docs: add PM Agent architecture and MCP integration documentation

## PM Agent Architecture Redesign ### Auto-Activation System - **pm-agent-auto-activation.md**: Behavior-based auto-activation architecture - 5 activation layers (Session Start, Documentation Guardian, Commander, Post-Implementation, Mistake Handler) - Remove manual `/sc:pm` command requirement - Auto-trigger based on context detection ### Responsibility Cleanup - **pm-agent-responsibility-cleanup.md**: Memory management strategy and MCP role clarification - Delete `docs/memory/` directory (redundant with Mindbase) - Remove `write_memory()` / `read_memory()` usage (Serena is code-only) - Clear lifecycle rules for each memory layer ## MCP Integration Policy ### Core Definitions - **mcp-integration-policy.md**: Complete MCP server definitions and usage guidelines - Mindbase: Automatic conversation history (don't touch) - Serena: Code understanding only (not task management) - Sequential: Complex reasoning engine - Context7: Official documentation reference - Tavily: Web search and research - Clear auto-trigger conditions for each MCP - Anti-patterns and best practices ### Optional Design - **mcp-optional-design.md**: MCP-optional architecture with graceful fallbacks - SuperClaude works fully without any MCPs - MCPs are performance enhancements (2-3x faster, 30-50% fewer tokens) - Automatic fallback to native tools - User choice: Minimal → Standard → Enhanced setup ## Key Benefits **Simplicity**: - Remove `docs/memory/` complexity - Clear MCP role separation - Auto-activation (no manual commands) **Reliability**: - Works without MCPs (graceful degradation) - Clear fallback strategies - No single point of failure **Performance** (with MCPs): - 2-3x faster execution - 30-50% token reduction - Better code understanding (Serena) - Efficient reasoning (Sequential) 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com>
2025-12-29 16:16:08 +00:00 · 2025-10-19 22:37:51 +09:00
parent b5d6bbb7ae
commit 76ac7f231b
4 changed files with 1722 additions and 0 deletions
--- a/docs/architecture/pm-agent-auto-activation.md
+++ b/docs/architecture/pm-agent-auto-activation.md
@@ -0,0 +1,455 @@
+# PM Agent Auto-Activation Architecture
+
+## Problem Statement
+
+**Current Issue**: PM Agent functionality requires manual `/sc:pm` command invocation, making it easy to forget and inconsistently applied.
+
+**User Concern**: "今は、/sc:pmコマンドを毎回叩かないと、PM-modeやってくれないきがする"
+
+## Solution: Behavior-Based Auto-Activation
+
+PM Agent should activate automatically based on **context detection**, not manual commands.
+
+### Architecture Overview
+
+```yaml
+PM Agent Activation Layers:
+
+  Layer 1 - Session Start (ALWAYS):
+    Trigger: Every new conversation session
+    Action: Auto-restore context from docs/memory/
+    Detection: Session initialization event
+
+  Layer 2 - Documentation Guardian (CONTINUOUS):
+    Trigger: Any file operation in project
+    Action: Ensure relevant docs are read before implementation
+    Detection: Write/Edit tool usage
+
+  Layer 3 - Commander (ON-DEMAND):
+    Trigger: Complex tasks (>3 steps OR >3 files)
+    Action: Orchestrate sub-agents and track progress
+    Detection: TodoWrite usage OR complexity keywords
+
+  Layer 4 - Post-Implementation (AUTO):
+    Trigger: Task completion
+    Action: Document learnings and update knowledge base
+    Detection: Completion keywords OR test pass
+
+  Layer 5 - Mistake Handler (IMMEDIATE):
+    Trigger: Errors or test failures
+    Action: Root cause analysis and prevention documentation
+    Detection: Error messages OR test failures
+```
+
+## Implementation Strategy
+
+### 1. Session Start Auto-Activation
+
+**File**: `~/.claude/superclaude/agents/pm-agent.md`
+
+**Trigger Detection**:
+```yaml
+session_start_indicators:
+  - First message in new conversation
+  - No prior context in current session
+  - Token budget reset to baseline
+  - No active TodoWrite items in memory
+```
+
+**Auto-Execution (No Manual Command)**:
+```yaml
+Wave 1 - PARALLEL Context Restoration:
+  1. Bash: git status && git branch
+  2. PARALLEL Read (silent):
+     - Read docs/memory/pm_context.md (if exists)
+     - Read docs/memory/last_session.md (if exists)
+     - Read docs/memory/next_actions.md (if exists)
+     - Read docs/memory/current_plan.json (if exists)
+     - Read CLAUDE.md (ALWAYS)
+     - Read docs/patterns/*.md (recent 5 files)
+
+Checkpoint - Confidence Check (200 tokens):
+  ❓ "全ファイル読めた？"
+  ❓ "コンテキストに矛盾ない？"
+  ❓ "次のアクション実行に十分な情報？"
+
+  IF confidence >70%:
+    → Output: 📍 [branch] | [status] | 🧠 [token]%
+    → Ready for user request
+  ELSE:
+    → Report what's missing
+    → Request user clarification
+```
+
+**Key Change**: This happens **automatically** at session start, not via `/sc:pm` command.
