestusExplicitConfig = hephaestusOverride !== undefined
-
-    const hasRequiredModel =
-      !hephaestusRequirement?.requiresModel ||
-      hasHephaestusExplicitConfig ||
-      isFirstRunNoCache ||
-      (availableModels.size > 0 && isModelAvailable(hephaestusRequirement.requiresModel, availableModels))
-
-    if (hasRequiredModel) {
-      let hephaestusResolution = applyModelResolution({
-        userModel: hephaestusOverride?.model,
-        requirement: hephaestusRequirement,
-        availableModels,
-        systemDefaultModel,
-      })
-
-      if (isFirstRunNoCache && !hephaestusOverride?.model) {
-        hephaestusResolution = getFirstFallbackModel(hephaestusRequirement)
-      }
-
-      if (hephaestusResolution) {
-        const { model: hephaestusModel, variant: hephaestusResolvedVariant } = hephaestusResolution
-
-        let hephaestusConfig = createHephaestusAgent(
-          hephaestusModel,
-          availableAgents,
-          undefined,
-          availableSkills,
-          availableCategories
-        )
-        
-        hephaestusConfig = { ...hephaestusConfig, variant: hephaestusResolvedVariant ?? "medium" }
-
-        const hepOverrideCategory = (hephaestusOverride as Record<string, unknown> | undefined)?.category as string | undefined
-        if (hepOverrideCategory) {
-          hephaestusConfig = applyCategoryOverride(hephaestusConfig, hepOverrideCategory, mergedCategories)
-        }
-
-        if (directory && hephaestusConfig.prompt) {
-          const envContext = createEnvContext()
-          hephaestusConfig = { ...hephaestusConfig, prompt: hephaestusConfig.prompt + envContext }
-        }
-
-        if (hephaestusOverride) {
-          hephaestusConfig = mergeAgentConfig(hephaestusConfig, hephaestusOverride)
-        }
-
-        result["hephaestus"] = hephaestusConfig
-      }
-    }
-   }
-
-   // Add pending agents after sisyphus and hephaestus to maintain order
-   for (const [name, config] of pendingAgentConfigs) {
-     result[name] = config
-   }
-
-    if (!disabledAgents.includes("atlas")) {
-      const orchestratorOverride = agentOverrides["atlas"]
-      const atlasRequirement = AGENT_MODEL_REQUIREMENTS["atlas"]
-
-      const atlasResolution = applyModelResolution({
-        uiSelectedModel,
-        userModel: orchestratorOverride?.model,
-        requirement: atlasRequirement,
-        availableModels,
-        systemDefaultModel,
-      })
-    
-    if (atlasResolution) {
-      const { model: atlasModel, variant: atlasResolvedVariant } = atlasResolution
-
-      let orchestratorConfig = createAtlasAgent({
-        model: atlasModel,
-        availableAgents,
-        availableSkills,
-        userCategories: categories,
-      })
-      
-      if (atlasResolvedVariant) {
-        orchestratorConfig = { ...orchestratorConfig, variant: atlasResolvedVariant }
-      }
-
-      orchestratorConfig = applyOverrides(orchestratorConfig, orchestratorOverride, mergedCategories)
-
-      result["atlas"] = orchestratorConfig
-    }
-   }
-
-   return result
- }

src/cli/AGENTS.md

@@ -2,77 +2,68 @@
 
 ## OVERVIEW
 
-CLI entry: `bunx oh-my-opencode`. 4 commands with Commander.js + @clack/prompts TUI.
-
-**Commands**: install (interactive setup), doctor (14 health checks), run (session launcher), get-local-version
+CLI entry: `bunx oh-my-opencode`. 107+ files with Commander.js + @clack/prompts TUI. 5 commands: install, run, doctor, get-local-version, mcp-oauth.
 
 ## STRUCTURE
-
 ```
 cli/
-├── index.ts              # Commander.js entry (4 commands)
-├── install.ts            # Interactive TUI (542 lines)
-├── config-manager.ts     # JSONC parsing (667 lines)
-├── types.ts              # InstallArgs, InstallConfig
-├── model-fallback.ts     # Model fallback configuration
-├── doctor/
-│   ├── index.ts          # Doctor entry
-│   ├── runner.ts         # Check orchestration
-│   ├── formatter.ts      # Colored output
-│   ├── constants.ts      # Check IDs, symbols
-│   ├── types.ts          # CheckResult, CheckDefinition (114 lines)
-│   └── checks/           # 14 checks, 23 files
-│       ├── version.ts    # OpenCode + plugin version
-│       ├── config.ts     # JSONC validity, Zod
-│       ├── auth.ts       # Anthropic, OpenAI, Google
-│       ├── dependencies.ts # AST-Grep, Comment Checker
-│       ├── lsp.ts        # LSP connectivity
-│       ├── mcp.ts        # MCP validation
-│       ├── model-resolution.ts # Model resolution check
-│       └── gh.ts         # GitHub CLI
-├── run/
-│   └── index.ts          # Session launcher
-├── mcp-oauth/
-│   └── index.ts          # MCP OAuth flow
-└── get-local-version/
-    └── index.ts          # Version detection
+├── index.ts                 # Entry point (5 lines)
+├── cli-program.ts           # Commander.js program (150+ lines, 5 commands)
+├── install.ts               # TTY routing (TUI or CLI installer)
+├── cli-installer.ts         # Non-interactive installer (164 lines)
+├── tui-installer.ts         # Interactive TUI with @clack/prompts (140 lines)
+├── config-manager/          # 20 config utilities
+│   ├── add-plugin-to-opencode-config.ts  # Plugin registration
+│   ├── add-provider-config.ts            # Provider setup (Google/Antigravity)
+│   ├── detect-current-config.ts          # Installed providers detection
+│   ├── write-omo-config.ts               # JSONC writing
+│   ├── generate-omo-config.ts            # Config generation
+│   ├── jsonc-provider-editor.ts          # JSONC editing
+│   └── ...                               # 14 more utilities
+├── doctor/                  # 4 check categories, 21 check files
+│   ├── runner.ts            # Parallel check execution + result aggregation
+│   ├── formatter.ts         # Colored output (default/status/verbose/JSON)
+│   └── checks/              # system (4), config (1), tools (4), models (6 sub-checks)
+├── run/                     # Session launcher (24 files)
+│   ├── runner.ts            # Run orchestration (126 lines)
+│   ├── agent-resolver.ts    # Agent: flag → env → config → Sisyphus
+│   ├── session-resolver.ts  # Session create or resume with retries
+│   ├── event-handlers.ts    # Event processing (125 lines)
+│   ├── completion.ts        # Completion detection
+│   └── poll-for-completion.ts # Polling with timeout
+├── mcp-oauth/               # OAuth token management (login, logout, status)
+├── get-local-version/       # Version detection + update check
+├── model-fallback.ts        # Model fallback configuration
+└── provider-availability.ts # Provider availability checks
 ```
 
 ## COMMANDS
 
-| Command | Purpose |
-|---------|---------|
-| `install` | Interactive setup with provider selection |
-| `doctor` | 14 health checks for diagnostics |
-| `run` | Launch session with todo enforcement |
-| `get-local-version` | Version detection and update check |
+| Command | Purpose | Key Logic |
+|---------|---------|-----------|
+| `install` | Interactive setup | Provider selection → config generation → plugin registration |
+| `run` | Session launcher | Agent: flag → env → config → Sisyphus. Enforces todo completion. |
+| `doctor` | 4-category health checks | system, config, tools, models (6 sub-checks) |
+| `get-local-version` | Version check | Detects installed, compares with npm latest |
+| `mcp-oauth` | OAuth tokens | login (PKCE flow), logout, status |
 
-## DOCTOR CATEGORIES (14 Checks)
+## RUN SESSION LIFECYCLE
 
-| Category | Checks |
-|----------|--------|
-| installation | opencode, plugin |
-| configuration | config validity, Zod, model-resolution |
-| authentication | anthropic, openai, google |
-| dependencies | ast-grep, comment-checker, gh-cli |
-| tools | LSP, MCP |
-| updates | version comparison |
+1. Load config, resolve agent (CLI > env > config > Sisyphus)
+2. Create server connection (port/attach), setup cleanup/signal handlers
+3. Resolve session (create new or resume with retries)
+4. Send prompt, start event processing, poll for completion
+5. Execute on-complete hook, output JSON if requested, cleanup
 
 ## HOW TO ADD CHECK
 
 1. Create `src/cli/doctor/checks/my-check.ts`
-2. Export `getXXXCheckDefinition()` factory returning `CheckDefinition`
+2. Export `getXXXCheckDefinition()` returning `CheckDefinition`
 3. Add to `getAllCheckDefinitions()` in `checks/index.ts`
 
-## TUI FRAMEWORK
-
-- **@clack/prompts**: `select()`, `spinner()`, `intro()`, `outro()`
-- **picocolors**: Terminal colors for status and headers
-- **Symbols**: ✓ (pass), ✗ (fail), ⚠ (warn), ℹ (info)
-
 ## ANTI-PATTERNS
 
-- **Blocking in non-TTY**: Always check `process.stdout.isTTY`
-- **Direct JSON.parse**: Use `parseJsonc()` from shared utils
-- **Silent failures**: Return `warn` or `fail` in doctor instead of throwing
-- **Hardcoded paths**: Use `getOpenCodeConfigPaths()` from `config-manager.ts`
+- **Blocking in non-TTY**: Check `process.stdout.isTTY`
+- **Direct JSON.parse**: Use `parseJsonc()` from shared
+- **Silent failures**: Return `warn` or `fail` in doctor, don't throw
+- **Hardcoded paths**: Use `getOpenCodeConfigPaths()` from config-manager

