diff --git a/AGENTS.md b/AGENTS.md
index d1183fb48..5ebc9a186 100644
--- a/AGENTS.md
+++ b/AGENTS.md
@@ -1,7 +1,7 @@
 # PROJECT KNOWLEDGE BASE
 
-**Generated:** 2026-02-03T16:10:30+09:00
-**Commit:** d7679e14
+**Generated:** 2026-02-06T18:30:00+09:00
+**Commit:** c6c149e
 **Branch:** dev
 
 ---
@@ -120,40 +120,45 @@ This is an **international open-source project**. To ensure accessibility and ma
 
 ## OVERVIEW
 
-OpenCode plugin: multi-model agent orchestration (Claude Opus 4.5, GPT-5.2, Gemini 3 Flash). 41 lifecycle hooks, 20+ tools (LSP, AST-Grep, delegation), 11 specialized agents, full Claude Code compatibility. "oh-my-zsh" for OpenCode.
+OpenCode plugin: multi-model agent orchestration (Claude Opus 4.6, GPT-5.3 Codex, Gemini 3 Flash). 40+ lifecycle hooks, 25+ tools (LSP, AST-Grep, delegation), 11 specialized agents, full Claude Code compatibility. "oh-my-zsh" for OpenCode.
 
 ## STRUCTURE
 
 ```
 oh-my-opencode/
 ├── src/
-│   ├── agents/        # 11 AI agents - see src/agents/AGENTS.md
-│   ├── hooks/         # 41 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/            # 40+ lifecycle hooks - see src/hooks/AGENTS.md
+│   ├── tools/            # 25+ tools - see src/tools/AGENTS.md
+│   ├── features/         # Background agents, skills, 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 (schema.ts 455 lines), TypeScript types
+│   ├── plugin-handlers/  # Plugin config loading (config-handler.ts 501 lines)
+│   ├── index.ts          # Main plugin entry (924 lines)
+│   ├── plugin-config.ts  # Config loading orchestration
+│   └── plugin-state.ts   # Model cache state
+├── script/               # build-schema.ts, build-binaries.ts, publish.ts
+├── packages/             # 11 platform-specific binaries
+└── dist/                 # Build output (ESM + .d.ts)
 ```
 
 ## WHERE TO LOOK
 
 | Task | Location | Notes |
 |------|----------|-------|
-| Add agent | `src/agents/` | Create .ts with factory, add to `agentSources` |
+| Add agent | `src/agents/` | Create .ts with factory, add to `agentSources` in utils.ts |
 | Add hook | `src/hooks/` | Create dir with `createXXXHook()`, register in index.ts |
 | Add tool | `src/tools/` | Dir with index/types/constants/tools.ts |
-| Add MCP | `src/mcp/` | Create config, add to index.ts |
+| Add MCP | `src/mcp/` | Create config, add to `createBuiltinMcps()` |
 | Add skill | `src/features/builtin-skills/` | Create dir with SKILL.md |
 | 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) |
+| Plugin config | `src/plugin-handlers/config-handler.ts` | JSONC loading, merging, migration |
+| Background agents | `src/features/background-agent/` | manager.ts (1556 lines) |
+| Orchestrator | `src/hooks/atlas/` | Main orchestration hook (770 lines) |
+| Delegation | `src/tools/delegate-task/` | Category routing (executor.ts 983 lines) |
 
 ## TDD (Test-Driven Development)
 
@@ -165,7 +170,7 @@ 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)
+- Test file: `*.test.ts` alongside source (100+ test files)
 - BDD comments: `//#given`, `//#when`, `//#then`
 
 ## CONVENTIONS
@@ -175,7 +180,7 @@ 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, 100+ test files
 - **Temperature**: 0.1 for code agents, max 0.3
 
