Phase 1: Research (Gemini via Subagent)
    ↓
Phase 2: Requirements & Planning (Claude)
    ↓
Phase 3: Design Review (Codex via Subagent)
    ↓
Phase 4: Task Creation (Claude)
    ↓
Phase 5: CLAUDE.md Update (Claude)
    ↓
[Implementation...]
    ↓
Phase 6: Multi-Session Review (New Session + Codex)

Task tool parameters:
- subagent_type: "general-purpose"
- run_in_background: true
- prompt: |
    Research for: {feature}

    1. Call Gemini CLI:
       gemini -p "Analyze this repository for: {feature}

       Provide:
       1. Repository structure and architecture
       2. Relevant existing code and patterns
       3. Library recommendations
       4. Technical considerations
       " --include-directories . 2>/dev/null

    2. Save full output to: .claude/docs/research/{feature}.md

    3. Return CONCISE summary (5-7 bullet points)

Task tool parameters:
- subagent_type: "general-purpose"
- run_in_background: true
- prompt: |
    Review plan for: {feature}

    Draft plan: {plan from Phase 2}

    1. Call Codex CLI:
       codex exec --model gpt-5.2-codex --sandbox read-only --full-auto "
       Review this implementation plan:
       {plan}

       Analyze:
       1. Approach assessment
       2. Risk analysis
       3. Implementation order
       4. Improvements
       " 2>/dev/null

    2. Return CONCISE summary:
       - Top 3-5 recommendations
       - Key risks
       - Suggested order

{
    "content": "Implement {specific feature}",
    "activeForm": "Implementing {specific feature}",
    "status": "pending"
}

---

## Current Project: {feature}

### Context
- Goal: {1-2 sentences}
- Key files: {list}
- Dependencies: {list}

### Decisions
- {Decision 1}: {rationale}
- {Decision 2}: {rationale}

### Notes
- {Important constraints or considerations}

Task tool parameters:
- subagent_type: "general-purpose"
- prompt: |
    Review implementation for: {feature}

    1. Run: git diff main...HEAD
    2. Call Codex CLI:
       codex exec --model gpt-5.2-codex --sandbox read-only --full-auto "
       Review this implementation:
       {diff output}

       Check:
       1. Code quality and patterns
       2. Potential bugs
       3. Missing edge cases
       4. Security concerns
       " 2>/dev/null

    3. Return findings and recommendations

## 프로젝트 계획 : {feature}

### 조사 결과 (Gemini)
{Key findings - 3-5 bullet points}

### 설계 정책 (Codex 검토)
{Approach with refinements}

### 작업 목록 ({N}개)
{Task list}

### 위험과 주의사항
{From Codex analysis}

### 다음 단계
1. 이 계획으로 진행하시겠습니까?
2. 구현 완료 후 다른 세션에서 검토를 수행한다.

---
이 계획으로 진행하시겠습니까?