src/cli/cli-installer.test.ts

@@ -0,0 +1,83 @@
+import { afterEach, beforeEach, describe, expect, it, mock, spyOn } from "bun:test"
+import * as configManager from "./config-manager"
+import { runCliInstaller } from "./cli-installer"
+import type { InstallArgs } from "./types"
+
+describe("runCliInstaller", () => {
+  const mockConsoleLog = mock(() => {})
+  const mockConsoleError = mock(() => {})
+  const originalConsoleLog = console.log
+  const originalConsoleError = console.error
+
+  beforeEach(() => {
+    console.log = mockConsoleLog
+    console.error = mockConsoleError
+    mockConsoleLog.mockClear()
+    mockConsoleError.mockClear()
+  })
+
+  afterEach(() => {
+    console.log = originalConsoleLog
+    console.error = originalConsoleError
+  })
+
+  it("runs auth and provider setup steps when openai or copilot are enabled without gemini", async () => {
+    //#given
+    const addAuthPluginsSpy = spyOn(configManager, "addAuthPlugins").mockResolvedValue({
+      success: true,
+      configPath: "/tmp/opencode.jsonc",
+    })
+    const addProviderConfigSpy = spyOn(configManager, "addProviderConfig").mockReturnValue({
+      success: true,
+      configPath: "/tmp/opencode.jsonc",
+    })
+    const restoreSpies = [
+      addAuthPluginsSpy,
+      addProviderConfigSpy,
+      spyOn(configManager, "detectCurrentConfig").mockReturnValue({
+        isInstalled: false,
+        hasClaude: false,
+        isMax20: false,
+        hasOpenAI: false,
+        hasGemini: false,
+        hasCopilot: false,
+        hasOpencodeZen: false,
+        hasZaiCodingPlan: false,
+        hasKimiForCoding: false,
+      }),
+      spyOn(configManager, "isOpenCodeInstalled").mockResolvedValue(true),
+      spyOn(configManager, "getOpenCodeVersion").mockResolvedValue("1.0.200"),
+      spyOn(configManager, "addPluginToOpenCodeConfig").mockResolvedValue({
+        success: true,
+        configPath: "/tmp/opencode.jsonc",
+      }),
+      spyOn(configManager, "writeOmoConfig").mockReturnValue({
+        success: true,
+        configPath: "/tmp/oh-my-opencode.jsonc",
+      }),
+    ]
+
+    const args: InstallArgs = {
+      tui: false,
+      claude: "no",
+      openai: "yes",
+      gemini: "no",
+      copilot: "yes",
+      opencodeZen: "no",
+      zaiCodingPlan: "no",
+      kimiForCoding: "no",
+    }
+
+    //#when
+    const result = await runCliInstaller(args, "3.4.0")
+
+    //#then
+    expect(result).toBe(0)
+    expect(addAuthPluginsSpy).toHaveBeenCalledTimes(1)
+    expect(addProviderConfigSpy).toHaveBeenCalledTimes(1)
+
+    for (const spy of restoreSpies) {
+      spy.mockRestore()
+    }
+  })
+})

src/cli/cli-installer.ts

@@ -0,0 +1,166 @@
+import color from "picocolors"
+import type { InstallArgs } from "./types"
+import {
+  addAuthPlugins,
+  addPluginToOpenCodeConfig,
+  addProviderConfig,
+  detectCurrentConfig,
+  getOpenCodeVersion,
+  isOpenCodeInstalled,
+  writeOmoConfig,
+} from "./config-manager"
+import {
+  SYMBOLS,
+  argsToConfig,
+  detectedToInitialValues,
+  formatConfigSummary,
+  printBox,
+  printError,
+  printHeader,
+  printInfo,
+  printStep,
+  printSuccess,
+  printWarning,
+  validateNonTuiArgs,
+} from "./install-validators"
+
+export async function runCliInstaller(args: InstallArgs, version: string): Promise<number> {
+  const validation = validateNonTuiArgs(args)
+  if (!validation.valid) {
+    printHeader(false)
+    printError("Validation failed:")
+    for (const err of validation.errors) {
+      console.log(`  ${SYMBOLS.bullet} ${err}`)
+    }
+    console.log()
+    printInfo(
+      "Usage: bunx oh-my-opencode install --no-tui --claude=<no|yes|max20> --gemini=<no|yes> --copilot=<no|yes>",
+    )
+    console.log()
+    return 1
+  }
+
+  const detected = detectCurrentConfig()
+  const isUpdate = detected.isInstalled
+
+  printHeader(isUpdate)
+
+  const totalSteps = 6
+  let step = 1
+
+  printStep(step++, totalSteps, "Checking OpenCode installation...")
+  const installed = await isOpenCodeInstalled()
+  const openCodeVersion = await getOpenCodeVersion()
+  if (!installed) {
+    printWarning(
+      "OpenCode binary not found. Plugin will be configured, but you'll need to install OpenCode to use it.",
+    )
+    printInfo("Visit https://opencode.ai/docs for installation instructions")
+  } else {
+    printSuccess(`OpenCode ${openCodeVersion ?? ""} detected`)
+  }
+
+  if (isUpdate) {
+    const initial = detectedToInitialValues(detected)
+    printInfo(`Current config: Claude=${initial.claude}, Gemini=${initial.gemini}`)
+  }
+
+  const config = argsToConfig(args)
+
+  printStep(step++, totalSteps, "Adding oh-my-opencode plugin...")
+  const pluginResult = await addPluginToOpenCodeConfig(version)
+  if (!pluginResult.success) {
+    printError(`Failed: ${pluginResult.error}`)
+    return 1
+  }
+  printSuccess(
+    `Plugin ${isUpdate ? "verified" : "added"} ${SYMBOLS.arrow} ${color.dim(pluginResult.configPath)}`,
+  )
+
+  const needsProviderSetup = config.hasGemini || config.hasOpenAI || config.hasCopilot
+
+  if (needsProviderSetup) {
+    printStep(step++, totalSteps, "Adding auth plugins...")
+    const authResult = await addAuthPlugins(config)
+    if (!authResult.success) {
+      printError(`Failed: ${authResult.error}`)
+      return 1
+    }
+    printSuccess(`Auth plugins configured ${SYMBOLS.arrow} ${color.dim(authResult.configPath)}`)
+
+    printStep(step++, totalSteps, "Adding provider configurations...")
+    const providerResult = addProviderConfig(config)
+    if (!providerResult.success) {
+      printError(`Failed: ${providerResult.error}`)
+      return 1
+    }
+    printSuccess(`Providers configured ${SYMBOLS.arrow} ${color.dim(providerResult.configPath)}`)
+  } else {
+    step += 2
+  }
+
+  printStep(step++, totalSteps, "Writing oh-my-opencode configuration...")
+  const omoResult = writeOmoConfig(config)
+  if (!omoResult.success) {
+    printError(`Failed: ${omoResult.error}`)
+    return 1
+  }
+  printSuccess(`Config written ${SYMBOLS.arrow} ${color.dim(omoResult.configPath)}`)
+
+  printBox(formatConfigSummary(config), isUpdate ? "Updated Configuration" : "Installation Complete")
+
+  if (!config.hasClaude) {
+    console.log()
+    console.log(color.bgRed(color.white(color.bold(" CRITICAL WARNING "))))
+    console.log()
+    console.log(color.red(color.bold("  Sisyphus agent is STRONGLY optimized for Claude Opus 4.5.")))
+    console.log(color.red("  Without Claude, you may experience significantly degraded performance:"))
+    console.log(color.dim("    • Reduced orchestration quality"))
+    console.log(color.dim("    • Weaker tool selection and delegation"))
+    console.log(color.dim("    • Less reliable task completion"))
+    console.log()
+    console.log(color.yellow("  Consider subscribing to Claude Pro/Max for the best experience."))
+    console.log()
+  }
+
+  if (
+    !config.hasClaude &&
+    !config.hasOpenAI &&
+    !config.hasGemini &&
+    !config.hasCopilot &&
+    !config.hasOpencodeZen
+  ) {
+    printWarning("No model providers configured. Using opencode/glm-4.7-free as fallback.")
+  }
+
+  console.log(`${SYMBOLS.star} ${color.bold(color.green(isUpdate ? "Configuration updated!" : "Installation complete!"))}`)
+  console.log(`  Run ${color.cyan("opencode")} to start!`)
+  console.log()
+
+  printBox(
+    `${color.bold("Pro Tip:")} Include ${color.cyan("ultrawork")} (or ${color.cyan("ulw")}) in your prompt.\n` +
+      `All features work like magic—parallel agents, background tasks,\n` +
+      `deep exploration, and relentless execution until completion.`,
+    "The Magic Word",
+  )
+
+  console.log(`${SYMBOLS.star} ${color.yellow("If you found this helpful, consider starring the repo!")}`)
+  console.log(
+    `  ${color.dim("gh api --silent --method PUT /user/starred/code-yeongyu/oh-my-opencode >/dev/null 2>&1 || true")}`,
+  )
+  console.log()
+  console.log(color.dim("oMoMoMoMo... Enjoy!"))
+  console.log()
+
+  if ((config.hasClaude || config.hasGemini || config.hasCopilot) && !args.skipAuth) {
+    printBox(
+      `Run ${color.cyan("opencode auth login")} and select your provider:\n` +
+        (config.hasClaude ? `  ${SYMBOLS.bullet} Anthropic ${color.gray("→ Claude Pro/Max")}\n` : "") +
+        (config.hasGemini ? `  ${SYMBOLS.bullet} Google ${color.gray("→ OAuth with Antigravity")}\n` : "") +
+        (config.hasCopilot ? `  ${SYMBOLS.bullet} GitHub ${color.gray("→ Copilot")}` : ""),
+      "Authenticate Your Providers",
+    )
+  }
+
+  return 0
+}