+
+### 2. Documentation Guardian (Continuous)
+
+**Purpose**: Ensure documentation is ALWAYS read before making changes
+
+**Trigger Detection**:
+```yaml
+pre_write_checks:
+  - BEFORE any Write tool usage
+  - BEFORE any Edit tool usage
+  - BEFORE complex TodoWrite (>3 tasks)
+
+detection_logic:
+  IF tool_name in [Write, Edit, MultiEdit]:
+    AND file_path matches project patterns:
+      → Auto-trigger Documentation Guardian
+```
+
+**Auto-Execution**:
+```yaml
+Documentation Guardian Protocol:
+
+1. Identify Relevant Docs:
+   file_path: src/auth.ts
+   → Read docs/patterns/authentication-*.md
+   → Read docs/mistakes/auth-*.md
+   → Read CLAUDE.md sections matching "auth"
+
+2. Confidence Check:
+   ❓ "関連ドキュメント全部読んだ？"
+   ❓ "過去の失敗パターン把握してる？"
+   ❓ "既存の成功パターン確認した？"
+
+   IF any_missing:
+     → Read missing docs
+     → Update understanding
+     → Proceed with implementation
+   ELSE:
+     → Proceed confidently
+
+3. Pattern Matching:
+   IF similar_mistakes_found:
+     ⚠️ "過去に同じミス発生: [mistake_pattern]"
+     ⚠️ "防止策: [prevention_checklist]"
+     → Apply prevention before implementation
+```
+
+**Key Change**: Automatic documentation reading BEFORE any file modification.
+
+### 3. Commander Mode (On-Demand)
+
+**Purpose**: Orchestrate complex multi-step tasks with sub-agents
+
+**Trigger Detection**:
+```yaml
+commander_triggers:
+  complexity_based:
+    - TodoWrite with >3 tasks
+    - Operations spanning >3 files
+    - Multi-directory scope (>2 dirs)
+    - Keywords: "refactor", "migrate", "redesign"
+
+  explicit_keywords:
+    - "orchestrate"
+    - "coordinate"
+    - "delegate"
+    - "parallel execution"
+```
+
+**Auto-Execution**:
+```yaml
+Commander Protocol:
+
+1. Task Analysis:
+   - Identify independent vs dependent tasks
+   - Determine parallelization opportunities
+   - Select appropriate sub-agents
+
+2. Orchestration Plan:
+   tasks:
+     - task_1: [agent-backend] → auth refactor
+     - task_2: [agent-frontend] → UI updates (parallel)
+     - task_3: [agent-test] → test updates (after 1+2)
+
+   parallelization:
+     wave_1: [task_1, task_2] # parallel
+     wave_2: [task_3]         # sequential dependency
+
+3. Execution with Tracking:
+   - TodoWrite for overall plan
+   - Sub-agent delegation via Task tool
+   - Progress tracking in docs/memory/checkpoint.json
+   - Validation gates between waves
+
+4. Synthesis:
+   - Collect sub-agent outputs
+   - Integrate results
+   - Final validation
+   - Update documentation
+```
+
+**Key Change**: Auto-activates when complexity detected, no manual command needed.