 ## ANTI-PATTERNS
@@ -222,7 +227,7 @@ 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               # 100+ test files
 ```
 
 ## DEPLOYMENT
@@ -236,30 +241,38 @@ bun test               # 100 test files
 
 | File | Lines | Description |
 |------|-------|-------------|
-| `src/features/builtin-skills/skills.ts` | 29 | Skill definitions |
-| `src/features/background-agent/manager.ts` | 1418 | Task lifecycle, concurrency |
-| `src/agents/prometheus/` | 1492 | 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/features/background-agent/manager.ts` | 1556 | Task lifecycle, concurrency |
+| `src/features/builtin-skills/skills/git-master.ts` | 1107 | Git master skill definition |
+| `src/tools/delegate-task/executor.ts` | 983 | Category-based delegation executor |
+| `src/index.ts` | 924 | Main plugin entry |
+| `src/tools/lsp/client.ts` | 803 | LSP client operations |
+| `src/hooks/atlas/index.ts` | 770 | Orchestrator hook |
+| `src/tools/background-task/tools.ts` | 734 | Background task tools |
 | `src/cli/config-manager.ts` | 667 | JSONC config parsing |
+| `src/features/skill-mcp-manager/manager.ts` | 640 | MCP client lifecycle |
 | `src/features/builtin-commands/templates/refactor.ts` | 619 | Refactor command template |
+| `src/agents/hephaestus.ts` | 618 | Autonomous deep worker agent |
+| `src/tools/delegate-task/constants.ts` | 552 | Delegation constants |
+| `src/cli/install.ts` | 542 | Interactive CLI installer |
+| `src/agents/sisyphus.ts` | 530 | Main orchestrator agent |
 
 ## MCP ARCHITECTURE
 
 Three-tier system:
-1. **Built-in**: websearch (Exa), context7 (docs), grep_app (GitHub)
+1. **Built-in**: websearch (Exa/Tavily), context7 (docs), grep_app (GitHub)
 2. **Claude Code compat**: .mcp.json with `${VAR}` expansion
 3. **Skill-embedded**: YAML frontmatter in skills
 
 ## CONFIG SYSTEM
 
-- **Zod validation**: `src/config/schema.ts`
+- **Zod validation**: `src/config/schema.ts` (455 lines)
 - **JSONC support**: Comments, trailing commas
 - **Multi-level**: Project (`.opencode/`) → User (`~/.config/opencode/`)
+- **Loading**: `src/plugin-handlers/config-handler.ts` → merge → validate
 
 ## NOTES
 
 - **OpenCode**: Requires >= 1.0.150
 - **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
diff --git a/src/agents/AGENTS.md b/src/agents/AGENTS.md
index 539ddb7a5..ff1dec185 100644
--- a/src/agents/AGENTS.md
+++ b/src/agents/AGENTS.md
@@ -15,32 +15,32 @@
 agents/
 ├── atlas/                      # Master Orchestrator (holds todo list)
 │   ├── index.ts
-│   ├── default.ts
-│   ├── gpt.ts
+│   ├── default.ts              # Claude-optimized prompt (390 lines)
+│   ├── gpt.ts                  # GPT-optimized prompt (330 lines)
 │   └── utils.ts
-├── sisyphus.ts                 # Main prompt (SF Bay Area engineer identity)
-├── hephaestus.ts               # Autonomous Deep Worker (GPT 5.2 Codex, "The Legitimate Craftsman")
+├── prometheus/                 # Planning Agent (Interview/Consultant mode)
+│   ├── index.ts
+│   ├── plan-template.ts        # Work plan structure (423 lines)
+│   ├── interview-mode.ts       # Interview flow (335 lines)
+│   ├── plan-generation.ts
+│   ├── high-accuracy-mode.ts
+│   ├── identity-constraints.ts # Identity rules (301 lines)
+│   └── behavioral-summary.ts
 ├── sisyphus-junior/            # Delegated task executor (category-spawned)
 │   ├── index.ts
 │   ├── default.ts
 │   └── gpt.ts
+├── sisyphus.ts                 # Main orchestrator prompt (530 lines)
+├── hephaestus.ts               # Autonomous deep worker (618 lines, GPT 5.3 Codex)
 ├── oracle.ts                   # Strategic advisor (GPT-5.2)
-├── librarian.ts                # Multi-repo research (GitHub CLI, Context7)
-├── explore.ts                  # Fast contextual grep (Grok Code Fast)
+├── librarian.ts                # Multi-repo research (328 lines)
+├── explore.ts                  # Fast contextual grep
 ├── multimodal-looker.ts        # Media analyzer (Gemini 3 Flash)
-├── prometheus/                 # Planning (Interview/Consultant mode)
-│   ├── index.ts
-│   ├── plan-template.ts
-│   ├── interview-mode.ts
-│   ├── plan-generation.ts
-│   ├── high-accuracy-mode.ts
-│   ├── identity-constraints.ts
-│   └── behavioral-summary.ts
-├── metis.ts                    # Pre-planning analysis (Gap detection)
-├── momus.ts                    # Plan reviewer (Ruthless fault-finding)
-├── dynamic-agent-prompt-builder.ts  # Dynamic prompt generation
+├── metis.ts                    # Pre-planning analysis (347 lines)
+├── momus.ts                    # Plan reviewer
+├── dynamic-agent-prompt-builder.ts  # Dynamic prompt generation (431 lines)
 ├── types.ts                    # AgentModelConfig, AgentPromptMetadata
-├── utils.ts                    # createBuiltinAgents(), resolveModelWithFallback()
+├── utils.ts                    # createBuiltinAgents(), resolveModelWithFallback() (485 lines)
 └── index.ts                    # builtinAgents export
 ```
 
