diff --git a/src/agents/athena/council-orchestrator.test.ts b/src/agents/athena/council-orchestrator.test.ts
deleted file mode 100644
index 264ac3b77..000000000
--- a/src/agents/athena/council-orchestrator.test.ts
+++ /dev/null
@@ -1,228 +0,0 @@
-import { describe, expect, test } from "bun:test"
-import { buildCouncilPrompt } from "./council-prompt"
-import { executeCouncil } from "./council-orchestrator"
-import type { CouncilConfig } from "./types"
-
-interface MockLaunchInput {
-  description: string
-  prompt: string
-  agent: string
-  parentSessionID: string
-  parentMessageID: string
-  parentAgent?: string
-  model?: { providerID: string; modelID: string; variant?: string }
-}
-
-function createMockTask(id: string, launch: MockLaunchInput) {
-  return {
-    id,
-    status: "pending" as const,
-    parentSessionID: launch.parentSessionID,
-    parentMessageID: launch.parentMessageID,
-    description: launch.description,
-    prompt: launch.prompt,
-    agent: launch.agent,
-  }
-}
-
-describe("executeCouncil", () => {
-  //#given a council with 3 members and a question
-  //#when executeCouncil is called
-  //#then all members are launched with the same prompt and parsed model ids
-  test("launches all members with identical prompt and model params", async () => {
-    const launches: MockLaunchInput[] = []
-    const launcher = {
-      launch: async (input: MockLaunchInput) => {
-        launches.push(input)
-        return createMockTask(`task-${launches.length}`, input)
-      },
-    }
-
-    const council: CouncilConfig = {
-      members: [
-        { model: "openai/gpt-5.3-codex", name: "openai" },
-        { model: "anthropic/claude-sonnet-4-5", name: "anthropic" },
-        { model: "google/gemini-3-pro", name: "google" },
-      ],
-    }
-
-    const question = "How can we improve the retry strategy?"
-    const result = await executeCouncil({
-      question,
-      council,
-      launcher,
-      parentSessionID: "session-1",
-      parentMessageID: "message-1",
-      parentAgent: "sisyphus",
-    })
-
-    const expectedPrompt = buildCouncilPrompt(question)
-
-    expect(launches).toHaveLength(3)
-    expect(result.launched).toHaveLength(3)
-    expect(result.failures).toHaveLength(0)
-    expect(result.totalMembers).toBe(3)
-
-    for (const launch of launches) {
-      expect(launch.prompt).toBe(expectedPrompt)
-      expect(launch.agent).toBe("council-member")
-    }
-
-    expect(launches[0]?.model).toEqual({ providerID: "openai", modelID: "gpt-5.3-codex" })
-    expect(launches[1]?.model).toEqual({ providerID: "anthropic", modelID: "claude-sonnet-4-5" })
-    expect(launches[2]?.model).toEqual({ providerID: "google", modelID: "gemini-3-pro" })
-  })
-
-  //#given a council with 3 members where 1 launch throws
-  //#when executeCouncil is called
-  //#then launch failures are captured separately from successful launches
-  test("captures launch failures separately from successful launches", async () => {
-    const launcher = {
-      launch: async (input: MockLaunchInput) => {
-        if (input.model?.providerID === "anthropic") {
-          throw new Error("Provider unavailable")
-        }
-        return createMockTask(`task-${input.model?.providerID}`, input)
-      },
-    }
-
-    const result = await executeCouncil({
-      question: "Find race condition risks",
-      council: {
-        members: [
-          { model: "openai/gpt-5.3-codex" },
-          { model: "anthropic/claude-sonnet-4-5" },
-          { model: "google/gemini-3-pro" },
-        ],
-      },
-      launcher,
-      parentSessionID: "session-1",
-      parentMessageID: "message-1",
-    })
-
-    expect(result.launched).toHaveLength(2)
-    expect(result.failures).toHaveLength(1)
-    expect(result.totalMembers).toBe(3)
-    expect(result.failures[0]?.member.model).toBe("anthropic/claude-sonnet-4-5")
-    expect(result.failures[0]?.error).toContain("Launch failed")
-  })
-
-  //#given a council where all launches throw
-  //#when executeCouncil is called
-  //#then all members appear as failures with zero launched
-  test("returns all failures when every launch throws", async () => {
-    const launcher = {
-      launch: async () => {
-        throw new Error("Model unavailable")
-      },
-    }
-
-    const result = await executeCouncil({
-      question: "Analyze unknown module",
-      council: {
-        members: [
-          { model: "openai/gpt-5.3-codex" },