+
+### 4. Post-Implementation Auto-Documentation
+
+**Trigger Detection**:
+```yaml
+completion_indicators:
+  test_based:
+    - "All tests passing" in output
+    - pytest: X/X passed
+    - ✅ keywords detected
+
+  task_based:
+    - All TodoWrite items marked completed
+    - No pending tasks remaining
+
+  explicit:
+    - User says "done", "finished", "complete"
+    - Commit message created
+```
+
+**Auto-Execution**:
+```yaml
+Post-Implementation Protocol:
+
+1. Self-Evaluation (The Four Questions):
+   ❓ "テストは全てpassしてる？"
+   ❓ "要件を全て満たしてる？"
+   ❓ "思い込みで実装してない？"
+   ❓ "証拠はある？"
+
+   IF any_fail:
+     ❌ NOT complete
+     → Report actual status
+   ELSE:
+     ✅ Proceed to documentation
+
+2. Pattern Extraction:
+   - What worked? → docs/patterns/[pattern].md
+   - What failed? → docs/mistakes/[mistake].md
+   - New learnings? → docs/memory/patterns_learned.jsonl
+
+3. Knowledge Base Update:
+   IF global_pattern_discovered:
+     → Update CLAUDE.md with new rule
+   IF project_specific_pattern:
+     → Update docs/patterns/
+   IF anti_pattern_identified:
+     → Update docs/mistakes/
+
+4. Session State Update:
+   - Write docs/memory/session_summary.json
+   - Update docs/memory/next_actions.md
+   - Clean up temporary docs (>7 days old)
+```
+
+**Key Change**: Automatic documentation after task completion, no manual trigger needed.
+
+### 5. Mistake Handler (Immediate)
+
+**Trigger Detection**:
+```yaml
+error_indicators:
+  test_failures:
+    - "FAILED" in pytest output
+    - "Error" in test results
+    - Non-zero exit code
+
+  runtime_errors:
+    - Exception stacktrace detected
+    - Build failures
+    - Linter errors (critical only)
+
+  validation_failures:
+    - Type check errors
+    - Schema validation failures
+```
+
+**Auto-Execution**:
+```yaml
+Mistake Handler Protocol:
+
+1. STOP Current Work:
+   → Halt further implementation
+   → Do not workaround the error
+
+2. Reflexion Pattern:
+   a) Check Past Errors:
+      → Grep docs/memory/solutions_learned.jsonl
+      → Grep docs/mistakes/ for similar errors
+
+   b) IF similar_error_found:
+      ✅ "過去に同じエラー発生済み"
+      ✅ "解決策: [past_solution]"
+      → Apply known solution
+
+   c) ELSE (new error):
+      → Root cause investigation
+      → Document new solution
+
+3. Documentation:
+   Create docs/mistakes/[feature]-YYYY-MM-DD.md:
+     - What Happened (現象)
+     - Root Cause (根本原因)
+     - Why Missed (なぜ見逃したか)
+     - Fix Applied (修正内容)
+     - Prevention Checklist (防止策)
+     - Lesson Learned (教訓)
+
+4. Update Knowledge Base:
+   → echo '{"error":"...","solution":"..."}' >> docs/memory/solutions_learned.jsonl
+   → Update prevention checklists
+```
+
+**Key Change**: Immediate automatic activation when errors detected, no manual trigger.