@@ -73,15 +73,17 @@ agents/
 | explore | write, edit, task, delegate_task, call_omo_agent |
 | multimodal-looker | Allowlist: read only |
 | Sisyphus-Junior | task, delegate_task |
+| Atlas | task, call_omo_agent |
 
 ## 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.
+- **Metadata**: `XXX_PROMPT_METADATA` with category, cost, triggers
+- **Tool restrictions**: `createAgentToolRestrictions(tools)` or `createAgentToolAllowlist(tools)`
+- **Thinking**: 32k budget tokens for Sisyphus, Oracle, Prometheus, Atlas
+- **Model-specific routing**: Atlas, Sisyphus-Junior have GPT vs Claude prompt variants
 
 ## 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 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
diff --git a/src/cli/AGENTS.md b/src/cli/AGENTS.md
index 7b951faaf..eced5d811 100644
--- a/src/cli/AGENTS.md
+++ b/src/cli/AGENTS.md
@@ -2,25 +2,25 @@
 
 ## OVERVIEW
 
-CLI entry: `bunx oh-my-opencode`. 4 commands with Commander.js + @clack/prompts TUI.
+CLI entry: `bunx oh-my-opencode`. 5 commands with Commander.js + @clack/prompts TUI.
 
-**Commands**: install (interactive setup), doctor (14 health checks), run (session launcher), get-local-version
+**Commands**: install (interactive setup), doctor (14 health checks), run (session launcher), get-local-version, mcp-oauth
 
 ## STRUCTURE
 
 ```
 cli/
-├── index.ts              # Commander.js entry (4 commands)
+├── index.ts              # Commander.js entry (5 commands)
 ├── install.ts            # Interactive TUI (542 lines)
 ├── config-manager.ts     # JSONC parsing (667 lines)
-├── types.ts              # InstallArgs, InstallConfig
 ├── model-fallback.ts     # Model fallback configuration
+├── types.ts              # InstallArgs, InstallConfig
 ├── doctor/
 │   ├── index.ts          # Doctor entry
 │   ├── runner.ts         # Check orchestration
 │   ├── formatter.ts      # Colored output
 │   ├── constants.ts      # Check IDs, symbols
-│   ├── types.ts          # CheckResult, CheckDefinition (114 lines)
+│   ├── types.ts          # CheckResult, CheckDefinition
 │   └── checks/           # 14 checks, 23 files
 │       ├── version.ts    # OpenCode + plugin version
 │       ├── config.ts     # JSONC validity, Zod
@@ -28,10 +28,11 @@ cli/
 │       ├── dependencies.ts # AST-Grep, Comment Checker
 │       ├── lsp.ts        # LSP connectivity
 │       ├── mcp.ts        # MCP validation
-│       ├── model-resolution.ts # Model resolution check
+│       ├── model-resolution.ts # Model resolution check (323 lines)
 │       └── gh.ts         # GitHub CLI
 ├── run/
-│   └── index.ts          # Session launcher
+│   ├── index.ts          # Session launcher
+│   └── events.ts         # CLI run events (325 lines)
 ├── mcp-oauth/
 │   └── index.ts          # MCP OAuth flow
 └── get-local-version/
@@ -46,6 +47,7 @@ cli/
 | `doctor` | 14 health checks for diagnostics |
 | `run` | Launch session with todo enforcement |
 | `get-local-version` | Version detection and update check |
+| `mcp-oauth` | MCP OAuth authentication flow |
 
 ## DOCTOR CATEGORIES (14 Checks)
 
diff --git a/src/features/AGENTS.md b/src/features/AGENTS.md
index 695fd0e89..4cb9cc47b 100644
--- a/src/features/AGENTS.md
+++ b/src/features/AGENTS.md
@@ -2,7 +2,7 @@
 
 ## OVERVIEW
 
-20 feature modules: background agents, skill MCPs, builtin skills/commands, Claude Code compatibility layer.
+17 feature modules: background agents, skill MCPs, builtin skills/commands, Claude Code compatibility layer, task management.
 
 **Feature Types**: Task orchestration, Skill definitions, Command templates, Claude Code loaders, Supporting utilities
 
@@ -10,27 +10,25 @@
 