src/cli/cli-program.ts

@@ -0,0 +1,183 @@
+import { Command } from "commander"
+import { install } from "./install"
+import { run } from "./run"
+import { getLocalVersion } from "./get-local-version"
+import { doctor } from "./doctor"
+import { createMcpOAuthCommand } from "./mcp-oauth"
+import type { InstallArgs } from "./types"
+import type { RunOptions } from "./run"
+import type { GetLocalVersionOptions } from "./get-local-version/types"
+import type { DoctorOptions } from "./doctor"
+import packageJson from "../../package.json" with { type: "json" }
+
+const VERSION = packageJson.version
+
+const program = new Command()
+
+program
+  .name("oh-my-opencode")
+  .description("The ultimate OpenCode plugin - multi-model orchestration, LSP tools, and more")
+  .version(VERSION, "-v, --version", "Show version number")
+  .enablePositionalOptions()
+
+program
+  .command("install")
+  .description("Install and configure oh-my-opencode with interactive setup")
+  .option("--no-tui", "Run in non-interactive mode (requires all options)")
+  .option("--claude <value>", "Claude subscription: no, yes, max20")
+  .option("--openai <value>", "OpenAI/ChatGPT subscription: no, yes (default: no)")
+  .option("--gemini <value>", "Gemini integration: no, yes")
+  .option("--copilot <value>", "GitHub Copilot subscription: no, yes")
+  .option("--opencode-zen <value>", "OpenCode Zen access: no, yes (default: no)")
+  .option("--zai-coding-plan <value>", "Z.ai Coding Plan subscription: no, yes (default: no)")
+  .option("--kimi-for-coding <value>", "Kimi For Coding subscription: no, yes (default: no)")
+  .option("--skip-auth", "Skip authentication setup hints")
+  .addHelpText("after", `
+Examples:
+  $ bunx oh-my-opencode install
+  $ bunx oh-my-opencode install --no-tui --claude=max20 --openai=yes --gemini=yes --copilot=no
+  $ bunx oh-my-opencode install --no-tui --claude=no --gemini=no --copilot=yes --opencode-zen=yes
+
+Model Providers (Priority: Native > Copilot > OpenCode Zen > Z.ai > Kimi):
+  Claude        Native anthropic/ models (Opus, Sonnet, Haiku)
+  OpenAI        Native openai/ models (GPT-5.2 for Oracle)
+  Gemini        Native google/ models (Gemini 3 Pro, Flash)
+  Copilot       github-copilot/ models (fallback)
+  OpenCode Zen  opencode/ models (opencode/claude-opus-4-6, etc.)
+  Z.ai          zai-coding-plan/glm-4.7 (Librarian priority)
+  Kimi          kimi-for-coding/k2p5 (Sisyphus/Prometheus fallback)
+`)
+  .action(async (options) => {
+    const args: InstallArgs = {
+      tui: options.tui !== false,
+      claude: options.claude,
+      openai: options.openai,
+      gemini: options.gemini,
+      copilot: options.copilot,
+      opencodeZen: options.opencodeZen,
+      zaiCodingPlan: options.zaiCodingPlan,
+      kimiForCoding: options.kimiForCoding,
+      skipAuth: options.skipAuth ?? false,
+    }
+    const exitCode = await install(args)
+    process.exit(exitCode)
+  })
+
+program
+   .command("run <message>")
+   .allowUnknownOption()
+   .passThroughOptions()
+   .description("Run opencode with todo/background task completion enforcement")
+  .option("-a, --agent <name>", "Agent to use (default: from CLI/env/config, fallback: Sisyphus)")
+  .option("-d, --directory <path>", "Working directory")
+  .option("-t, --timeout <ms>", "Timeout in milliseconds (default: 30 minutes)", parseInt)
+  .option("-p, --port <port>", "Server port (attaches if port already in use)", parseInt)
+  .option("--attach <url>", "Attach to existing opencode server URL")
+  .option("--on-complete <command>", "Shell command to run after completion")
+  .option("--json", "Output structured JSON result to stdout")
+  .option("--session-id <id>", "Resume existing session instead of creating new one")
+  .addHelpText("after", `
+Examples:
+  $ bunx oh-my-opencode run "Fix the bug in index.ts"
+  $ bunx oh-my-opencode run --agent Sisyphus "Implement feature X"
+  $ bunx oh-my-opencode run --timeout 3600000 "Large refactoring task"
+  $ bunx oh-my-opencode run --port 4321 "Fix the bug"
+  $ bunx oh-my-opencode run --attach http://127.0.0.1:4321 "Fix the bug"
+  $ bunx oh-my-opencode run --json "Fix the bug" | jq .sessionId
+  $ bunx oh-my-opencode run --on-complete "notify-send Done" "Fix the bug"
+  $ bunx oh-my-opencode run --session-id ses_abc123 "Continue the work"
+
+Agent resolution order:
+  1) --agent flag
+  2) OPENCODE_DEFAULT_AGENT
+  3) oh-my-opencode.json "default_run_agent"
+  4) Sisyphus (fallback)
+
+Available core agents:
+  Sisyphus, Hephaestus, Prometheus, Atlas
+
+Unlike 'opencode run', this command waits until:
+  - All todos are completed or cancelled
+  - All child sessions (background tasks) are idle
+`)
+  .action(async (message: string, options) => {
+    if (options.port && options.attach) {
+      console.error("Error: --port and --attach are mutually exclusive")
+      process.exit(1)
+    }
+    const runOptions: RunOptions = {
+      message,
+      agent: options.agent,
+      directory: options.directory,
+      timeout: options.timeout,
+      port: options.port,
+      attach: options.attach,
+      onComplete: options.onComplete,
+      json: options.json ?? false,
+      sessionId: options.sessionId,
+    }
+    const exitCode = await run(runOptions)
+    process.exit(exitCode)
+  })
+
+program
+  .command("get-local-version")
+  .description("Show current installed version and check for updates")
+  .option("-d, --directory <path>", "Working directory to check config from")
+  .option("--json", "Output in JSON format for scripting")
+  .addHelpText("after", `
+Examples:
+  $ bunx oh-my-opencode get-local-version
+  $ bunx oh-my-opencode get-local-version --json
+  $ bunx oh-my-opencode get-local-version --directory /path/to/project
+
+This command shows:
+  - Current installed version
+  - Latest available version on npm
+  - Whether you're up to date
+  - Special modes (local dev, pinned version)
+`)
+  .action(async (options) => {
+    const versionOptions: GetLocalVersionOptions = {
+      directory: options.directory,
+      json: options.json ?? false,
+    }
+    const exitCode = await getLocalVersion(versionOptions)
+    process.exit(exitCode)
+  })
+
+program
+  .command("doctor")
+  .description("Check oh-my-opencode installation health and diagnose issues")
+  .option("--status", "Show compact system dashboard")
+  .option("--verbose", "Show detailed diagnostic information")
+  .option("--json", "Output results in JSON format")
+  .addHelpText("after", `
+Examples:
+  $ bunx oh-my-opencode doctor            # Show problems only
+  $ bunx oh-my-opencode doctor --status   # Compact dashboard
+  $ bunx oh-my-opencode doctor --verbose  # Deep diagnostics
+  $ bunx oh-my-opencode doctor --json     # JSON output
+`)
+  .action(async (options) => {
+    const mode = options.status ? "status" : options.verbose ? "verbose" : "default"
+    const doctorOptions: DoctorOptions = {
+      mode,
+      json: options.json ?? false,
+    }
+    const exitCode = await doctor(doctorOptions)
+    process.exit(exitCode)
+  })
+
+program
+  .command("version")
+  .description("Show version information")
+  .action(() => {
+    console.log(`oh-my-opencode v${VERSION}`)
+  })
+
+program.addCommand(createMcpOAuthCommand())
+
+export function runCli(): void {
+  program.parse()
+}

src/cli/config-manager.test.ts

@@ -259,7 +259,7 @@ describe("generateOmoConfig - model fallback system", () => {
     // #then Sisyphus uses Claude (OR logic - at least one provider available)
     expect(result.$schema).toBe("https://raw.githubusercontent.com/code-yeongyu/oh-my-opencode/master/assets/oh-my-opencode.schema.json")
     expect(result.agents).toBeDefined()
-    expect((result.agents as Record<string, { model: string }>).sisyphus.model).toBe("anthropic/claude-opus-4-5")
+    expect((result.agents as Record<string, { model: string }>).sisyphus.model).toBe("anthropic/claude-opus-4-6")
   })
 
   test("generates native opus models when Claude max20 subscription", () => {
@@ -279,7 +279,7 @@ describe("generateOmoConfig - model fallback system", () => {
     const result = generateOmoConfig(config)
 
     // #then Sisyphus uses Claude (OR logic - at least one provider available)
-    expect((result.agents as Record<string, { model: string }>).sisyphus.model).toBe("anthropic/claude-opus-4-5")
+    expect((result.agents as Record<string, { model: string }>).sisyphus.model).toBe("anthropic/claude-opus-4-6")
   })
 
   test("uses github-copilot sonnet fallback when only copilot available", () => {
@@ -298,8 +298,8 @@ describe("generateOmoConfig - model fallback system", () => {
     // #when generating config
     const result = generateOmoConfig(config)
 
-    // #then Sisyphus uses Copilot (OR logic - copilot is in claude-opus-4-5 providers)
-    expect((result.agents as Record<string, { model: string }>).sisyphus.model).toBe("github-copilot/claude-opus-4.5")
+    // #then Sisyphus uses Copilot (OR logic - copilot is in claude-opus-4-6 providers)
+    expect((result.agents as Record<string, { model: string }>).sisyphus.model).toBe("github-copilot/claude-opus-4.6")
   })
 
   test("uses ultimate fallback when no providers configured", () => {
@@ -342,7 +342,7 @@ describe("generateOmoConfig - model fallback system", () => {
     // #then librarian should use zai-coding-plan/glm-4.7
     expect((result.agents as Record<string, { model: string }>).librarian.model).toBe("zai-coding-plan/glm-4.7")
     // #then Sisyphus uses Claude (OR logic)
-    expect((result.agents as Record<string, { model: string }>).sisyphus.model).toBe("anthropic/claude-opus-4-5")
+    expect((result.agents as Record<string, { model: string }>).sisyphus.model).toBe("anthropic/claude-opus-4-6")
   })
 
   test("uses native OpenAI models when only ChatGPT available", () => {

src/cli/config-manager.ts

@@ -1,667 +1,23 @@
-import { existsSync, mkdirSync, readFileSync, writeFileSync, statSync } from "node:fs"
-import {
-  parseJsonc,
-  getOpenCodeConfigPaths,
-  type OpenCodeBinaryType,
-  type OpenCodeConfigPaths,
-} from "../shared"
-import type { ConfigMergeResult, DetectedConfig, InstallConfig } from "./types"
-import { generateModelConfig } from "./model-fallback"
+export type { ConfigContext } from "./config-manager/config-context"
+export {
+  initConfigContext,
+  getConfigContext,
+  resetConfigContext,
+} from "./config-manager/config-context"
 
-const OPENCODE_BINARIES = ["opencode", "opencode-desktop"] as const
+export { fetchNpmDistTags } from "./config-manager/npm-dist-tags"
+export { getPluginNameWithVersion } from "./config-manager/plugin-name-with-version"
+export { addPluginToOpenCodeConfig } from "./config-manager/add-plugin-to-opencode-config"
 
-interface ConfigContext {
-  binary: OpenCodeBinaryType
-  version: string | null
-  paths: OpenCodeConfigPaths
-}
+export { generateOmoConfig } from "./config-manager/generate-omo-config"
+export { writeOmoConfig } from "./config-manager/write-omo-config"
 
-let configContext: ConfigContext | null = null
+export { isOpenCodeInstalled, getOpenCodeVersion } from "./config-manager/opencode-binary"
 
-export function initConfigContext(binary: OpenCodeBinaryType, version: string | null): void {
-  const paths = getOpenCodeConfigPaths({ binary, version })
-  configContext = { binary, version, paths }
-}
+export { fetchLatestVersion, addAuthPlugins } from "./config-manager/auth-plugins"
+export { ANTIGRAVITY_PROVIDER_CONFIG } from "./config-manager/antigravity-provider-configuration"
+export { addProviderConfig } from "./config-manager/add-provider-config"
+export { detectCurrentConfig } from "./config-manager/detect-current-config"
 
