fix(athena): remove duplicate council prompt, add temp file cleanup, fix code quality

- Remove COUNCIL_MEMBER_PROMPT from temp file content since it's already
  provided as the council member's system prompt via agent config, saving
  ~350+ tokens per council member per invocation
- Add startup cleanup for stale athena-council-*.md files older than 30
  minutes in .sisyphus/tmp/ to handle cases where process exits before
  setTimeout cleanup fires
- Remove redundant intermediate permission object spread in createAthenaAgent
- Fix test style: it() -> test(), add #given/#then prefixes per conventions

src/agents/athena/agent.ts

@@ -236,9 +236,6 @@ export function createAthenaAgent(model: string): AgentConfig {
   const restrictions = createAgentToolRestrictions(["write", "edit", "call_omo_agent"])
 
   // question permission is set by tool-config-handler.ts based on CLI mode (allow/deny)
-  const permission = {
-    ...restrictions.permission,
-  }
 
   const base = {
     description:
@@ -246,7 +243,7 @@ export function createAthenaAgent(model: string): AgentConfig {
     mode: MODE,
     model,
     temperature: 0.1,
-    permission,
+    permission: restrictions.permission,
     prompt: ATHENA_SYSTEM_PROMPT,
     color: "#1F8EFA",
   }

src/agents/athena/model-thinking-config.test.ts

@@ -1,4 +1,4 @@
-import { describe, expect, it } from "bun:test"
+import { describe, expect, test } from "bun:test"
 import type { AgentConfig } from "@opencode-ai/sdk"
 import { applyModelThinkingConfig } from "./model-thinking-config"
 
@@ -10,20 +10,20 @@ const BASE_CONFIG: AgentConfig = {
 }
 
 describe("applyModelThinkingConfig", () => {
-  describe("given a GPT model", () => {
-    it("returns reasoningEffort medium", () => {
+  describe("#given a GPT model", () => {
+    test("#then returns reasoningEffort medium", () => {
       const result = applyModelThinkingConfig(BASE_CONFIG, "gpt-5.2")
       expect(result).toEqual({ ...BASE_CONFIG, reasoningEffort: "medium" })
     })
 
-    it("returns reasoningEffort medium for openai-prefixed model", () => {
+    test("#then returns reasoningEffort medium for openai-prefixed model", () => {
       const result = applyModelThinkingConfig(BASE_CONFIG, "openai/gpt-5.2")
       expect(result).toEqual({ ...BASE_CONFIG, reasoningEffort: "medium" })
     })
   })
 
-  describe("given an Anthropic model", () => {
-    it("returns thinking config with budgetTokens 32000", () => {
+  describe("#given an Anthropic model", () => {
+    test("#then returns thinking config with budgetTokens 32000", () => {
       const result = applyModelThinkingConfig(BASE_CONFIG, "anthropic/claude-opus-4-6")
       expect(result).toEqual({
         ...BASE_CONFIG,
@@ -32,29 +32,29 @@ describe("applyModelThinkingConfig", () => {
     })
   })
 
-  describe("given a Google model", () => {
-    it("returns base config unchanged", () => {
+  describe("#given a Google model", () => {
+    test("#then returns base config unchanged", () => {
       const result = applyModelThinkingConfig(BASE_CONFIG, "google/gemini-3-pro")
       expect(result).toBe(BASE_CONFIG)
     })
   })
 
-  describe("given a Kimi model", () => {
-    it("returns base config unchanged", () => {
+  describe("#given a Kimi model", () => {
+    test("#then returns base config unchanged", () => {
       const result = applyModelThinkingConfig(BASE_CONFIG, "kimi/kimi-k2.5")
       expect(result).toBe(BASE_CONFIG)
     })
   })
 
-  describe("given a model with no provider prefix", () => {
-    it("returns base config unchanged for non-GPT model", () => {
+  describe("#given a model with no provider prefix", () => {
+    test("#then returns base config unchanged for non-GPT model", () => {
       const result = applyModelThinkingConfig(BASE_CONFIG, "gemini-3-pro")
       expect(result).toBe(BASE_CONFIG)
     })
   })
 