 ```
 features/
-├── background-agent/           # Task lifecycle (1418 lines)
+├── background-agent/           # Task lifecycle (1556 lines)
 │   ├── manager.ts              # Launch → poll → complete
 │   └── concurrency.ts          # Per-provider limits
-├── builtin-skills/             # Core skills (1729 lines)
-│   └── skills.ts               # playwright, agent-browser, frontend-ui-ux, git-master, dev-browser
+├── builtin-skills/             # Core skills
+│   └── skills/                 # playwright, agent-browser, frontend-ui-ux, git-master, dev-browser
 ├── builtin-commands/           # ralph-loop, refactor, ulw-loop, init-deep, start-work, cancel-ralph, stop-continuation
 ├── claude-code-agent-loader/   # ~/.claude/agents/*.md
 ├── claude-code-command-loader/ # ~/.claude/commands/*.md
 ├── claude-code-mcp-loader/     # .mcp.json with ${VAR} expansion
-├── claude-code-plugin-loader/  # installed_plugins.json
+├── claude-code-plugin-loader/  # installed_plugins.json (486 lines)
 ├── claude-code-session-state/  # Session persistence
-├── opencode-skill-loader/      # Skills from 6 directories
+├── opencode-skill-loader/      # Skills from 6 directories (loader.ts 311 lines)
 ├── context-injector/           # AGENTS.md/README.md injection
 ├── boulder-state/              # Todo state persistence
 ├── hook-message-injector/      # Message injection
 ├── task-toast-manager/         # Background task notifications
-├── skill-mcp-manager/          # MCP client lifecycle (617 lines)
-├── tmux-subagent/              # Tmux session management
+├── skill-mcp-manager/          # MCP client lifecycle (640 lines)
+├── tmux-subagent/              # Tmux session management (472 lines)
 ├── mcp-oauth/                  # MCP OAuth handling
-├── sisyphus-swarm/             # Swarm coordination
-├── sisyphus-tasks/             # Task tracking
 └── claude-tasks/               # Task schema/storage - see AGENTS.md
 ```
 
diff --git a/src/features/claude-tasks/AGENTS.md b/src/features/claude-tasks/AGENTS.md
index 4b152a2d4..3c0c140d1 100644
--- a/src/features/claude-tasks/AGENTS.md
+++ b/src/features/claude-tasks/AGENTS.md
@@ -12,6 +12,7 @@ claude-tasks/
 ├── types.test.ts     # Schema validation tests (8 tests)
 ├── storage.ts        # File operations
 ├── storage.test.ts   # Storage tests (14 tests)
+├── todo-sync.ts      # Task → Todo synchronization
 └── index.ts          # Barrel exports
 ```
 
@@ -44,86 +45,21 @@ interface Task {
 
 ## TODO SYNC
 
-The task system includes a sync layer (`todo-sync.ts`) that automatically mirrors task state to the project's Todo system.
+Task system includes sync layer (`todo-sync.ts`) that automatically mirrors task state to the project's Todo system.
 
-- **Creation**: Creating a task via `task_create` adds a corresponding item to the Todo list.
-- **Updates**: Updating a task's `status` or `subject` via `task_update` reflects in the Todo list.
-- **Completion**: Marking a task as `completed` automatically marks the Todo item as done.
+- **Creation**: `task_create` adds corresponding Todo item
+- **Updates**: `task_update` reflects in Todo list
+- **Completion**: `completed` status marks Todo item done
 
 ## STORAGE UTILITIES
 
-### getTaskDir(config)
-
-Returns the task storage directory path.
-
-**Default behavior (no config override):**
-Returns `~/.config/opencode/tasks/<task-list-id>/` where:
-- Task list ID is resolved via `resolveTaskListId()`
-
-**With `storage_path` config:**
-- Absolute paths (starting with `/`) are returned as-is
-- Relative paths are joined with `process.cwd()`
-
-### resolveTaskListId(config)
-
-Resolves the task list ID for directory scoping.
-
-**Priority order:**
-1. `ULTRAWORK_TASK_LIST_ID` environment variable
-2. `config.sisyphus?.tasks?.task_list_id` config option
-3. Sanitized `basename(process.cwd())` as fallback
-
-**Sanitization:** Replaces non-alphanumeric characters (except `-` and `_`) with `-`
-
-### readJsonSafe(filePath, schema)
-
-- Returns parsed & validated data or `null`
-- Safe for missing files, invalid JSON, schema violations
-
-### writeJsonAtomic(filePath, data)
-
-- Atomic write via temp file + rename
-- Creates parent directories automatically
-- Cleans up temp file on error
-
-### acquireLock(dirPath)
-
-- File-based lock: `.lock` file with timestamp
-- 30-second stale threshold
-- Returns `{ acquired: boolean, release: () => void }`
-
-## TESTING
-
-**types.test.ts** (8 tests):
-- Valid status enum values
-- Required vs optional fields
-- Array validation (blocks, blockedBy)
-- Schema rejection for invalid data
-
-**storage.test.ts** (14 tests):
-- Path construction
-- Safe JSON reading (missing files, invalid JSON, schema failures)
-- Atomic writes (directory creation, overwrites)
-- Lock acquisition (fresh locks, stale locks, release)
-
-## USAGE
-
-```typescript
-import { TaskSchema, getTaskDir, readJsonSafe, writeJsonAtomic, acquireLock } from "./features/claude-tasks"
-
-const taskDir = getTaskDir(config)
-const lock = acquireLock(taskDir)
-
-try {
-  const task = readJsonSafe(join(taskDir, "1.json"), TaskSchema)
-  if (task) {
-    task.status = "completed"
-    writeJsonAtomic(join(taskDir, "1.json"), task)
-  }
-} finally {
-  lock.release()
-}
-```
+| Function | Purpose |
+|----------|---------|
+| `getTaskDir(config)` | Returns task storage directory path |
+| `resolveTaskListId(config)` | Resolves task list ID (env → config → cwd basename) |
+| `readJsonSafe(path, schema)` | Parse + validate, returns null on failure |
+| `writeJsonAtomic(path, data)` | Atomic write via temp file + rename |
+| `acquireLock(dirPath)` | File-based lock with 30s stale threshold |
 