+
+## Removal of Manual `/sc:pm` Command
+
+### Current State
+- `/sc:pm` command in `~/.claude/commands/sc/pm.md`
+- Requires user to manually invoke every session
+- Inconsistent application
+
+### Proposed Change
+- **Remove** `/sc:pm` command entirely
+- **Replace** with behavior-based auto-activation
+- **Keep** pm-agent persona for all behaviors
+
+### Migration Path
+
+```yaml
+Step 1 - Update pm-agent.md:
+  Remove: "Manual Invocation: /sc:pm command"
+  Add: "Auto-Activation: Behavior-based triggers (see below)"
+
+Step 2 - Delete /sc:pm command:
+  File: ~/.claude/commands/sc/pm.md
+  Action: Archive or delete (functionality now in persona)
+
+Step 3 - Update rules.md:
+  Agent Orchestration section:
+  - Remove references to /sc:pm command
+  - Add auto-activation trigger documentation
+
+Step 4 - Test Auto-Activation:
+  - Start new session → Should auto-restore context
+  - Make file changes → Should auto-read relevant docs
+  - Complete task → Should auto-document learnings
+  - Encounter error → Should auto-trigger mistake handler
+```
+
+## Benefits
+
+### 1. No Manual Commands Required
+- ✅ PM Agent always active, never forgotten
+- ✅ Consistent documentation reading
+- ✅ Automatic knowledge base maintenance
+
+### 2. Context-Aware Activation
+- ✅ Right behavior at right time
+- ✅ No unnecessary overhead
+- ✅ Efficient token usage
+
+### 3. Guaranteed Documentation Quality
+- ✅ Always read relevant docs before changes
+- ✅ Automatic pattern documentation
+- ✅ Mistake prevention through Reflexion
+
+### 4. Seamless Orchestration
+- ✅ Auto-detects complex tasks
+- ✅ Auto-delegates to sub-agents
+- ✅ Auto-tracks progress
+
+## Token Budget Impact
+
+```yaml
+Current (Manual /sc:pm):
+  If forgotten: 0 tokens (no PM functionality)
+  If remembered: 200-500 tokens per invocation
+  Average: Inconsistent, user-dependent
+
+Proposed (Auto-Activation):
+  Session Start: 200 tokens (ALWAYS)
+  Documentation Guardian: 0-100 tokens (as needed)
+  Commander: 0 tokens (only if complex task)
+  Post-Implementation: 200-2,500 tokens (only after completion)
+  Mistake Handler: 0 tokens (only if error)
+
+  Total per session: 400-3,000 tokens (predictable)
+
+  Trade-off: Slight increase in baseline usage
+  Benefit: 100% consistent PM Agent functionality
+  ROI: Prevents 5K-50K token waste from wrong implementations
+```
+
+## Implementation Checklist
+
+```yaml
+Phase 1 - Core Auto-Activation:
+  - [ ] Update pm-agent.md with auto-activation triggers
+  - [ ] Remove session start from /sc:pm command
+  - [ ] Test session start auto-restoration
+  - [ ] Verify token budget calculations
+
+Phase 2 - Documentation Guardian:
+  - [ ] Add pre-write documentation checks
+  - [ ] Implement pattern matching logic
+  - [ ] Test with various file operations
+  - [ ] Verify no performance degradation
+
+Phase 3 - Commander Mode:
+  - [ ] Add complexity detection logic
+  - [ ] Implement sub-agent delegation
+  - [ ] Test parallel execution patterns
+  - [ ] Verify progress tracking
+
+Phase 4 - Post-Implementation:
+  - [ ] Add completion detection logic
+  - [ ] Implement auto-documentation triggers
+  - [ ] Test pattern extraction
+  - [ ] Verify knowledge base updates
+
+Phase 5 - Mistake Handler:
+  - [ ] Add error detection logic
+  - [ ] Implement Reflexion pattern lookup
+  - [ ] Test mistake documentation
+  - [ ] Verify prevention checklist updates
+
+Phase 6 - Cleanup:
+  - [ ] Archive /sc:pm command
+  - [ ] Update all documentation
+  - [ ] Remove manual invocation references
+  - [ ] Final integration testing
+```
+
+## Example Workflow (After Implementation)
+
+```yaml
+User Session:
+
+1. Start Conversation:
+   Claude: [Auto-activates PM Agent]
+   Claude: 📍 feature/auth | ✨ Clean | 🧠 15% (30K/200K)
+   User: "Fix authentication bug in auth.ts"
+
+2. Pre-Implementation:
+   Claude: [Documentation Guardian activates]
+   Claude: [Reads docs/patterns/authentication-*.md silently]
+   Claude: [Reads docs/mistakes/auth-*.md silently]
+   Claude: ⚠️ Past mistake found: "Missing token validation"
+   Claude: Applying prevention checklist before implementation...
