Accepts any topic, designs a team on its own, a general-purpose orchestrator skill that automatically handles everything from research → analysis → feasibility review → deriving results.
0. Environment check
0-1. Check whether the agent team feature is enabled
cat ~/.claude/settings.json | grep -i "CLAUDE_CODE_EXPERIMENTAL_AGENT_TEAMS"
"1"if not, stop immediatelyand guide:
⚠️ 에이전트 팀 기능이 비활성화되어 있습니다.
Add the following to ~/.claude/settings.json and then restart Claude Code:
{ "env": { "CLAUDE_CODE_EXPERIMENTAL_AGENT_TEAMS": "1" } }
Reference: docs/06-agent-team-settings.md
### 0-2. tmux 환경 감지
```bash
echo "${TMUX:-not_in_tmux}"
not_in_tmuxif so → output the guide and continue (works in in-process mode even without tmux):
💡 tmux 환경이 아닙니다.
팀원을 실시간으로 동시에 확인하려면 tmux 세션 안에서 실행하세요:
tmux new-session -s think && claude
지금은 in-process 모드로 진행합니다. (Shift+Down으로 팀원 전환)
0-3. Detect the Codex plugin
cat ~/.claude/settings.json | grep -i "openai-codex"
"codex@openai-codex": trueif present →CODEX_AVAILABLE=true- if not →
CODEX_AVAILABLE=false(substitute with a critic team member, output the guide)
ℹ️ Codex 플러그인 미감지 — critic 팀원으로 교차 검증을 대체합니다.
(Codex 활성화: settings.json에 "codex@openai-codex": true 추가)
1. Complexity judgment — team vs solo
When a topic is received, before forming a team, first judge the complexity. This is to prevent overengineering.
Complexity score table
| Item | Condition | Score |
|---|---|---|
| Perspective diversity | Are two or more independent perspectives needed | +1 |
| Parallel separation | Are there two or more independent areas that can be handled simultaneously | +1 |
| Cross-validation | Is counterargument/feasibility review meaningful for the conclusion | +1 |
Judgment criteria
| Score | Handling method |
|---|---|
| 0점 | Solo handling — answer directly without a team |
| 1점 | Borderline — decide after confirming with the user |
| 2~3점 | Team formation → run the agent team |
0-point examples (solo handling):
- "Tell me how to migrate to React Query v5"
- "Find the cause of this code bug"
- "Simple comparison of A vs B"
2–3-point examples (team needed):
- "How should we change our service's authentication architecture?" (3 perspectives: security/performance/maintainability)
- "Set a development strategy for this feature" (separate research + design + risk)
- "Analyze 3 competitors" (parallel research then synthesis)
Example of user confirmation when it is 1 point:
이 주제는 단독으로도 처리 가능합니다.
팀으로 진행하면 더 다각적이지만 시간이 걸립니다.
[1] 팀으로 진행 [2] 단독으로 바로 답변
2. Autonomous team type decision
If the score is 2–3 points, autonomously decide the team type according to the nature of the topic.
Team type
| Type | When | Composition |
|---|---|---|
| Research team | Information gathering, comparison, status 파악 | PM + N analysts (by perspective) + critic |
| Execution team | Design, planning, artifact generation | PM + N developers (by area) + critic |
| Verification team | Quality, validity, and risk review | PM + reviewer + tester + critic |
| Mixed team | Complex task | PM + research + execution + verification mixed + critic |
critic role (always included)
- Team members' conclusions attempt counterargumentsan independent reviewer who does this
- Determine when to bring in the critic based on topic complexity:
- Simple (2 points): only once at the end
- Complex (3 points): midway + at the end
3. Present team composition plan → user confirmation
Before forming the team, the composition plan must be shown first. This is to avoid wasting resources on a wrong team composition.
📋 팀 구성안
주제: [주제 한 줄 요약]
팀 유형: [조사/실행/검증/혼합]
팀원:
├─ PM(리더): 종합 판단 및 결과 도출
├─ [역할1]: [담당 관점/영역]
├─ [역할2]: [담당 관점/영역]
├─ [역할3]: [담당 관점/영역] (복잡도 높을 때)
└─ critic: 결론 타당성 반론 검토
예상 산출물: [결과물 형태]
이 구성으로 진행할까요? [Y/n]
If the user requests changes, revise the composition plan and reconfirm. If there is no response within 5 seconds or the answer is Y → execute immediately.