 ## ANTI-PATTERNS
 
diff --git a/src/hooks/AGENTS.md b/src/hooks/AGENTS.md
index 25f8de788..a23b677e1 100644
--- a/src/hooks/AGENTS.md
+++ b/src/hooks/AGENTS.md
@@ -2,7 +2,7 @@
 
 ## OVERVIEW
 
-41 lifecycle hooks intercepting/modifying agent behavior across 5 events.
+40+ lifecycle hooks intercepting/modifying agent behavior across 5 events.
 
 **Event Types**:
 - `UserPromptSubmit` (`chat.message`) - Can block
@@ -14,10 +14,10 @@
 ## STRUCTURE
 ```
 hooks/
-├── atlas/                      # Main orchestration (757 lines)
+├── atlas/                      # Main orchestration (770 lines)
 ├── anthropic-context-window-limit-recovery/ # Auto-summarize
-├── todo-continuation-enforcer.ts # Force TODO completion
-├── ralph-loop/                 # Self-referential dev loop
+├── todo-continuation-enforcer.ts # Force TODO completion (517 lines)
+├── ralph-loop/                 # Self-referential dev loop (428 lines)
 ├── claude-code-hooks/          # settings.json compat layer - see AGENTS.md
 ├── comment-checker/            # Prevents AI slop
 ├── auto-slash-command/         # Detects /command patterns
@@ -27,13 +27,14 @@ hooks/
 ├── edit-error-recovery/        # Recovers from failures
 ├── thinking-block-validator/   # Ensures valid <thinking>
 ├── context-window-monitor.ts   # Reminds of headroom
-├── session-recovery/           # Auto-recovers from crashes
+├── session-recovery/           # Auto-recovers from crashes (436 lines)
+├── session-notification.ts     # Session event notifications (337 lines)
 ├── think-mode/                 # Dynamic thinking budget
 ├── keyword-detector/           # ultrawork/search/analyze modes
 ├── background-notification/    # OS notification
 ├── prometheus-md-only/         # Planner read-only mode
 ├── agent-usage-reminder/       # Specialized agent hints
-├── auto-update-checker/        # Plugin update check
+├── auto-update-checker/        # Plugin update check (304 lines)
 ├── tool-output-truncator.ts    # Prevents context bloat
 ├── compaction-context-injector/ # Injects context on compaction
 ├── delegate-task-retry/        # Retries failed delegations
@@ -47,6 +48,11 @@ hooks/
 ├── sisyphus-junior-notepad/    # Sisyphus Junior notepad
 ├── stop-continuation-guard/    # Guards stop continuation
 ├── subagent-question-blocker/  # Blocks subagent questions
+├── task-reminder/              # Task progress reminders
+├── tasks-todowrite-disabler/   # Disables TodoWrite when task system active
+├── unstable-agent-babysitter/  # Monitors unstable agent behavior
+├── write-existing-file-guard/  # Guards against overwriting existing files
+├── preemptive-compaction.ts    # Preemptive context compaction
 └── index.ts                    # Hook aggregation + registration
 ```
 