-export function getConfigContext(): ConfigContext {
-  if (!configContext) {
-    const paths = getOpenCodeConfigPaths({ binary: "opencode", version: null })
-    configContext = { binary: "opencode", version: null, paths }
-  }
-  return configContext
-}
-
-export function resetConfigContext(): void {
-  configContext = null
-}
-
-function getConfigDir(): string {
-  return getConfigContext().paths.configDir
-}
-
-function getConfigJson(): string {
-  return getConfigContext().paths.configJson
-}
-
-function getConfigJsonc(): string {
-  return getConfigContext().paths.configJsonc
-}
-
-function getPackageJson(): string {
-  return getConfigContext().paths.packageJson
-}
-
-function getOmoConfig(): string {
-  return getConfigContext().paths.omoConfig
-}
-
-const BUN_INSTALL_TIMEOUT_SECONDS = 60
-const BUN_INSTALL_TIMEOUT_MS = BUN_INSTALL_TIMEOUT_SECONDS * 1000
-
-interface NodeError extends Error {
-  code?: string
-}
-
-function isPermissionError(err: unknown): boolean {
-  const nodeErr = err as NodeError
-  return nodeErr?.code === "EACCES" || nodeErr?.code === "EPERM"
-}
-
-function isFileNotFoundError(err: unknown): boolean {
-  const nodeErr = err as NodeError
-  return nodeErr?.code === "ENOENT"
-}
-
-function formatErrorWithSuggestion(err: unknown, context: string): string {
-  if (isPermissionError(err)) {
-    return `Permission denied: Cannot ${context}. Try running with elevated permissions or check file ownership.`
-  }
-
-  if (isFileNotFoundError(err)) {
-    return `File not found while trying to ${context}. The file may have been deleted or moved.`
-  }
-
-  if (err instanceof SyntaxError) {
-    return `JSON syntax error while trying to ${context}: ${err.message}. Check for missing commas, brackets, or invalid characters.`
-  }
-
-  const message = err instanceof Error ? err.message : String(err)
-
-  if (message.includes("ENOSPC")) {
-    return `Disk full: Cannot ${context}. Free up disk space and try again.`
-  }
-
-  if (message.includes("EROFS")) {
-    return `Read-only filesystem: Cannot ${context}. Check if the filesystem is mounted read-only.`
-  }
-
-  return `Failed to ${context}: ${message}`
-}
-
-export async function fetchLatestVersion(packageName: string): Promise<string | null> {
-  try {
-    const res = await fetch(`https://registry.npmjs.org/${packageName}/latest`)
-    if (!res.ok) return null
-    const data = await res.json() as { version: string }
-    return data.version
-  } catch {
-    return null
-  }
-}
-
-interface NpmDistTags {
-  latest?: string
-  beta?: string
-  next?: string
-  [tag: string]: string | undefined
-}
-
-const NPM_FETCH_TIMEOUT_MS = 5000
-
-export async function fetchNpmDistTags(packageName: string): Promise<NpmDistTags | null> {
-  try {
-    const res = await fetch(`https://registry.npmjs.org/-/package/${packageName}/dist-tags`, {
-      signal: AbortSignal.timeout(NPM_FETCH_TIMEOUT_MS),
-    })
-    if (!res.ok) return null
-    const data = await res.json() as NpmDistTags
-    return data
-  } catch {
-    return null
-  }
-}
-
-const PACKAGE_NAME = "oh-my-opencode"
-
-const PRIORITIZED_TAGS = ["latest", "beta", "next"] as const
-
-export async function getPluginNameWithVersion(currentVersion: string): Promise<string> {
-  const distTags = await fetchNpmDistTags(PACKAGE_NAME)
-
-  if (distTags) {
-    const allTags = new Set([...PRIORITIZED_TAGS, ...Object.keys(distTags)])
-    for (const tag of allTags) {
-      if (distTags[tag] === currentVersion) {
-        return `${PACKAGE_NAME}@${tag}`
-      }
-    }
-  }
-
-  return `${PACKAGE_NAME}@${currentVersion}`
-}
-
-type ConfigFormat = "json" | "jsonc" | "none"
-
-interface OpenCodeConfig {
-  plugin?: string[]
-  [key: string]: unknown
-}
-
-export function detectConfigFormat(): { format: ConfigFormat; path: string } {
-  const configJsonc = getConfigJsonc()
-  const configJson = getConfigJson()
-
-  if (existsSync(configJsonc)) {
-    return { format: "jsonc", path: configJsonc }
-  }
-  if (existsSync(configJson)) {
-    return { format: "json", path: configJson }
-  }
-  return { format: "none", path: configJson }
-}
-
-interface ParseConfigResult {
-  config: OpenCodeConfig | null
-  error?: string
-}
-
-function isEmptyOrWhitespace(content: string): boolean {
-  return content.trim().length === 0
-}
-
-function parseConfig(path: string, _isJsonc: boolean): OpenCodeConfig | null {
-  const result = parseConfigWithError(path)
-  return result.config
-}
-
-function parseConfigWithError(path: string): ParseConfigResult {
-  try {
-    const stat = statSync(path)
-    if (stat.size === 0) {
-      return { config: null, error: `Config file is empty: ${path}. Delete it or add valid JSON content.` }
-    }
-
-    const content = readFileSync(path, "utf-8")
-
-    if (isEmptyOrWhitespace(content)) {
-      return { config: null, error: `Config file contains only whitespace: ${path}. Delete it or add valid JSON content.` }
-    }
-
-    const config = parseJsonc<OpenCodeConfig>(content)
-
-    if (config === null || config === undefined) {
-      return { config: null, error: `Config file parsed to null/undefined: ${path}. Ensure it contains valid JSON.` }
-    }
-
-    if (typeof config !== "object" || Array.isArray(config)) {
-      return { config: null, error: `Config file must contain a JSON object, not ${Array.isArray(config) ? "an array" : typeof config}: ${path}` }
-    }
-
-    return { config }
-  } catch (err) {
-    return { config: null, error: formatErrorWithSuggestion(err, `parse config file ${path}`) }
-  }
-}
-
-function ensureConfigDir(): void {
-  const configDir = getConfigDir()
-  if (!existsSync(configDir)) {
-    mkdirSync(configDir, { recursive: true })
-  }
-}
-
-export async function addPluginToOpenCodeConfig(currentVersion: string): Promise<ConfigMergeResult> {
-  try {
-    ensureConfigDir()
-  } catch (err) {
-    return { success: false, configPath: getConfigDir(), error: formatErrorWithSuggestion(err, "create config directory") }
-  }
-
-  const { format, path } = detectConfigFormat()
-  const pluginEntry = await getPluginNameWithVersion(currentVersion)
-
-  try {
-    if (format === "none") {
-      const config: OpenCodeConfig = { plugin: [pluginEntry] }
-      writeFileSync(path, JSON.stringify(config, null, 2) + "\n")
-      return { success: true, configPath: path }
-    }
-
-    const parseResult = parseConfigWithError(path)
-    if (!parseResult.config) {
-      return { success: false, configPath: path, error: parseResult.error ?? "Failed to parse config file" }
-    }
-
-    const config = parseResult.config
-    const plugins = config.plugin ?? []
-    const existingIndex = plugins.findIndex((p) => p === PACKAGE_NAME || p.startsWith(`${PACKAGE_NAME}@`))
-
-    if (existingIndex !== -1) {
-      if (plugins[existingIndex] === pluginEntry) {
-        return { success: true, configPath: path }
-      }
-      plugins[existingIndex] = pluginEntry
-    } else {
-      plugins.push(pluginEntry)
-    }
-
-    config.plugin = plugins
-
-    if (format === "jsonc") {
-      const content = readFileSync(path, "utf-8")
-      const pluginArrayRegex = /"plugin"\s*:\s*\[([\s\S]*?)\]/
-      const match = content.match(pluginArrayRegex)
-
-      if (match) {
-        const formattedPlugins = plugins.map((p) => `"${p}"`).join(",\n    ")
-        const newContent = content.replace(pluginArrayRegex, `"plugin": [\n    ${formattedPlugins}\n  ]`)
-        writeFileSync(path, newContent)
-      } else {
-        const newContent = content.replace(/^(\s*\{)/, `$1\n  "plugin": ["${pluginEntry}"],`)
-        writeFileSync(path, newContent)
-      }
-    } else {
-      writeFileSync(path, JSON.stringify(config, null, 2) + "\n")
-    }
-
-    return { success: true, configPath: path }
-  } catch (err) {
-    return { success: false, configPath: path, error: formatErrorWithSuggestion(err, "update opencode config") }
-  }
-}
-
-function deepMerge<T extends Record<string, unknown>>(target: T, source: Partial<T>): T {
-  const result = { ...target }
-
-  for (const key of Object.keys(source) as Array<keyof T>) {
-    const sourceValue = source[key]
-    const targetValue = result[key]
-
-    if (
-      sourceValue !== null &&
-      typeof sourceValue === "object" &&
-      !Array.isArray(sourceValue) &&
-      targetValue !== null &&
-      typeof targetValue === "object" &&
-      !Array.isArray(targetValue)
-    ) {
-      result[key] = deepMerge(
-        targetValue as Record<string, unknown>,
-        sourceValue as Record<string, unknown>
-      ) as T[keyof T]
-    } else if (sourceValue !== undefined) {
-      result[key] = sourceValue as T[keyof T]
-    }
-  }
-
-  return result
-}
-
-export function generateOmoConfig(installConfig: InstallConfig): Record<string, unknown> {
-  return generateModelConfig(installConfig)
-}
-
-export function writeOmoConfig(installConfig: InstallConfig): ConfigMergeResult {
-  try {
-    ensureConfigDir()
-  } catch (err) {
-    return { success: false, configPath: getConfigDir(), error: formatErrorWithSuggestion(err, "create config directory") }
-  }
-
-  const omoConfigPath = getOmoConfig()
-
-  try {
-    const newConfig = generateOmoConfig(installConfig)
-
-    if (existsSync(omoConfigPath)) {
-      try {
-        const stat = statSync(omoConfigPath)
-        const content = readFileSync(omoConfigPath, "utf-8")
-
-        if (stat.size === 0 || isEmptyOrWhitespace(content)) {
-          writeFileSync(omoConfigPath, JSON.stringify(newConfig, null, 2) + "\n")
-          return { success: true, configPath: omoConfigPath }
-        }
-
-        const existing = parseJsonc<Record<string, unknown>>(content)
-        if (!existing || typeof existing !== "object" || Array.isArray(existing)) {
-          writeFileSync(omoConfigPath, JSON.stringify(newConfig, null, 2) + "\n")
-          return { success: true, configPath: omoConfigPath }
-        }
-
-        const merged = deepMerge(existing, newConfig)
-        writeFileSync(omoConfigPath, JSON.stringify(merged, null, 2) + "\n")
-      } catch (parseErr) {
-        if (parseErr instanceof SyntaxError) {
-          writeFileSync(omoConfigPath, JSON.stringify(newConfig, null, 2) + "\n")
-          return { success: true, configPath: omoConfigPath }
-        }
-        throw parseErr
-      }
-    } else {
-      writeFileSync(omoConfigPath, JSON.stringify(newConfig, null, 2) + "\n")
-    }
-