+
+3. Implementation:
+   Claude: [Makes changes with prevention applied]
+   Claude: [Runs tests]
+   Claude: ✅ All tests passing
+
+4. Post-Implementation:
+   Claude: [Auto-activates documentation]
+   Claude: [Runs Four Questions self-check]
+   Claude: [Extracts pattern: "Token validation pattern"]
+   Claude: [Updates docs/patterns/authentication-token-validation.md]
+   Claude: ✅ Task complete with documentation updated
+
+User: [Never had to invoke /sc:pm manually]
+```
+
+## Conclusion
+
+This architecture ensures PM Agent functionality is **always active** through behavior-based triggers, eliminating the need for manual `/sc:pm` command invocation while maintaining clear responsibility separation and guaranteed documentation quality.
--- a/docs/architecture/pm-agent-responsibility-cleanup.md
+++ b/docs/architecture/pm-agent-responsibility-cleanup.md
@@ -0,0 +1,306 @@
+# PM Agent Responsibility Cleanup & MCP Integration
+
+## 問題整理
+
+### 1. 既存MODEとの重複
+
+**MODE_Task_Management.md と pm-agent.md が完全重複**:
+
+```yaml
+MODE_Task_Management.md:
+  - write_memory() / read_memory() 使用
+  - Serena MCP依存
+  - セッション開始時のlist_memories()
+  - TodoWrite + memory並行管理
+
+pm-agent.md:
+  - docs/memory/ ファイル管理
+  - ローカルファイルベース
+  - セッション開始時のRead並行実行
+  - TodoWrite + docs/memory/並行管理
+
+結論: 完全に機能が重複、統合必須
+```
+
+### 2. Memory管理の責務が不明確
+
+**現状の問題**:
+```yaml
+docs/memory/:
+  - いつクリアするか決まってない
+  - ファイルベース vs MCP memoryの使い分け不明
+  - ライフサイクル管理なし
+
+write_memory() (Serena MCP):
+  - いつ使うべきか不明確
+  - docs/memory/との使い分けなし
+  - 削除タイミング不明
+```
+
+### 3. MCPの役割分担が曖昧
+
+**ユーザーの指摘**:
+- Serena = コード理解に使う
+- Memory = Mindbaseに任せるべき
+- 現状は役割が混在
+
+## 解決策: 責務の明確化
+
+### Memory Management Strategy
+
+```yaml
+Level 1 - Session Memory (Mindbase MCP):
+  Purpose: 会話履歴の長期保存（Claude Code標準機能）
+  Technology: Mindbase MCP (自動管理)
+  Scope: 全プロジェクト横断
+  Lifecycle: 永続（自動管理）
+  Use Cases:
+    - 過去の会話検索
+    - 長期的なパターン学習
+    - プロジェクト間の知識共有
+
+Level 2 - Project Documentation (File-based):
+  Purpose: プロジェクト固有の知識ベース
+  Technology: Markdown files in docs/
+  Scope: プロジェクトごと
+  Lifecycle: Git管理（明示的削除まで永続）
+  Locations:
+    docs/patterns/: 成功パターン（永続）
+    docs/mistakes/: 失敗記録（永続）
+    CLAUDE.md: グローバルルール（永続）
+
+Level 3 - Task State (Serena MCP - Code Understanding):
+  Purpose: コードベース理解のためのシンボル管理
+  Technology: Serena MCP