@@ -61,8 +67,8 @@ hooks/
 
 ## EXECUTION ORDER
 - **UserPromptSubmit**: keywordDetector → claudeCodeHooks → autoSlashCommand → startWork
-- **PreToolUse**: subagentQuestionBlocker → questionLabelTruncator → claudeCodeHooks → nonInteractiveEnv → commentChecker → directoryAgentsInjector → directoryReadmeInjector → rulesInjector → prometheusMdOnly → sisyphusJuniorNotepad → atlasHook
-- **PostToolUse**: claudeCodeHooks → toolOutputTruncator → contextWindowMonitor → commentChecker → directoryAgentsInjector → directoryReadmeInjector → rulesInjector → emptyTaskResponseDetector → agentUsageReminder → interactiveBashSession → editErrorRecovery → delegateTaskRetry → atlasHook → taskResumeInfo
+- **PreToolUse**: subagentQuestionBlocker → questionLabelTruncator → claudeCodeHooks → nonInteractiveEnv → commentChecker → directoryAgentsInjector → directoryReadmeInjector → rulesInjector → prometheusMdOnly → sisyphusJuniorNotepad → writeExistingFileGuard → atlasHook
+- **PostToolUse**: claudeCodeHooks → toolOutputTruncator → contextWindowMonitor → commentChecker → directoryAgentsInjector → directoryReadmeInjector → rulesInjector → emptyTaskResponseDetector → agentUsageReminder → interactiveBashSession → editErrorRecovery → delegateTaskRetry → atlasHook → taskResumeInfo → taskReminder
 
 ## HOW TO ADD
 1. Create `src/hooks/name/` with `index.ts` exporting `createMyHook(ctx)`
diff --git a/src/hooks/claude-code-hooks/AGENTS.md b/src/hooks/claude-code-hooks/AGENTS.md
index 0f021ecbf..ca0d1927d 100644
--- a/src/hooks/claude-code-hooks/AGENTS.md
+++ b/src/hooks/claude-code-hooks/AGENTS.md
@@ -4,12 +4,12 @@
 
 Full Claude Code `settings.json` hook compatibility layer. Intercepts OpenCode events to execute external scripts/commands.
 
-**Config Sources** (priority): `.claude/settings.json` (project) > `~/.claude/settings.json` (global)
+**Config Sources** (priority): `.claude/settings.local.json` > `.claude/settings.json` (project) > `~/.claude/settings.json` (global)
 
 ## STRUCTURE
 ```
 claude-code-hooks/
-├── index.ts              # Main factory (401 lines)
+├── index.ts              # Main factory (421 lines)
 ├── config.ts             # Loads ~/.claude/settings.json
 ├── config-loader.ts      # Extended config (disabledHooks)
 ├── pre-tool-use.ts       # PreToolUse executor
@@ -19,6 +19,7 @@ claude-code-hooks/
 ├── pre-compact.ts        # PreCompact executor
 ├── transcript.ts         # Tool use recording
 ├── tool-input-cache.ts   # Pre→post input caching
+├── todo.ts               # Todo integration
 └── types.ts              # Hook & IO type definitions
 ```
 
@@ -31,22 +32,16 @@ claude-code-hooks/
 | Stop | Session idle/end | Inject | sessionId, parentSessionId, cwd |
 | PreCompact | Before summarize | No | sessionId, cwd |
 
-## CONFIG SOURCES
-Priority (highest first):
-1. `.claude/settings.local.json` (Project-local, git-ignored)
-2. `.claude/settings.json` (Project)
-3. `~/.claude/settings.json` (Global user)
-
 ## HOOK EXECUTION
-- **Matchers**: Hooks filter by tool name or event type via regex/glob.
-- **Commands**: Executed via subprocess with env vars (`$SESSION_ID`, `$TOOL_NAME`).
+- **Matchers**: Hooks filter by tool name or event type via regex/glob
+- **Commands**: Executed via subprocess with env vars (`$SESSION_ID`, `$TOOL_NAME`)
 - **Exit Codes**:
   - `0`: Pass (Success)
   - `1`: Warn (Continue with system message)
   - `2`: Block (Abort operation/prompt)
 