-    return { success: true, configPath: omoConfigPath }
-  } catch (err) {
-    return { success: false, configPath: omoConfigPath, error: formatErrorWithSuggestion(err, "write oh-my-opencode config") }
-  }
-}
-
-interface OpenCodeBinaryResult {
-  binary: OpenCodeBinaryType
-  version: string
-}
-
-async function findOpenCodeBinaryWithVersion(): Promise<OpenCodeBinaryResult | null> {
-  for (const binary of OPENCODE_BINARIES) {
-    try {
-      const proc = Bun.spawn([binary, "--version"], {
-        stdout: "pipe",
-        stderr: "pipe",
-      })
-      const output = await new Response(proc.stdout).text()
-      await proc.exited
-      if (proc.exitCode === 0) {
-        const version = output.trim()
-        initConfigContext(binary, version)
-        return { binary, version }
-      }
-    } catch {
-      continue
-    }
-  }
-  return null
-}
-
-export async function isOpenCodeInstalled(): Promise<boolean> {
-  const result = await findOpenCodeBinaryWithVersion()
-  return result !== null
-}
-
-export async function getOpenCodeVersion(): Promise<string | null> {
-  const result = await findOpenCodeBinaryWithVersion()
-  return result?.version ?? null
-}
-
-export async function addAuthPlugins(config: InstallConfig): Promise<ConfigMergeResult> {
-  try {
-    ensureConfigDir()
-  } catch (err) {
-    return { success: false, configPath: getConfigDir(), error: formatErrorWithSuggestion(err, "create config directory") }
-  }
-
-  const { format, path } = detectConfigFormat()
-
-  try {
-    let existingConfig: OpenCodeConfig | null = null
-    if (format !== "none") {
-      const parseResult = parseConfigWithError(path)
-      if (parseResult.error && !parseResult.config) {
-        existingConfig = {}
-      } else {
-        existingConfig = parseResult.config
-      }
-    }
-
-    const plugins: string[] = existingConfig?.plugin ?? []
-
-    if (config.hasGemini) {
-      const version = await fetchLatestVersion("opencode-antigravity-auth")
-      const pluginEntry = version ? `opencode-antigravity-auth@${version}` : "opencode-antigravity-auth"
-      if (!plugins.some((p) => p.startsWith("opencode-antigravity-auth"))) {
-        plugins.push(pluginEntry)
-      }
-    }
-
-
-
-    const newConfig = { ...(existingConfig ?? {}), plugin: plugins }
-    writeFileSync(path, JSON.stringify(newConfig, null, 2) + "\n")
-    return { success: true, configPath: path }
-  } catch (err) {
-    return { success: false, configPath: path, error: formatErrorWithSuggestion(err, "add auth plugins to config") }
-  }
-}
-
-export interface BunInstallResult {
-  success: boolean
-  timedOut?: boolean
-  error?: string
-}
-
-export async function runBunInstall(): Promise<boolean> {
-  const result = await runBunInstallWithDetails()
-  return result.success
-}
-
-export async function runBunInstallWithDetails(): Promise<BunInstallResult> {
-  try {
-    const proc = Bun.spawn(["bun", "install"], {
-      cwd: getConfigDir(),
-      stdout: "pipe",
-      stderr: "pipe",
-    })
-
-    const timeoutPromise = new Promise<"timeout">((resolve) =>
-      setTimeout(() => resolve("timeout"), BUN_INSTALL_TIMEOUT_MS)
-    )
-
-    const exitPromise = proc.exited.then(() => "completed" as const)
-
-    const result = await Promise.race([exitPromise, timeoutPromise])
-
-    if (result === "timeout") {
-      try {
-        proc.kill()
-      } catch {
-        /* intentionally empty - process may have already exited */
-      }
-      return {
-        success: false,
-        timedOut: true,
-        error: `bun install timed out after ${BUN_INSTALL_TIMEOUT_SECONDS} seconds. Try running manually: cd ~/.config/opencode && bun i`,
-      }
-    }
-
-    if (proc.exitCode !== 0) {
-      const stderr = await new Response(proc.stderr).text()
-      return {
-        success: false,
-        error: stderr.trim() || `bun install failed with exit code ${proc.exitCode}`,
-      }
-    }
-
-    return { success: true }
-  } catch (err) {
-    const message = err instanceof Error ? err.message : String(err)
-    return {
-      success: false,
-      error: `bun install failed: ${message}. Is bun installed? Try: curl -fsSL https://bun.sh/install | bash`,
-    }
-  }
-}
-
-/**
- * Antigravity Provider Configuration
- *
- * IMPORTANT: Model names MUST use `antigravity-` prefix for stability.
- *
- * Since opencode-antigravity-auth v1.3.0, models use a variant system:
- * - `antigravity-gemini-3-pro` with variants: low, high
- * - `antigravity-gemini-3-flash` with variants: minimal, low, medium, high
- *
- * Legacy tier-suffixed names (e.g., `antigravity-gemini-3-pro-high`) still work
- * but variants are the recommended approach.
- *
- * @see https://github.com/NoeFabris/opencode-antigravity-auth#models
- */
-export const ANTIGRAVITY_PROVIDER_CONFIG = {
-  google: {
-    name: "Google",
-    models: {
-      "antigravity-gemini-3-pro": {
-        name: "Gemini 3 Pro (Antigravity)",
-        limit: { context: 1048576, output: 65535 },
-        modalities: { input: ["text", "image", "pdf"], output: ["text"] },
-        variants: {
-          low: { thinkingLevel: "low" },
-          high: { thinkingLevel: "high" },
-        },
-      },
-      "antigravity-gemini-3-flash": {
-        name: "Gemini 3 Flash (Antigravity)",
-        limit: { context: 1048576, output: 65536 },
-        modalities: { input: ["text", "image", "pdf"], output: ["text"] },
-        variants: {
-          minimal: { thinkingLevel: "minimal" },
-          low: { thinkingLevel: "low" },
-          medium: { thinkingLevel: "medium" },
-          high: { thinkingLevel: "high" },
-        },
-      },
-      "antigravity-claude-sonnet-4-5": {
-        name: "Claude Sonnet 4.5 (Antigravity)",
-        limit: { context: 200000, output: 64000 },
-        modalities: { input: ["text", "image", "pdf"], output: ["text"] },
-      },
-      "antigravity-claude-sonnet-4-5-thinking": {
-        name: "Claude Sonnet 4.5 Thinking (Antigravity)",
-        limit: { context: 200000, output: 64000 },
-        modalities: { input: ["text", "image", "pdf"], output: ["text"] },
-        variants: {
-          low: { thinkingConfig: { thinkingBudget: 8192 } },
-          max: { thinkingConfig: { thinkingBudget: 32768 } },
-        },
-      },
-      "antigravity-claude-opus-4-5-thinking": {
-        name: "Claude Opus 4.5 Thinking (Antigravity)",
-        limit: { context: 200000, output: 64000 },
-        modalities: { input: ["text", "image", "pdf"], output: ["text"] },
-        variants: {
-          low: { thinkingConfig: { thinkingBudget: 8192 } },
-          max: { thinkingConfig: { thinkingBudget: 32768 } },
-        },
-      },
-    },
-  },
-}
-
-
-
-export function addProviderConfig(config: InstallConfig): ConfigMergeResult {
-  try {
-    ensureConfigDir()
-  } catch (err) {
-    return { success: false, configPath: getConfigDir(), error: formatErrorWithSuggestion(err, "create config directory") }
-  }
-
-  const { format, path } = detectConfigFormat()
-
-  try {
-    let existingConfig: OpenCodeConfig | null = null
-    if (format !== "none") {
-      const parseResult = parseConfigWithError(path)
-      if (parseResult.error && !parseResult.config) {
-        existingConfig = {}
-      } else {
-        existingConfig = parseResult.config
-      }
-    }
-
-    const newConfig = { ...(existingConfig ?? {}) }
-
-    const providers = (newConfig.provider ?? {}) as Record<string, unknown>
-
-    if (config.hasGemini) {
-      providers.google = ANTIGRAVITY_PROVIDER_CONFIG.google
-    }
-
-    if (Object.keys(providers).length > 0) {
-      newConfig.provider = providers
-    }
-
-    writeFileSync(path, JSON.stringify(newConfig, null, 2) + "\n")
-    return { success: true, configPath: path }
-  } catch (err) {
-    return { success: false, configPath: path, error: formatErrorWithSuggestion(err, "add provider config") }
-  }
-}
-
-function detectProvidersFromOmoConfig(): { hasOpenAI: boolean; hasOpencodeZen: boolean; hasZaiCodingPlan: boolean; hasKimiForCoding: boolean } {
-  const omoConfigPath = getOmoConfig()
-  if (!existsSync(omoConfigPath)) {
-    return { hasOpenAI: true, hasOpencodeZen: true, hasZaiCodingPlan: false, hasKimiForCoding: false }
-  }
-
-  try {
-    const content = readFileSync(omoConfigPath, "utf-8")
-    const omoConfig = parseJsonc<Record<string, unknown>>(content)
-    if (!omoConfig || typeof omoConfig !== "object") {
-      return { hasOpenAI: true, hasOpencodeZen: true, hasZaiCodingPlan: false, hasKimiForCoding: false }
-    }
-
-    const configStr = JSON.stringify(omoConfig)
-    const hasOpenAI = configStr.includes('"openai/')
-    const hasOpencodeZen = configStr.includes('"opencode/')
-    const hasZaiCodingPlan = configStr.includes('"zai-coding-plan/')
-    const hasKimiForCoding = configStr.includes('"kimi-for-coding/')
-
-    return { hasOpenAI, hasOpencodeZen, hasZaiCodingPlan, hasKimiForCoding }
-  } catch {
-    return { hasOpenAI: true, hasOpencodeZen: true, hasZaiCodingPlan: false, hasKimiForCoding: false }
-  }
-}
-
-export function detectCurrentConfig(): DetectedConfig {
-  const result: DetectedConfig = {
-    isInstalled: false,
-    hasClaude: true,
-    isMax20: true,
-    hasOpenAI: true,
-    hasGemini: false,
-    hasCopilot: false,
-    hasOpencodeZen: true,
-    hasZaiCodingPlan: false,
-    hasKimiForCoding: false,
-  }
-
-  const { format, path } = detectConfigFormat()
-  if (format === "none") {
-    return result
-  }
-
-  const parseResult = parseConfigWithError(path)
-  if (!parseResult.config) {
-    return result
-  }
-
-  const openCodeConfig = parseResult.config
-  const plugins = openCodeConfig.plugin ?? []
-  result.isInstalled = plugins.some((p) => p.startsWith("oh-my-opencode"))
-
-  if (!result.isInstalled) {
-    return result
-  }
-
-  // Gemini auth plugin detection still works via plugin presence
-  result.hasGemini = plugins.some((p) => p.startsWith("opencode-antigravity-auth"))
-
-  const { hasOpenAI, hasOpencodeZen, hasZaiCodingPlan, hasKimiForCoding } = detectProvidersFromOmoConfig()
-  result.hasOpenAI = hasOpenAI
-  result.hasOpencodeZen = hasOpencodeZen
-  result.hasZaiCodingPlan = hasZaiCodingPlan
-  result.hasKimiForCoding = hasKimiForCoding
-
-  return result
-}
+export type { BunInstallResult } from "./config-manager/bun-install"
+export { runBunInstall, runBunInstallWithDetails } from "./config-manager/bun-install"

