Agent Orchestration
Available Agents
Located in ~/.claude/agents/:
| Agent | Purpose | When to Use |
|---|---|---|
| planner | Implementation planning | Complex features, refactoring |
| architect | System design | Architectural decisions |
| tdd-guide | Test-driven development | New features, bug fixes |
| code-reviewer | Code review | After writing code |
| security-reviewer | Security analysis | Before commits |
| build-error-resolver | Fix build errors | When build fails |
| e2e-runner | E2E testing | Critical user flows |
| refactor-cleaner | Dead code cleanup | Code maintenance |
| doc-updater | Documentation | Updating docs |
Immediate Agent Usage
No user prompt needed:
- Complex feature requests - Use planner agent
- Code just written/modified - Use code-reviewer agent
- Bug fix or new feature - Use tdd-guide agent
- Architectural decision - Use architect agent
Cost-Efficient Exploration (Haiku 모델 활용)
코드베이스 탐색, 파일 구조 파악 등 사전 조사 단계에서는 저비용 모델을 활용한다:
1# 탐색 작업 → Haiku 모델로 비용 절감
2Agent(
3 subagent_type: "Explore",
4 model: "haiku",
5 prompt: "prototypes/sokind-admin의 라우트 구조를 파악해줘"
6)
7
8# 구현/분석 작업 → Opus 모델 유지
9Agent(
10 subagent_type: "general-purpose",
11 prompt: "이 컴포넌트를 리팩토링해줘"
12)Haiku 사용이 적합한 경우:
- 파일/폴더 구조 파악
- 특정 패턴/함수 검색
- 의존성 그래프 추적
- 코드 통계 수집
Opus가 필요한 경우:
- 아키텍처 의사결정
- 복잡한 코드 리뷰
- 보안 분석
- 구현 계획 수립
Parallel Task Execution
ALWAYS use parallel Task execution for independent operations:
1# GOOD: Parallel execution
2Launch 3 agents in parallel:
31. Agent 1: Security analysis of auth module
42. Agent 2: Performance review of cache system
53. Agent 3: Type checking of utilities
6
7# BAD: Sequential when unnecessary
8First agent 1, then agent 2, then agent 3Multi-Perspective Analysis
For complex problems, use split role sub-agents:
- Factual reviewer
- Senior engineer
- Security expert
- Consistency reviewer
- Redundancy checker