 ## ANTI-PATTERNS
-- **Heavy PreToolUse**: Runs before EVERY tool; keep logic light to avoid latency.
-- **Blocking non-critical**: Prefer PostToolUse warnings for non-fatal issues.
-- **Direct state mutation**: Use `updatedInput` in PreToolUse instead of side effects.
-- **Ignoring Exit Codes**: Ensure scripts return `2` to properly block sensitive tools.
+- **Heavy PreToolUse**: Runs before EVERY tool; keep logic light to avoid latency
+- **Blocking non-critical**: Prefer PostToolUse warnings for non-fatal issues
+- **Direct state mutation**: Use `updatedInput` in PreToolUse instead of side effects
+- **Ignoring Exit Codes**: Ensure scripts return `2` to properly block sensitive tools
diff --git a/src/mcp/AGENTS.md b/src/mcp/AGENTS.md
index 478a03841..5253a823b 100644
--- a/src/mcp/AGENTS.md
+++ b/src/mcp/AGENTS.md
@@ -14,7 +14,7 @@ Tier 1 of three-tier MCP system: 3 built-in remote HTTP MCPs.
 ```
 mcp/
 ├── index.ts        # createBuiltinMcps() factory
-├── websearch.ts    # Exa AI web search
+├── websearch.ts    # Exa AI / Tavily web search
 ├── context7.ts     # Library documentation
 ├── grep-app.ts     # GitHub code search
 ├── types.ts        # McpNameSchema
@@ -26,26 +26,16 @@ mcp/
 | Name | URL | Purpose | Auth |
 |------|-----|---------|------|
 | websearch | mcp.exa.ai / mcp.tavily.com | Real-time web search | EXA_API_KEY / TAVILY_API_KEY |
-| context7 | mcp.context7.com/mcp | Library docs | CONTEXT7_API_KEY |
+| context7 | mcp.context7.com/mcp | Library docs | CONTEXT7_API_KEY (optional) |
 | grep_app | mcp.grep.app | GitHub code search | None |
 
-## THREE-TIER MCP SYSTEM
-
-1. **Built-in** (this directory): websearch, context7, grep_app
-2. **Claude Code compat**: `.mcp.json` with `${VAR}` expansion
-3. **Skill-embedded**: YAML frontmatter in skills (handled by skill-mcp-manager)
-
 ## Websearch Provider Configuration
 
-The `websearch` MCP supports multiple providers. Exa is the default for backward compatibility and works without an API key.
-
 | Provider | URL | Auth | API Key Required |
 |----------|-----|------|------------------|
 | exa (default) | mcp.exa.ai | x-api-key header | No (optional) |
 | tavily | mcp.tavily.com | Authorization Bearer | Yes |
 
-### Configuration Example
-
 ```jsonc
 {
   "websearch": {
@@ -54,17 +44,6 @@ The `websearch` MCP supports multiple providers. Exa is the default for backward
 }
 ```
 
-### Environment Variables
-
-- `EXA_API_KEY`: Optional. Used when provider is `exa`.
-- `TAVILY_API_KEY`: Required when provider is `tavily`.
-
-### Priority and Behavior
-
-- **Default**: Exa is used if no provider is specified.
-- **Backward Compatibility**: Existing setups using `EXA_API_KEY` continue to work without changes.
-- **Validation**: Selecting `tavily` without providing `TAVILY_API_KEY` will result in a configuration error.
-
 ## CONFIG PATTERN
 