src/cli/config-manager/add-plugin-to-opencode-config.ts

@@ -0,0 +1,82 @@
+import { readFileSync, writeFileSync } from "node:fs"
+import type { ConfigMergeResult } from "../types"
+import { getConfigDir } from "./config-context"
+import { ensureConfigDirectoryExists } from "./ensure-config-directory-exists"
+import { formatErrorWithSuggestion } from "./format-error-with-suggestion"
+import { detectConfigFormat } from "./opencode-config-format"
+import { parseOpenCodeConfigFileWithError, type OpenCodeConfig } from "./parse-opencode-config-file"
+import { getPluginNameWithVersion } from "./plugin-name-with-version"
+
+const PACKAGE_NAME = "oh-my-opencode"
+
+export async function addPluginToOpenCodeConfig(currentVersion: string): Promise<ConfigMergeResult> {
+  try {
+    ensureConfigDirectoryExists()
+  } catch (err) {
+    return {
+      success: false,
+      configPath: getConfigDir(),
+      error: formatErrorWithSuggestion(err, "create config directory"),
+    }
+  }
+
+  const { format, path } = detectConfigFormat()
+  const pluginEntry = await getPluginNameWithVersion(currentVersion)
+
+  try {
+    if (format === "none") {
+      const config: OpenCodeConfig = { plugin: [pluginEntry] }
+      writeFileSync(path, JSON.stringify(config, null, 2) + "\n")
+      return { success: true, configPath: path }
+    }
+
+    const parseResult = parseOpenCodeConfigFileWithError(path)
+    if (!parseResult.config) {
+      return {
+        success: false,
+        configPath: path,
+        error: parseResult.error ?? "Failed to parse config file",
+      }
+    }
+
+    const config = parseResult.config
+    const plugins = config.plugin ?? []
+    const existingIndex = plugins.findIndex((p) => p === PACKAGE_NAME || p.startsWith(`${PACKAGE_NAME}@`))
+
+    if (existingIndex !== -1) {
+      if (plugins[existingIndex] === pluginEntry) {
+        return { success: true, configPath: path }
+      }
+      plugins[existingIndex] = pluginEntry
+    } else {
+      plugins.push(pluginEntry)
+    }
+
+    config.plugin = plugins
+
+    if (format === "jsonc") {
+      const content = readFileSync(path, "utf-8")
+      const pluginArrayRegex = /"plugin"\s*:\s*\[([\s\S]*?)\]/
+      const match = content.match(pluginArrayRegex)
+
+      if (match) {
+        const formattedPlugins = plugins.map((p) => `"${p}"`).join(",\n    ")
+        const newContent = content.replace(pluginArrayRegex, `"plugin": [\n    ${formattedPlugins}\n  ]`)
+        writeFileSync(path, newContent)
+      } else {
+        const newContent = content.replace(/(\{)/, `$1\n  "plugin": ["${pluginEntry}"],`)
+        writeFileSync(path, newContent)
+      }
+    } else {
+      writeFileSync(path, JSON.stringify(config, null, 2) + "\n")
+    }
+
+    return { success: true, configPath: path }
+  } catch (err) {
+    return {
+      success: false,
+      configPath: path,
+      error: formatErrorWithSuggestion(err, "update opencode config"),
+    }
+  }
+}

src/cli/config-manager/add-provider-config.test.ts

@@ -0,0 +1,205 @@
+import { describe, expect, it } from "bun:test"
+import { modifyProviderInJsonc } from "./jsonc-provider-editor"
+import { parseJsonc } from "../../shared/jsonc-parser"
+
+describe("modifyProviderInJsonc", () => {
+  describe("Test 1: Basic JSONC with existing provider", () => {
+    it("replaces provider value, preserves comments and other keys", () => {
+      // given
+      const content = `{
+  // my config
+  "provider": { "openai": {} },
+  "plugin": ["foo"]
+}`
+      const newProviderValue = { google: { name: "Google" } }
+
+      // when
+      const result = modifyProviderInJsonc(content, newProviderValue)
+
+      // then
+      expect(result).toContain('"google"')
+      expect(result).toContain('"plugin": ["foo"]')
+      expect(result).toContain('// my config')
+
+      // Post-write validation
+      const parsed = parseJsonc<Record<string, unknown>>(result)
+      expect(parsed).toHaveProperty('plugin')
+      expect(parsed).toHaveProperty('provider')
+    })
+  })
+
+  describe("Test 2: Comment containing '}' inside provider block", () => {
+    it("must NOT corrupt file", () => {
+      // given
+      const content = `{
+  "provider": {
+    // } this brace should be ignored
+    "openai": {}
+  },
+  "other": 1
+}`
+      const newProviderValue = { google: { name: "Google" } }
+
+      // when
+      const result = modifyProviderInJsonc(content, newProviderValue)
+
+      // then
+      expect(result).toContain('"other"')
+
+      // Post-write validation
+      const parsed = parseJsonc<Record<string, unknown>>(result)
+      expect(parsed).toHaveProperty('other')
+      expect(parsed.other).toBe(1)
+    })
+  })
+
+  describe("Test 3: Comment containing '\"provider\"' before real key", () => {
+    it("must NOT match wrong location", () => {
+      // given
+      const content = `{
+  // "provider": { "example": true }
+  "provider": { "openai": {} },
+  "other": 1
+}`
+      const newProviderValue = { google: { name: "Google" } }
+
+      // when
+      const result = modifyProviderInJsonc(content, newProviderValue)
+
+      // then
+      expect(result).toContain('"other"')
+
+      // Post-write validation
+      const parsed = parseJsonc<Record<string, unknown>>(result)
+      expect(parsed).toHaveProperty('other')
+      expect(parsed.other).toBe(1)
+      expect(parsed.provider).toHaveProperty('google')
+    })
+  })
+
+  describe("Test 4: Comment containing '{' inside provider", () => {
+    it("must NOT mess up depth", () => {
+      // given
+      const content = `{
+  "provider": {
+    // { unmatched brace in comment
+    "openai": {}
+  },
+  "other": 1
+}`
+      const newProviderValue = { google: { name: "Google" } }
+
+      // when
+      const result = modifyProviderInJsonc(content, newProviderValue)
+
+      // then
+      expect(result).toContain('"other"')
+
+      // Post-write validation
+      const parsed = parseJsonc<Record<string, unknown>>(result)
+      expect(parsed).toHaveProperty('other')
+      expect(parsed.other).toBe(1)
+    })
+  })
+
+  describe("Test 5: No existing provider key", () => {
+    it("inserts provider without corrupting", () => {
+      // given
+      const content = `{
+  // config comment
+  "plugin": ["foo"]
+}`
+      const newProviderValue = { google: { name: "Google" } }
+
+      // when
+      const result = modifyProviderInJsonc(content, newProviderValue)
+
+      // then
+      expect(result).toContain('"provider"')
+      expect(result).toContain('"plugin"')
+      expect(result).toContain('foo')
+      expect(result).toContain('// config comment')
+
+      // Post-write validation
+      const parsed = parseJsonc<Record<string, unknown>>(result)
+      expect(parsed).toHaveProperty('provider')
+      expect(parsed).toHaveProperty('plugin')
+      expect(parsed.plugin).toEqual(['foo'])
+    })
+  })
+
+  describe("Test 6: String value exactly 'provider' before real key", () => {
+    it("must NOT match wrong location", () => {
+      // given
+      const content = `{
+  "note": "provider",
+  "provider": { "openai": {} },
+  "other": 1
+}`
+      const newProviderValue = { google: { name: "Google" } }
+
+      // when
+      const result = modifyProviderInJsonc(content, newProviderValue)
+
+      // then
+      expect(result).toContain('"other"')
+      expect(result).toContain('"note": "provider"')
+
+      // Post-write validation
+      const parsed = parseJsonc<Record<string, unknown>>(result)
+      expect(parsed).toHaveProperty('other')
+      expect(parsed.other).toBe(1)
+      expect(parsed.note).toBe('provider')
+    })
+  })
+
+  describe("Test 7: Post-write validation", () => {
+    it("result file must be valid JSONC for all cases", () => {
+      // Test Case 1
+      const content1 = `{
+  "provider": { "openai": {} },
+  "plugin": ["foo"]
+}`
+      const result1 = modifyProviderInJsonc(content1, { google: {} })
+      expect(() => parseJsonc(result1)).not.toThrow()
+
+      // Test Case 2
+      const content2 = `{
+  "provider": {
+    // } comment
+    "openai": {}
+  }
+}`
+      const result2 = modifyProviderInJsonc(content2, { google: {} })
+      expect(() => parseJsonc(result2)).not.toThrow()
+
+      // Test Case 3
+      const content3 = `{
+  "plugin": ["foo"]
+}`
+      const result3 = modifyProviderInJsonc(content3, { google: {} })
+      expect(() => parseJsonc(result3)).not.toThrow()
+    })
+  })
+
+  describe("Test 8: Trailing commas preserved", () => {
+    it("file is valid JSONC with trailing commas", () => {
+      // given
+      const content = `{
+  "provider": { "openai": {}, },
+  "plugin": ["foo",],
+}`
+      const newProviderValue = { google: { name: "Google" } }
+
+      // when
+      const result = modifyProviderInJsonc(content, newProviderValue)
+
+      // then
+      expect(() => parseJsonc(result)).not.toThrow()
+
+      const parsed = parseJsonc<Record<string, unknown>>(result)
+      expect(parsed).toHaveProperty('plugin')
+      expect(parsed.plugin).toEqual(['foo'])
+    })
+  })
+})