-          { model: "anthropic/claude-sonnet-4-5" },
-        ],
-      },
-      launcher,
-      parentSessionID: "session-1",
-      parentMessageID: "message-1",
-    })
-
-    expect(result.launched).toHaveLength(0)
-    expect(result.failures).toHaveLength(2)
-    expect(result.totalMembers).toBe(2)
-    expect(result.failures.every((f) => f.error.includes("Launch failed"))).toBe(true)
-  })
-
-  //#given a council with one invalid model string
-  //#when executeCouncil is called
-  //#then invalid member becomes a failure while others still launch
-  test("handles invalid model strings without crashing council execution", async () => {
-    const launches: MockLaunchInput[] = []
-    const launcher = {
-      launch: async (input: MockLaunchInput) => {
-        launches.push(input)
-        return createMockTask(`task-${launches.length}`, input)
-      },
-    }
-
-    const result = await executeCouncil({
-      question: "Audit dependency graph",
-      council: {
-        members: [
-          { model: "invalid-model" },
-          { model: "openai/gpt-5.3-codex" },
-        ],
-      },
-      launcher,
-      parentSessionID: "session-1",
-      parentMessageID: "message-1",
-    })
-
-    expect(launches).toHaveLength(1)
-    expect(result.launched).toHaveLength(1)
-    expect(result.failures).toHaveLength(1)
-    expect(result.failures.find((f) => f.member.model === "invalid-model")?.error).toContain("Launch failed")
-  })
-
-  //#given members with per-member variant
-  //#when executeCouncil is called
-  //#then launch receives variant in model for each corresponding member
-  test("passes member variant to launch input model", async () => {
-    const launches: MockLaunchInput[] = []
-    const launcher = {
-      launch: async (input: MockLaunchInput) => {
-        launches.push(input)
-        return createMockTask(`task-${launches.length}`, input)
-      },
-    }
-
-    await executeCouncil({
-      question: "Compare architecture options",
-      council: {
-        members: [
-          { model: "openai/gpt-5.3-codex", variant: "high" },
-          { model: "anthropic/claude-sonnet-4-5" },
-        ],
-      },
-      launcher,
-      parentSessionID: "session-1",
-      parentMessageID: "message-1",
-    })
-
-    expect(launches).toHaveLength(2)
-    expect(launches[0]?.model?.variant).toBe("high")
-    expect(launches[1]?.model?.variant).toBeUndefined()
-  })
-
-  //#given launched members
-  //#when executeCouncil returns
-  //#then each launched member has a taskId for background_output retrieval
-  test("returns task IDs for background_output retrieval", async () => {
-    const launcher = {
-      launch: async (input: MockLaunchInput) =>
-        createMockTask(`bg_${input.model?.providerID}`, input),
-    }
-
-    const result = await executeCouncil({
-      question: "Review error handling",
-      council: {
-        members: [
-          { model: "openai/gpt-5.3-codex", name: "OpenAI" },
-          { model: "google/gemini-3-pro", name: "Gemini" },
-        ],
-      },
-      launcher,
-      parentSessionID: "session-1",
-      parentMessageID: "message-1",
-    })
-
-    expect(result.launched).toHaveLength(2)
-    expect(result.launched[0]?.taskId).toBe("bg_openai")
-    expect(result.launched[0]?.member.name).toBe("OpenAI")
-    expect(result.launched[1]?.taskId).toBe("bg_google")
-    expect(result.launched[1]?.member.name).toBe("Gemini")
-  })
-})
diff --git a/src/agents/athena/council-orchestrator.ts b/src/agents/athena/council-orchestrator.ts
deleted file mode 100644
index f5877d96e..000000000
--- a/src/agents/athena/council-orchestrator.ts
+++ /dev/null
@@ -1,94 +0,0 @@
-import type { LaunchInput, BackgroundTask } from "../../features/background-agent/types"
-import { log } from "../../shared/logger"
-import { buildCouncilPrompt } from "./council-prompt"
-import { parseModelString } from "./model-parser"
-import type { CouncilConfig, CouncilLaunchFailure, CouncilLaunchedMember, CouncilLaunchResult, CouncilMemberConfig } from "./types"
-
-export type CouncilLaunchInput = LaunchInput
-
-export interface CouncilLauncher {
-  launch(input: CouncilLaunchInput): Promise<BackgroundTask>
-}
-
-export interface CouncilExecutionInput {
-  question: string
-  council: CouncilConfig
-  launcher: CouncilLauncher
-  parentSessionID: string
-  parentMessageID: string
-  parentAgent?: string
-}
-
-/**
- * Launches all council members in parallel and returns launch outcomes.