 ```typescript
@@ -77,15 +56,6 @@ export const mcp_name = {
 }
 ```
 
-## USAGE
-
-```typescript
-import { createBuiltinMcps } from "./mcp"
-
-const mcps = createBuiltinMcps()  // Enable all
-const mcps = createBuiltinMcps(["websearch"])  // Disable specific
-```
-
 ## HOW TO ADD
 
 1. Create `src/mcp/my-mcp.ts`
@@ -96,6 +66,5 @@ const mcps = createBuiltinMcps(["websearch"])  // Disable specific
 
 - **Remote only**: HTTP/SSE, no stdio
 - **Disable**: User can set `disabled_mcps: ["name"]` in config
-- **Context7**: Optional auth using `CONTEXT7_API_KEY` env var
-- **Exa**: Optional auth using `EXA_API_KEY` env var
+- **Exa**: Default provider, works without API key
 - **Tavily**: Requires `TAVILY_API_KEY` env var
diff --git a/src/shared/AGENTS.md b/src/shared/AGENTS.md
index b40e7906b..ed5aa349d 100644
--- a/src/shared/AGENTS.md
+++ b/src/shared/AGENTS.md
@@ -9,12 +9,14 @@
 ## STRUCTURE
 ```
 shared/
-├── tmux/                  # Tmux TUI integration (types, utils, constants)
+├── tmux/                  # Tmux TUI integration (types, utils 312 lines, constants)
 ├── logger.ts              # File-based logging (/tmp/oh-my-opencode.log) - 53 imports
 ├── dynamic-truncator.ts   # Token-aware context window management (194 lines)
 ├── model-resolver.ts      # 3-step resolution (Override → Fallback → Default)
 ├── model-requirements.ts  # Agent/category model fallback chains (162 lines)
-├── model-availability.ts  # Provider model fetching & fuzzy matching (154 lines)
+├── model-availability.ts  # Provider model fetching & fuzzy matching (357 lines)
+├── model-sanitizer.ts     # Model name sanitization
+├── model-suggestion-retry.ts # Model suggestion on failure
 ├── jsonc-parser.ts        # JSONC parsing with comment support
 ├── frontmatter.ts         # YAML frontmatter extraction (JSON_SCHEMA only) - 9 imports
 ├── data-path.ts           # XDG-compliant storage resolution
@@ -22,16 +24,26 @@ shared/
 ├── claude-config-dir.ts   # ~/.claude resolution - 9 imports
 ├── migration.ts           # Legacy config migration logic (231 lines)
 ├── opencode-version.ts    # Semantic version comparison
-├── permission-compat.ts   # Agent tool restriction enforcement
-├── system-directive.ts    # Unified system message prefix & types
+├── permission-compat.ts   # Agent tool restriction enforcement - 6 imports
+├── system-directive.ts    # Unified system message prefix & types - 8 imports
 ├── session-utils.ts       # Session cursor, orchestrator detection
+├── session-cursor.ts      # Session message cursor tracking
 ├── shell-env.ts           # Cross-platform shell environment
 ├── agent-variant.ts       # Agent variant from config
 ├── zip-extractor.ts       # Binary/Resource ZIP extraction
 ├── deep-merge.ts          # Recursive object merging (proto-pollution safe, MAX_DEPTH=50)
 ├── case-insensitive.ts    # Case-insensitive object lookups
-├── session-cursor.ts      # Session message cursor tracking
 ├── command-executor.ts    # Shell command execution (225 lines)
+├── snake-case.ts          # Case conversion utilities
+├── tool-name.ts           # Tool naming conventions
+├── pattern-matcher.ts     # Pattern matching utilities
+├── port-utils.ts          # Port management
+├── file-utils.ts          # File operation utilities
+├── file-reference-resolver.ts # File reference resolution
+├── connected-providers-cache.ts # Provider caching
+├── external-plugin-detector.ts  # Plugin detection
+├── first-message-variant.ts     # Message variant types
+├── opencode-server-auth.ts      # Authentication utilities
 └── index.ts               # Barrel export for all utilities
 ```
 
diff --git a/src/tools/AGENTS.md b/src/tools/AGENTS.md
index fb7718749..5313b9389 100644
--- a/src/tools/AGENTS.md
+++ b/src/tools/AGENTS.md
@@ -2,9 +2,9 @@
 
 ## OVERVIEW
 
-20+ tools across 7 categories. Two patterns: Direct ToolDefinition (static) and Factory Function (context-dependent).
+25+ tools across 8 categories. Two patterns: Direct ToolDefinition (static) and Factory Function (context-dependent).
 
-**Categories**: LSP (6), AST-Grep (2), Search (2), Session (4), Agent delegation (2), Background (2), Skill (3)
+**Categories**: LSP (6), AST-Grep (2), Search (2), Session (4), Task (4), Agent delegation (2), Background (2), Skill (3), System (2)
 
 ## STRUCTURE
 
@@ -15,20 +15,20 @@ tools/
 │   ├── tools.ts      # ToolDefinition or factory
 │   ├── types.ts      # Zod schemas
 │   └── constants.ts  # Fixed values
-├── lsp/              # 6 tools: definition, references, symbols, diagnostics, rename (client.ts 540 lines)
+├── lsp/              # 6 tools: definition, references, symbols, diagnostics, rename (client.ts 803 lines)
 ├── ast-grep/         # 2 tools: search, replace (25 languages)
-├── delegate-task/    # Category-based routing (1135 lines)
+├── delegate-task/    # Category-based routing (executor.ts 983 lines, constants.ts 552 lines)
 ├── task/             # 4 tools: create, get, list, update (Claude Code compatible)
 ├── session-manager/  # 4 tools: list, read, search, info
 ├── grep/             # Custom grep with timeout (60s, 10MB)
 ├── glob/             # 60s timeout, 100 file limit
 ├── interactive-bash/ # Tmux session management
-├── look-at/          # Multimodal PDF/image
+├── look-at/          # Multimodal PDF/image (307 lines)
 ├── skill/            # Skill execution
 ├── skill-mcp/        # Skill MCP operations
 ├── slashcommand/     # Slash command dispatch
-├── call-omo-agent/   # Direct agent invocation
-└── background-task/  # background_output, background_cancel
+├── call-omo-agent/   # Direct agent invocation (358 lines)
+└── background-task/  # background_output, background_cancel (734 lines)
 ```
 
 ## TOOL CATEGORIES
@@ -49,13 +49,9 @@ tools/
 Claude Code compatible task management.
 
 - **task_create**: Creates a new task. Auto-generates ID and syncs to Todo.
-  - Args: `subject`, `description`, `activeForm`, `blocks`, `blockedBy`, `owner`, `metadata`
 - **task_get**: Retrieves a task by ID.
-  - Args: `id`
 - **task_list**: Lists active tasks. Filters out completed/deleted by default.
-  - Args: `status`, `parentID`
 - **task_update**: Updates task fields. Supports additive `addBlocks`/`addBlockedBy`.
-  - Args: `id`, `subject`, `description`, `status`, `activeForm`, `addBlocks`, `addBlockedBy`, `owner`, `metadata`
 
 ## HOW TO ADD