src/cli/config-manager/add-provider-config.ts

@@ -0,0 +1,82 @@
+import { readFileSync, writeFileSync, copyFileSync } from "node:fs"
+import type { ConfigMergeResult, InstallConfig } from "../types"
+import { getConfigDir } from "./config-context"
+import { ensureConfigDirectoryExists } from "./ensure-config-directory-exists"
+import { formatErrorWithSuggestion } from "./format-error-with-suggestion"
+import { detectConfigFormat } from "./opencode-config-format"
+import { parseOpenCodeConfigFileWithError, type OpenCodeConfig } from "./parse-opencode-config-file"
+import { ANTIGRAVITY_PROVIDER_CONFIG } from "./antigravity-provider-configuration"
+import { modifyProviderInJsonc } from "./jsonc-provider-editor"
+import { parseJsonc } from "../../shared/jsonc-parser"
+
+export function addProviderConfig(config: InstallConfig): ConfigMergeResult {
+  try {
+    ensureConfigDirectoryExists()
+  } catch (err) {
+    return {
+      success: false,
+      configPath: getConfigDir(),
+      error: formatErrorWithSuggestion(err, "create config directory"),
+    }
+  }
+
+  const { format, path } = detectConfigFormat()
+
+  try {
+    let existingConfig: OpenCodeConfig | null = null
+    if (format !== "none") {
+      const parseResult = parseOpenCodeConfigFileWithError(path)
+      if (parseResult.error && !parseResult.config) {
+        return {
+          success: false,
+          configPath: path,
+          error: `Failed to parse config file: ${parseResult.error}`,
+        }
+      }
+      existingConfig = parseResult.config
+    }
+
+    const newConfig = { ...(existingConfig ?? {}) }
+    const providers = (newConfig.provider ?? {}) as Record<string, unknown>
+
+    if (config.hasGemini) {
+      providers.google = ANTIGRAVITY_PROVIDER_CONFIG.google
+    }
+
+    if (Object.keys(providers).length > 0) {
+      newConfig.provider = providers
+    }
+
+    if (format === "jsonc") {
+      const content = readFileSync(path, "utf-8")
+
+      // Backup original file
+      copyFileSync(path, `${path}.bak`)
+
+      const providerValue = (newConfig.provider ?? {}) as Record<string, unknown>
+      const newContent = modifyProviderInJsonc(content, providerValue)
+
+      // Post-write validation
+      try {
+        parseJsonc(newContent)
+      } catch (error) {
+        return {
+          success: false,
+          configPath: path,
+          error: `Generated JSONC is invalid: ${error instanceof Error ? error.message : String(error)}`,
+        }
+      }
+
+      writeFileSync(path, newContent)
+    } else {
+      writeFileSync(path, JSON.stringify(newConfig, null, 2) + "\n")
+    }
+    return { success: true, configPath: path }
+  } catch (err) {
+    return {
+      success: false,
+      configPath: path,
+      error: formatErrorWithSuggestion(err, "add provider config"),
+    }
+  }
+}

src/cli/config-manager/antigravity-provider-configuration.ts

@@ -0,0 +1,64 @@
+/**
+ * Antigravity Provider Configuration
+ *
+ * IMPORTANT: Model names MUST use `antigravity-` prefix for stability.
+ *
+ * Since opencode-antigravity-auth v1.3.0, models use a variant system:
+ * - `antigravity-gemini-3-pro` with variants: low, high
+ * - `antigravity-gemini-3-flash` with variants: minimal, low, medium, high
+ *
+ * Legacy tier-suffixed names (e.g., `antigravity-gemini-3-pro-high`) still work
+ * but variants are the recommended approach.
+ *
+ * @see https://github.com/NoeFabris/opencode-antigravity-auth#models
+ */
+export const ANTIGRAVITY_PROVIDER_CONFIG = {
+  google: {
+    name: "Google",
+    models: {
+      "antigravity-gemini-3-pro": {
+        name: "Gemini 3 Pro (Antigravity)",
+        limit: { context: 1048576, output: 65535 },
+        modalities: { input: ["text", "image", "pdf"], output: ["text"] },
+        variants: {
+          low: { thinkingLevel: "low" },
+          high: { thinkingLevel: "high" },
+        },
+      },
+      "antigravity-gemini-3-flash": {
+        name: "Gemini 3 Flash (Antigravity)",
+        limit: { context: 1048576, output: 65536 },
+        modalities: { input: ["text", "image", "pdf"], output: ["text"] },
+        variants: {
+          minimal: { thinkingLevel: "minimal" },
+          low: { thinkingLevel: "low" },
+          medium: { thinkingLevel: "medium" },
+          high: { thinkingLevel: "high" },
+        },
+      },
+      "antigravity-claude-sonnet-4-5": {
+        name: "Claude Sonnet 4.5 (Antigravity)",
+        limit: { context: 200000, output: 64000 },
+        modalities: { input: ["text", "image", "pdf"], output: ["text"] },
+      },
+      "antigravity-claude-sonnet-4-5-thinking": {
+        name: "Claude Sonnet 4.5 Thinking (Antigravity)",
+        limit: { context: 200000, output: 64000 },
+        modalities: { input: ["text", "image", "pdf"], output: ["text"] },
+        variants: {
+          low: { thinkingConfig: { thinkingBudget: 8192 } },
+          max: { thinkingConfig: { thinkingBudget: 32768 } },
+        },
+      },
+      "antigravity-claude-opus-4-5-thinking": {
+        name: "Claude Opus 4.5 Thinking (Antigravity)",
+        limit: { context: 200000, output: 64000 },
+        modalities: { input: ["text", "image", "pdf"], output: ["text"] },
+        variants: {
+          low: { thinkingConfig: { thinkingBudget: 8192 } },
+          max: { thinkingConfig: { thinkingBudget: 32768 } },
+        },
+      },
+    },
+  },
+}

src/cli/config-manager/auth-plugins.test.ts

@@ -0,0 +1,224 @@
+import { describe, expect, it, beforeEach, afterEach, spyOn } from "bun:test"
+import { tmpdir } from "node:os"
+import { join } from "node:path"
+import { writeFileSync, readFileSync, existsSync, rmSync, mkdirSync } from "node:fs"
+import { parseJsonc } from "../../shared/jsonc-parser"
+import type { InstallConfig } from "../types"
+import { resetConfigContext } from "./config-context"
+
+let testConfigPath: string
+let testConfigDir: string
+let testCounter = 0
+let fetchVersionSpy: unknown
+
+beforeEach(async () => {
+  testCounter++
+  testConfigDir = join(tmpdir(), `test-opencode-${Date.now()}-${testCounter}`)
+  testConfigPath = join(testConfigDir, "opencode.jsonc")
+  mkdirSync(testConfigDir, { recursive: true })
+
+  process.env.OPENCODE_CONFIG_DIR = testConfigDir
+  resetConfigContext()
+
+  const module = await import("./auth-plugins")
+  fetchVersionSpy = spyOn(module, "fetchLatestVersion").mockResolvedValue("1.2.3")
+})
+
+afterEach(() => {
+  try {
+    rmSync(testConfigDir, { recursive: true, force: true })
+  } catch {}
+})
+
+const testConfig: InstallConfig = {
+  hasClaude: false,
+  isMax20: false,
+  hasOpenAI: false,
+  hasGemini: true,
+  hasCopilot: false,
+  hasOpencodeZen: false,
+  hasZaiCodingPlan: false,
+  hasKimiForCoding: false,
+}
+
+describe("addAuthPlugins", () => {
+  describe("Test 1: JSONC with commented plugin line", () => {
+    it("preserves comment, updates actual plugin array", async () => {
+      const content = `{
+  // "plugin": ["old-plugin"]
+  "plugin": ["existing-plugin"],
+  "provider": {}
+}`
+      writeFileSync(testConfigPath, content, "utf-8")
+
+      const { addAuthPlugins } = await import("./auth-plugins")
+      const result = await addAuthPlugins(testConfig)
+
+      expect(result.success).toBe(true)
+
+      const newContent = readFileSync(result.configPath, "utf-8")
+      expect(newContent).toContain('// "plugin": ["old-plugin"]')
+      expect(newContent).toContain('existing-plugin')
+      expect(newContent).toContain('opencode-antigravity-auth')
+
+      const parsed = parseJsonc<Record<string, unknown>>(newContent)
+      const plugins = parsed.plugin as string[]
+      expect(plugins).toContain('existing-plugin')
+      expect(plugins.some((p) => p.startsWith('opencode-antigravity-auth'))).toBe(true)
+    })
+  })
+
+  describe("Test 2: Plugin array already contains antigravity", () => {
+    it("does not add duplicate", async () => {
+      const content = `{
+  "plugin": ["existing-plugin", "opencode-antigravity-auth"],
+  "provider": {}
+}`
+      writeFileSync(testConfigPath, content, "utf-8")
+
+      const { addAuthPlugins } = await import("./auth-plugins")
+      const result = await addAuthPlugins(testConfig)
+
+      expect(result.success).toBe(true)
+
+      const newContent = readFileSync(testConfigPath, "utf-8")
+      const parsed = parseJsonc<Record<string, unknown>>(newContent)
+      const plugins = parsed.plugin as string[]
+
+      const antigravityCount = plugins.filter((p) => p.startsWith('opencode-antigravity-auth')).length
+      expect(antigravityCount).toBe(1)
+    })
+  })
+
+  describe("Test 3: Backup created before write", () => {
+    it("creates .bak file", async () => {
+      const originalContent = `{
+  "plugin": ["existing-plugin"],
+  "provider": {}
+}`
+      writeFileSync(testConfigPath, originalContent, "utf-8")
+      readFileSync(testConfigPath, "utf-8")
+
+      const { addAuthPlugins } = await import("./auth-plugins")
+      const result = await addAuthPlugins(testConfig)
+
+      expect(result.success).toBe(true)
+      expect(existsSync(`${result.configPath}.bak`)).toBe(true)
+
+      const backupContent = readFileSync(`${result.configPath}.bak`, "utf-8")
+      expect(backupContent).toBe(originalContent)
+    })
+  })
+
+  describe("Test 4: Comment with } character", () => {
+    it("preserves comments with special characters", async () => {
+      const content = `{
+  // This comment has } special characters
+  "plugin": ["existing-plugin"],
+  "provider": {}
+}`
+      writeFileSync(testConfigPath, content, "utf-8")
+
+      const { addAuthPlugins } = await import("./auth-plugins")
+      const result = await addAuthPlugins(testConfig)
+
+      expect(result.success).toBe(true)
+
+      const newContent = readFileSync(testConfigPath, "utf-8")
+      expect(newContent).toContain('// This comment has } special characters')
+
+      expect(() => parseJsonc(newContent)).not.toThrow()
+    })
+  })
+
+  describe("Test 5: Comment containing 'plugin' string", () => {
+    it("must NOT match comment location", async () => {
+      const content = `{
+  // "plugin": ["fake"]
+  "plugin": ["existing-plugin"],
+  "provider": {}
+}`
+      writeFileSync(testConfigPath, content, "utf-8")
+
+      const { addAuthPlugins } = await import("./auth-plugins")
+      const result = await addAuthPlugins(testConfig)
+
+      expect(result.success).toBe(true)
+
+      const newContent = readFileSync(testConfigPath, "utf-8")
+      expect(newContent).toContain('// "plugin": ["fake"]')
+
+      const parsed = parseJsonc<Record<string, unknown>>(newContent)
+      const plugins = parsed.plugin as string[]
+      expect(plugins).toContain('existing-plugin')
+      expect(plugins).not.toContain('fake')
+    })
+  })
+
+  describe("Test 6: No existing plugin array", () => {
+    it("creates plugin array when none exists", async () => {
+      const content = `{
+  "provider": {}
+}`
+      writeFileSync(testConfigPath, content, "utf-8")
+
+      const { addAuthPlugins } = await import("./auth-plugins")
+      const result = await addAuthPlugins(testConfig)
+
+      expect(result.success).toBe(true)
+
+      const newContent = readFileSync(result.configPath, "utf-8")
+
+      const parsed = parseJsonc<Record<string, unknown>>(newContent)
+      expect(parsed).toHaveProperty('plugin')
+      const plugins = parsed.plugin as string[]
+      expect(plugins.some((p) => p.startsWith('opencode-antigravity-auth'))).toBe(true)
+    })
+  })
+
+  describe("Test 7: Post-write validation ensures valid JSONC", () => {
+    it("result file must be valid JSONC", async () => {
+      const content = `{
+  "plugin": ["existing-plugin"],
+  "provider": {}
+}`
+      writeFileSync(testConfigPath, content, "utf-8")
+
+      const { addAuthPlugins } = await import("./auth-plugins")
+      const result = await addAuthPlugins(testConfig)
+
+      expect(result.success).toBe(true)
+
+      const newContent = readFileSync(testConfigPath, "utf-8")
+      expect(() => parseJsonc(newContent)).not.toThrow()
+
+      const parsed = parseJsonc<Record<string, unknown>>(newContent)
+      expect(parsed).toHaveProperty('plugin')
+      expect(parsed).toHaveProperty('provider')
+    })
+  })
+
+  describe("Test 8: Multiple plugins in array", () => {
+    it("appends to existing plugins", async () => {
+      const content = `{
+  "plugin": ["plugin-1", "plugin-2", "plugin-3"],
+  "provider": {}
+}`
+      writeFileSync(testConfigPath, content, "utf-8")
+
+      const { addAuthPlugins } = await import("./auth-plugins")
+      const result = await addAuthPlugins(testConfig)
+
+      expect(result.success).toBe(true)
+
+      const newContent = readFileSync(result.configPath, "utf-8")
+      const parsed = parseJsonc<Record<string, unknown>>(newContent)
+      const plugins = parsed.plugin as string[]
+
+      expect(plugins).toContain('plugin-1')
+      expect(plugins).toContain('plugin-2')
+      expect(plugins).toContain('plugin-3')
+      expect(plugins.some((p) => p.startsWith('opencode-antigravity-auth'))).toBe(true)
+    })
+  })
+})