+  Scope: セッション内
+  Lifecycle: セッション終了で自動削除
+  Use Cases:
+    - コード構造の理解
+    - シンボル間の関係追跡
+    - リファクタリング支援
+
+Level 4 - TodoWrite (Claude Code Built-in):
+  Purpose: 現在のタスク進捗管理
+  Technology: Claude Code標準機能
+  Scope: セッション内
+  Lifecycle: タスク完了で削除
+  Use Cases:
+    - 現在進行中のタスク追跡
+    - サブタスクの管理
+    - 進捗の可視化
+```
+
+### Memory Lifecycle Rules
+
+```yaml
+Session Start:
+  1. Mindbaseから過去の関連会話を自動ロード（Claude Code標準）
+  2. docs/patterns/ と docs/mistakes/ を読む（必要に応じて）
+  3. CLAUDE.md を常に読む
+  4. Serena: 使わない（コード理解時のみ）
+  5. TodoWrite: 新規作成（必要なら）
+
+During Work:
+  1. Mindbase: 自動保存（Claude Code標準）
+  2. docs/: 新しいパターン/ミスを文書化
+  3. Serena: コード理解時のみ使用
+  4. TodoWrite: 進捗更新
+
+Session End:
+  1. Mindbase: 自動保存（Claude Code標準）
+  2. docs/: 学習内容を永続化
+  3. Serena: 自動削除（何もしない）
+  4. TodoWrite: 完了タスクはクリア
+
+Monthly Maintenance:
+  1. docs/patterns/: 古い（>6ヶ月）で未参照なら削除
+  2. docs/mistakes/: 重複をマージ
+  3. CLAUDE.md: ベストプラクティス抽出
+```
+
+### MCP Role Clarification
+
+```yaml
+Mindbase MCP (会話履歴):
+  Auto-Managed: Claude Codeが自動管理
+  PM Agent Role: なし（自動で動く）
+  User Action: なし（透明）
+
+Serena MCP (コード理解):
+  Trigger: コードベース理解が必要な時のみ
+  PM Agent Role: コード理解時に自動活用
+  Examples:
+    - リファクタリング計画
+    - シンボル追跡
+    - コード構造分析
+  NOT for: タスク管理、会話記憶
+
+Sequential MCP (複雑な推論):
+  Trigger: 複雑な分析・設計が必要な時
+  PM Agent Role: Commander modeで活用
+  Examples:
+    - アーキテクチャ設計
+    - 複雑なデバッグ
+    - システム分析
+
+Context7 MCP (ドキュメント参照):
+  Trigger: 公式ドキュメント参照が必要な時
+  PM Agent Role: Pre-Implementation Confidence Check
+  Examples:
+    - ライブラリの使い方確認
+    - ベストプラクティス参照
+    - API仕様確認
+```
+
+## 統合後のPM Agent Architecture
+
+### 削除すべきもの
+
+```yaml
+DELETE:
+  1. docs/memory/ ディレクトリ全体
+     理由: Mindbaseと重複、ライフサイクル不明確
+
+  2. MODE_Task_Management.md の memory操作部分
+     理由: pm-agent.mdと重複
+
+  3. pm-agent.md の docs/memory/ 参照
+     理由: Mindbaseに統合
+
+  4. write_memory() / read_memory() 使用
+     理由: Serenaはコード理解専用
+```
+
+### 統合後の責務
+
+```yaml
+PM Agent Core Responsibilities:
+
+1. Session Lifecycle Management:
+   Start:
+     - Git status確認
+     - CLAUDE.md読み込み
+     - docs/patterns/ 最近5件読み込み
+     - Mindbase自動ロード（Claude Code標準）
+
+   End:
+     - docs/patterns/ or docs/mistakes/ 更新
+     - CLAUDE.md更新（必要なら）
+     - Mindbase自動保存（Claude Code標準）
+
+2. Documentation Guardian:
+   - 実装前にdocs/patterns/とdocs/mistakes/を確認
+   - 関連ドキュメントを自動読み込み