-  describe("given a Claude model through a non-Anthropic provider", () => {
-    it("returns thinking config for github-copilot/claude-opus-4-6", () => {
+  describe("#given a Claude model through a non-Anthropic provider", () => {
+    test("#then returns thinking config for github-copilot/claude-opus-4-6", () => {
       const result = applyModelThinkingConfig(BASE_CONFIG, "github-copilot/claude-opus-4-6")
       expect(result).toEqual({
         ...BASE_CONFIG,
@@ -62,7 +62,7 @@ describe("applyModelThinkingConfig", () => {
       })
     })
 
-    it("returns thinking config for opencode/claude-opus-4-6", () => {
+    test("#then returns thinking config for opencode/claude-opus-4-6", () => {
       const result = applyModelThinkingConfig(BASE_CONFIG, "opencode/claude-opus-4-6")
       expect(result).toEqual({
         ...BASE_CONFIG,
@@ -70,7 +70,7 @@ describe("applyModelThinkingConfig", () => {
       })
     })
 
-    it("returns thinking config for opencode/claude-sonnet-4-6", () => {
+    test("#then returns thinking config for opencode/claude-sonnet-4-6", () => {
       const result = applyModelThinkingConfig(BASE_CONFIG, "opencode/claude-sonnet-4-6")
       expect(result).toEqual({
         ...BASE_CONFIG,

src/tools/prepare-council-prompt/tools.ts

@@ -1,13 +1,38 @@
 import { tool, type ToolDefinition } from "@opencode-ai/plugin"
 import { randomUUID } from "node:crypto"
-import { writeFile, unlink, mkdir } from "node:fs/promises"
+import { writeFile, unlink, mkdir, readdir, stat } from "node:fs/promises"
 import { join } from "node:path"
 import { log } from "../../shared/logger"
-import { COUNCIL_MEMBER_PROMPT, COUNCIL_SOLO_ADDENDUM, COUNCIL_DELEGATION_ADDENDUM } from "../../agents/athena"
+import { COUNCIL_SOLO_ADDENDUM, COUNCIL_DELEGATION_ADDENDUM } from "../../agents/athena"
 
 const CLEANUP_DELAY_MS = 30 * 60 * 1000
 const COUNCIL_TMP_DIR = ".sisyphus/tmp"
 
+const COUNCIL_FILE_PREFIX = "athena-council-"
+
+async function cleanupStaleTempFiles(directory: string): Promise<void> {
+  const tmpDir = join(directory, COUNCIL_TMP_DIR)
+  try {
+    const files = await readdir(tmpDir)
+    const now = Date.now()
+    for (const file of files) {
+      if (!file.startsWith(COUNCIL_FILE_PREFIX) || !file.endsWith(".md")) continue
+      const filePath = join(tmpDir, file)
+      try {
+        const fileStat = await stat(filePath)
+        if (now - fileStat.mtimeMs > CLEANUP_DELAY_MS) {
+          await unlink(filePath)
+          log("[prepare-council-prompt] Cleaned up stale temp file", { filePath })
+        }
+      } catch {
+        // File may have been deleted between readdir and stat
+      }
+    }
+  } catch {
+    // Directory may not exist yet — nothing to clean
+  }
+}
+
 export function createPrepareCouncilPromptTool(directory: string): ToolDefinition {
   const description = `Save a council analysis prompt to a temp file so council members can read it.
 
@@ -21,6 +46,10 @@ The "mode" parameter controls whether council members can delegate exploration t
 
 Returns the file path to reference in subsequent task() calls.`
 
+  cleanupStaleTempFiles(directory).catch((err) => {
+    log("[prepare-council-prompt] Startup cleanup failed", { error: String(err) })
+  })
+
   return tool({
     description,
     args: {
@@ -40,8 +69,7 @@ Returns the file path to reference in subsequent task() calls.`
       const filePath = join(tmpDir, filename)
 
       const modeAddendum = mode === "delegation" ? COUNCIL_DELEGATION_ADDENDUM : COUNCIL_SOLO_ADDENDUM
-      const content = `${COUNCIL_MEMBER_PROMPT}
-${modeAddendum}
+      const content = `${modeAddendum}
 
 ## Analysis Question