src/cli/config-manager/auth-plugins.ts

@@ -0,0 +1,145 @@
+import { readFileSync, writeFileSync, copyFileSync, existsSync } from "node:fs"
+import { modify, applyEdits } from "jsonc-parser"
+import type { ConfigMergeResult, InstallConfig } from "../types"
+import { getConfigDir } from "./config-context"
+import { ensureConfigDirectoryExists } from "./ensure-config-directory-exists"
+import { formatErrorWithSuggestion } from "./format-error-with-suggestion"
+import { detectConfigFormat } from "./opencode-config-format"
+import { parseOpenCodeConfigFileWithError, type OpenCodeConfig } from "./parse-opencode-config-file"
+import { parseJsonc } from "../../shared/jsonc-parser"
+
+export async function fetchLatestVersion(packageName: string): Promise<string | null> {
+  try {
+    const res = await fetch(`https://registry.npmjs.org/${encodeURIComponent(packageName)}/latest`)
+    if (!res.ok) return null
+    const data = (await res.json()) as { version: string }
+    return data.version
+  } catch {
+    return null
+  }
+}
+
+export async function addAuthPlugins(config: InstallConfig): Promise<ConfigMergeResult> {
+  try {
+    ensureConfigDirectoryExists()
+  } catch (err) {
+    return {
+      success: false,
+      configPath: getConfigDir(),
+      error: formatErrorWithSuggestion(err, "create config directory"),
+    }
+  }
+
+  const { format, path } = detectConfigFormat()
+  const backupPath = `${path}.bak`
+
+  try {
+    let existingConfig: OpenCodeConfig | null = null
+    if (format !== "none") {
+      const parseResult = parseOpenCodeConfigFileWithError(path)
+      if (parseResult.error && !parseResult.config) {
+        return {
+          success: false,
+          configPath: path,
+          error: `Failed to parse config file: ${parseResult.error}`,
+        }
+      }
+      existingConfig = parseResult.config
+    }
+
+    const rawPlugins = existingConfig?.plugin
+    const plugins: string[] = Array.isArray(rawPlugins) ? rawPlugins : []
+
+    if (config.hasGemini) {
+      const version = await fetchLatestVersion("opencode-antigravity-auth")
+      const pluginEntry = version ? `opencode-antigravity-auth@${version}` : "opencode-antigravity-auth"
+      if (!plugins.some((p) => p.startsWith("opencode-antigravity-auth"))) {
+        plugins.push(pluginEntry)
+      }
+    }
+
+    const newConfig = { ...(existingConfig ?? {}), plugin: plugins }
+
+    if (format !== "none" && existsSync(path)) {
+      copyFileSync(path, backupPath)
+    }
+
+    if (format === "jsonc") {
+      const content = readFileSync(path, "utf-8")
+
+      const newContent = applyEdits(
+        content,
+        modify(content, ["plugin"], plugins, {
+          formattingOptions: { tabSize: 2, insertSpaces: true },
+        })
+      )
+
+      try {
+        parseJsonc(newContent)
+      } catch (error) {
+        if (existsSync(backupPath)) {
+          copyFileSync(backupPath, path)
+        }
+        throw new Error(`Generated JSONC is invalid: ${error instanceof Error ? error.message : String(error)}`)
+      }
+
+      try {
+        writeFileSync(path, newContent)
+      } catch (error) {
+        const hasBackup = existsSync(backupPath)
+        try {
+          if (hasBackup) {
+            copyFileSync(backupPath, path)
+          }
+        } catch (restoreError) {
+          return {
+            success: false,
+            configPath: path,
+            error: `Failed to write config file, and restore from backup failed: ${String(error)}; restore error: ${String(restoreError)}`,
+          }
+        }
+
+        return {
+          success: false,
+          configPath: path,
+          error: hasBackup
+            ? `Failed to write config file. Restored from backup: ${String(error)}`
+            : `Failed to write config file. No backup was available: ${String(error)}`,
+        }
+      }
+    } else {
+      const nextContent = JSON.stringify(newConfig, null, 2) + "\n"
+      try {
+        writeFileSync(path, nextContent)
+      } catch (error) {
+        const hasBackup = existsSync(backupPath)
+        try {
+          if (hasBackup) {
+            copyFileSync(backupPath, path)
+          }
+        } catch (restoreError) {
+          return {
+            success: false,
+            configPath: path,
+            error: `Failed to write config file, and restore from backup failed: ${String(error)}; restore error: ${String(restoreError)}`,
+          }
+        }
+
+        return {
+          success: false,
+          configPath: path,
+          error: hasBackup
+            ? `Failed to write config file. Restored from backup: ${String(error)}`
+            : `Failed to write config file. No backup was available: ${String(error)}`,
+        }
+      }
+    }
+    return { success: true, configPath: path }
+  } catch (err) {
+    return {
+      success: false,
+      configPath: path,
+      error: formatErrorWithSuggestion(err, "add auth plugins to config"),
+    }
+  }
+}

src/cli/config-manager/bun-install.ts

@@ -0,0 +1,61 @@
+import { getConfigDir } from "./config-context"
+
+const BUN_INSTALL_TIMEOUT_SECONDS = 60
+const BUN_INSTALL_TIMEOUT_MS = BUN_INSTALL_TIMEOUT_SECONDS * 1000
+
+export interface BunInstallResult {
+  success: boolean
+  timedOut?: boolean
+  error?: string
+}
+
+export async function runBunInstall(): Promise<boolean> {
+  const result = await runBunInstallWithDetails()
+  return result.success
+}
+
+export async function runBunInstallWithDetails(): Promise<BunInstallResult> {
+  try {
+    const proc = Bun.spawn(["bun", "install"], {
+      cwd: getConfigDir(),
+      stdout: "inherit",
+      stderr: "inherit",
+    })
+
+    let timeoutId: ReturnType<typeof setTimeout>
+    const timeoutPromise = new Promise<"timeout">((resolve) => {
+      timeoutId = setTimeout(() => resolve("timeout"), BUN_INSTALL_TIMEOUT_MS)
+    })
+    const exitPromise = proc.exited.then(() => "completed" as const)
+    const result = await Promise.race([exitPromise, timeoutPromise])
+    clearTimeout(timeoutId!)
+
+    if (result === "timeout") {
+      try {
+        proc.kill()
+      } catch {
+        /* intentionally empty - process may have already exited */
+      }
+      return {
+        success: false,
+        timedOut: true,
+        error: `bun install timed out after ${BUN_INSTALL_TIMEOUT_SECONDS} seconds. Try running manually: cd ${getConfigDir()} && bun i`,
+      }
+    }
+
+    if (proc.exitCode !== 0) {
+      return {
+        success: false,
+        error: `bun install failed with exit code ${proc.exitCode}`,
+      }
+    }
+
+    return { success: true }
+  } catch (err) {
+    const message = err instanceof Error ? err.message : String(err)
+    return {
+      success: false,
+      error: `bun install failed: ${message}. Is bun installed? Try: curl -fsSL https://bun.sh/install | bash`,
+    }
+  }
+}