- * Does NOT wait for task completion — actual results are collected by the
- * agent via background_output calls after this returns.
- */
-export async function executeCouncil(input: CouncilExecutionInput): Promise<CouncilLaunchResult> {
-  const { question, council, launcher, parentSessionID, parentMessageID, parentAgent } = input
-
-  log("[athena-council] Executing council", { memberCount: council.members.length })
-
-  const prompt = buildCouncilPrompt(question)
-
-  const launchResults = await Promise.allSettled(
-    council.members.map((member) =>
-      launchMember(member, prompt, launcher, parentSessionID, parentMessageID, parentAgent)
-    )
-  )
-
-  const launched: CouncilLaunchedMember[] = []
-  const failures: CouncilLaunchFailure[] = []
-
-  launchResults.forEach((result, index) => {
-    const member = council.members[index]
-
-    if (result.status === "fulfilled") {
-      launched.push({ member, taskId: result.value.id })
-      return
-    }
-
-    failures.push({
-      member,
-      error: `Launch failed: ${result.reason instanceof Error ? result.reason.message : String(result.reason)}`,
-    })
-  })
-
-  log("[athena-council] Council execution complete", { launched: launched.length, failures: failures.length })
-
-  return {
-    question,
-    launched,
-    failures,
-    totalMembers: council.members.length,
-  }
-}
-
-async function launchMember(
-  member: CouncilMemberConfig,
-  prompt: string,
-  launcher: CouncilLauncher,
-  parentSessionID: string,
-  parentMessageID: string,
-  parentAgent: string | undefined
-): Promise<BackgroundTask> {
-  const parsedModel = parseModelString(member.model)
-  if (!parsedModel) {
-    throw new Error(`Invalid model string: "${member.model}"`)
-  }
-
-  const memberName = member.name ?? member.model
-  return launcher.launch({
-    description: `Council member: ${memberName}`,
-    prompt,
-    agent: "council-member",
-    parentSessionID,
-    parentMessageID,
-    parentAgent,
-    model: {
-      providerID: parsedModel.providerID,
-      modelID: parsedModel.modelID,
-      ...(member.variant ? { variant: member.variant } : {}),
-    },
-  })
-}
diff --git a/src/agents/athena/council-prompt.ts b/src/agents/athena/council-prompt.ts
deleted file mode 100644
index 9ccdff64a..000000000
--- a/src/agents/athena/council-prompt.ts
+++ /dev/null
@@ -1,24 +0,0 @@
-export function buildCouncilPrompt(question: string): string {
-  return `You are a council member in a multi-model analysis council. Your role is to provide independent, thorough analysis of the question below.
-
-## Your Role
-- You are one of several AI models analyzing the same question independently
-- Your analysis should be thorough and evidence-based
-- You are read-only - you cannot modify any files, only analyze
-- Focus on finding real issues, not hypothetical ones
-
-## Instructions
-1. Analyze the question carefully
-2. Search the codebase thoroughly using available tools (Read, Grep, Glob, LSP)
-3. Report your findings with evidence (file paths, line numbers, code snippets)
-4. For each finding, state:
-   - What the issue/observation is
-   - Where it is (file path, line number)
-   - Why it matters (severity: critical/high/medium/low)
-   - Your confidence level (high/medium/low)
-5. Be concise but thorough - quality over quantity
-
-## Question
-
-${question}`
-}