+   - Pre-Implementation Confidence Check
+
+3. Commander (Complex Tasks):
+   - TodoWrite でタスク管理
+   - Sequentialで複雑な分析
+   - 並列実行の調整
+
+4. Post-Implementation Documentation:
+   - 成功パターン → docs/patterns/
+   - 失敗記録 → docs/mistakes/
+   - グローバルルール → CLAUDE.md
+
+5. Mistake Handler (Reflexion):
+   - docs/mistakes/ 検索（過去の失敗確認）
+   - 新しいミス → docs/mistakes/ 文書化
+   - 防止策の適用
+```
+
+### 簡潔な実装
+
+**不要な複雑性の削除**:
+```yaml
+削除:
+  - docs/memory/ 全体（Mindbaseで代替）
+  - write_memory() 使用（Serenaはコード理解専用）
+  - 複雑なメモリ管理ロジック
+
+残す:
+  - docs/patterns/（成功パターン）
+  - docs/mistakes/（失敗記録）
+  - CLAUDE.md（グローバルルール）
+  - TodoWrite（進捗管理）
+```
+
+**シンプルな自動起動**:
+```yaml
+Session Start:
+  1. git status && git branch
+  2. Read CLAUDE.md
+  3. Read docs/patterns/*.md (最近5件)
+  4. Mindbase自動ロード（透明）
+  5. 準備完了 → ユーザーリクエスト待機
+
+実装前:
+  1. 関連docs/patterns/とdocs/mistakes/読む
+  2. Confidence Check
+  3. Context7で公式ドキュメント確認（必要なら）
+
+実装中:
+  1. TodoWrite更新
+  2. コード理解が必要 → Serena使用
+  3. 複雑な分析 → Sequential使用
+
+実装後:
+  1. パターン抽出 → docs/patterns/
+  2. ミス記録 → docs/mistakes/
+  3. グローバルルール → CLAUDE.md
+  4. Mindbase自動保存
+```
+
+## 移行手順
+
+```yaml
+Phase 1 - Cleanup:
+  - [ ] docs/memory/ ディレクトリ削除
+  - [ ] MODE_Task_Management.md からmemory操作削除
+  - [ ] pm-agent.md からdocs/memory/参照削除
+
+Phase 2 - MCP Role Clarification:
+  - [ ] pm-agent.md にMCP使用ガイドライン追加
+  - [ ] Serena = コード理解専用 明記
+  - [ ] Mindbase = 自動管理 明記
+  - [ ] Sequential = 複雑な分析 明記
+  - [ ] Context7 = 公式ドキュメント参照 明記
+
+Phase 3 - Documentation:
+  - [ ] docs/patterns/README.md 作成（成功パターン記録ガイド）
+  - [ ] docs/mistakes/README.md 作成（失敗記録ガイド）
+  - [ ] Memory管理ポリシー文書化
+
+Phase 4 - Testing:
+  - [ ] セッション開始の自動ロードテスト
+  - [ ] 実装前のドキュメント確認テスト
+  - [ ] 実装後の文書化テスト
+  - [ ] MCPの適切な使用テスト
+```
+
+## 利点
+
+**シンプルさ**:
+- ✅ Memory管理層が明確（Mindbase / File-based / TodoWrite）
+- ✅ MCPの役割が明確（Serena=コード、Sequential=分析、Context7=ドキュメント）
+- ✅ 不要な複雑性削除（docs/memory/削除、write_memory()削除）
+
+**保守性**:
+- ✅ ライフサイクルが明確（永続 vs セッション内）
+- ✅ 責務分離（会話=Mindbase、知識=docs/、進捗=TodoWrite）
+- ✅ 削除ルールが明確（月次メンテナンス）
+
+**効率性**:
+- ✅ 自動管理（Mindbase、Serena自動削除）
+- ✅ 必要最小限のファイル読み込み
+- ✅ 適切なMCP使用（コード理解時のみSerena）
+
+## 結論
+
+**削除**: docs/memory/全体、write_memory()使用、MODE_Task_Management.mdのmemory部分
+
+**統合**: Mindbase（会話履歴）+ docs/（知識ベース）+ TodoWrite（進捗）+ Serena（コード理解）
+
+**簡潔化**: 責務を明確にして、不要な複雑性を削除
+
+これでPM Agentはシンプルかつ強力になります。