4. Create team and register tasks
TeamCreate: team_name="think-[주제-축약]-team"
# 조사 팀 예시
TaskCreate:
1. "[관점1] 조사" (owner: analyst-1)
2. "[관점2] 조사" (owner: analyst-2)
3. "[관점3] 조사" (owner: analyst-3) ← 관점 수에 따라 가변
4. "종합 판단" (blockedBy: 1,2,3, owner: pm)
5. "타당성 검토" (blockedBy: 4, owner: critic)
# 실행 팀 예시
TaskCreate:
1. "[영역1] 작성" (owner: dev-1)
2. "[영역2] 작성" (owner: dev-2)
3. "통합 검증" (blockedBy: 1,2, owner: pm)
4. "타당성 검토" (blockedBy: 3, owner: critic)
Task dependency rules:
- Parallelizable research/work:
blockedBynone - PM synthesis: after all team members complete
- critic: after PM synthesis
5. Deploy team members (parallel execution)
Deploy all team members in the same turn run_in_background: truesimultaneously.
Essential principles for team member prompts
- Role declaration: "You are [role]. You are in charge of Task #N."
- Sufficient background: Team members know nothing about the conversation history — provide the topic, purpose, and context in detail
- Absolute file paths: If there are files to reference, specify them with absolute paths
- Completion protocol: "After completion, TaskUpdate Task #N → completed, report to PM (team-lead@teamname) via SendMessage. Within 150 lines"
- Output limit: Specify the number of lines in the report (save tokens)
Key points for critic team member prompts
너는 독립 비판 검토자(critic)이다. Task #N 담당.
PM의 종합 판단 결과를 받아 아래 관점에서 반론을 시도하라:
1. 빠진 관점이나 증거는 없는가?
2. 논리적 비약이나 과도한 단순화는 없는가?
3. 리스크나 부작용이 충분히 다뤄졌는가?
반론이 타당하면 → "수정 필요: [구체적 항목]"
결론이 견고하면 → "타당성 확인: [근거]"
보고는 PM에게 SendMessage. 100줄 이내.
6. Collect reports and PM synthesis
When the PM receives all team member reports:
- Declare selection criteria first — state the evaluation criteria before drawing a conclusion
평가 기준: - 독립 분해 가능한가? (병렬 처리가 의미 있는가) - 검증 가능한 산출물이 있는가? - 역할 분담이 단독 대비 실질적 이점이 있는가? - Organize common points/agreements
- State conflict points/disagreements
- Decide whether to reflect critic counterarguments
- Derive final conclusion
Handling team member non-response
1. SendMessage로 보고 재요청 → 3분 대기
2. 응답 없으면 → 새 팀원(v2)으로 재투입
3. config.json에서 무응답 팀원 강제 제거 후 TeamDelete 진행
7. Codex cross-validation (when CODEX_AVAILABLE=true)
Automatically executed after PM synthesis is complete:
/codex:adversarial-review
Codex (GPT-5.4) looks for weaknesses in the conclusion from a different perspective than the Claude team. Reflect Codex feedback in the final result or state "review complete, no disagreements."
CODEX_AVAILABLE=false 시: Replace with critic team member results. Proceed without separate notice.
8. Team cleanup
SendMessage(shutdown_request) → 모든 팀원에게
TeamDelete → 팀 정리
If TeamDelete fails (active members error):
# config.json에서 팀원 강제 제거 후 재시도
python3 -c "
import json, os
path = os.path.expanduser('~/.claude/teams/[팀이름]/config.json')
with open(path) as f: data = json.load(f)
data['members'] = [m for m in data['members'] if m['name'] == 'team-lead']
with open(path, 'w') as f: json.dump(data, f, indent=2)
"
9. Output final result
## [주제] — 분석 결과
### 팀 구성
- 팀 유형: [유형]
- 팀원: [역할 목록]
- Codex 교차검증: [적용/미적용]
### 핵심 발견
1. [발견 1]
2. [발견 2]
3. [발견 3]
### 선정 기준
- 독립 분해 가능성: [평가]
- 산출물 검증 가능성: [평가]
- 역할 분담 실질 이점: [평가]
### 결론
[PM 종합 판단 — 명확하고 직접적으로]
### critic 검토
[타당성 확인 / 수정 반영 내역]
※ "조건부 타당" 판정이 있으면 해당 조건을 결론에 반드시 병기
### Codex 교차검증 (적용 시)
[이견 없음 / 반영된 수정 사항]
### 다음 액션
→ [권장 행동 1]
→ [권장 행동 2]
Reference documents
docs/07-에이전트팀-실전경험-E2E이식.md— Practical team operation patterns, team member prompt templatesdocs/06-에이전트팀-설정.md— tmux/settings.json configuration guidereferences/team-patterns.md— Detailed prompt examples by team type
Usage examples
# 어떤 주제든 그냥 전달
/peach-think-team 우리 서비스 인증 아키텍처 JWT vs Session 어떻게 결정해야 해?
/peach-think-team 경쟁사 3곳(토스, 카카오페이, 네이버페이) 결제 UX 분석해줘
/peach-think-team 이 PR diff를 보고 설계 상 문제점 찾아줘
/peach-think-team 내년 기술 로드맵 어떻게 잡으면 좋을지 다각도로 검토해줘