Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add skills/ggombee/code-forge/setup-agent-teamsnpx skills add ggombee/code-forge --skill setup-agent-teamsgit clone --depth 1 https://github.com/ggombee/code-forgeWhat it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00028 | $0.00896 |
| Opus 5 | $0.00014 | $0.00448 |
| Sonnet 5 | $0.00006 | $0.00179 |
| Haiku 4.5 | $0.00003 | $0.00090 |
Grade B, and why
setup-agent-teams scanned grade B with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
cat ~/.claude/settings.json How it starts
The opening of the file, as written. The whole thing — 126 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/setup-agent-teams
Claude Code Agent Teams 기능을 활성화한다. Claude Max 구독 필수.
사전 조건
| 조건 | 확인 방법 |
|---|---|
| Claude Max 구독 | claude --version + 플랜 확인 |
| Claude Code v2.1.32+ | claude --version |
실행 워크플로우
아래 단계를 순서대로 즉시 실행한다.
Step 1. 환경변수 설정
~/.claude/settings.json에 env 블록을 추가한다.
# 현재 설정 확인
cat ~/.claude/settings.json
env 블록이 없으면 추가:
{
"env": {
"CLAUDE_CODE_EXPERIMENTAL_AGENT_TEAMS": "1"
}
}
이미 env 블록이 있으면 해당 키만 추가한다.
Step 2. 세션 재시작 안내
환경변수 설정 후 현재 세션을 종료하고 새 세션을 시작해야 Agent Teams 도구가 로드된다.
설정 완료! Agent Teams를 사용하려면 새 세션을 시작하세요.
활성화되는 도구:
- TeamCreate — 팀 생성
- TeamDelete — 팀 삭제
- SendMessage — 팀원 간 메시지
- TaskCreate — 작업 생성 (팀원에게 할당)
- TaskUpdate — 작업 상태 변경
- TaskList — 작업 목록 조회
Step 3. 검증 (새 세션에서)
새 세션 시작 후 아래를 실행하여 정상 활성화 확인:
"Agent Teams 테스트: 2명의 팀원으로 간단한 코드 리뷰를 진행해줘"
TeamCreate가 호출되면 정상.
Agent Teams 사용 패턴
기본 흐름
TeamCreate("team-name")
→ Agent(name="member-1", team_name="team-name", prompt="...")
→ Agent(name="member-2", team_name="team-name", prompt="...")
→ SendMessage(to="member-1", message="...")
→ 작업 완료 대기
→ TeamDelete("team-name")
추천 팀 구성
| 시나리오 | 팀원 | 모델 |
|---|---|---|
| 코드 리뷰 | reviewer-1 (품질), reviewer-2 (보안) | sonnet, sonnet |
| 기능 구현 | architect (설계), implementor (구현) | opus, sonnet |
| 토론 | advocate (찬성), critic (반대), judge (판정) | sonnet, sonnet, opus |
| 리서치 | researcher-1 (공식문서), researcher-2 (커뮤니티) | sonnet, haiku |
Codex 팀원 참여
Codex를 팀원처럼 활용하려면 Bash 도구로 codex exec 실행:
codex exec -s read-only "{프롬프트}"
Agent Teams 팀원이 Codex를 호출하는 구조로 cross-model 협업 가능.
주의사항
| 주의 | 설명 |
|---|---|
| 토큰 사용량 증가 | 팀원마다 독립 컨텍스트 → 토큰 N배 |
| 순차 작업 부적합 | 병렬 가능한 독립 작업에만 사용 |
| Claude Max 전용 | 일반 플랜에서는 Agent 병렬 spawn으로 폴백 |
| 세션 재시작 필수 | settings.json 수정 후 현재 세션에서는 미반영 |
참조
| 문서 | 용도 |
|---|---|
instructions/multi-agent/coordination-guide.md |
멀티에이전트 협업 패턴 |
instructions/multi-agent/execution-patterns.md |
작업별 실행 패턴 |
skills/debate/SKILL.md |
Agent Teams 기반 토론 |
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 2d ago First seen · 126 lines · 28 tokens per session scan B 166e9d9a4e5c
setup-agent-teams is a skill published in the GitHub repository ggombee/code-forge (13 stars, last pushed 2mo ago), licensed MIT. It adds 28 tokens to every session and 896 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
digital-health-clinical-asr-setup
Stage 1 of Clinical ASR Flywheel. Use when bootstrapping a cycle: NVCF+MW disclosure, NVIDIAAPIKEY check, deps install, TTS+ASR smoke test.
scaffold
Use when starting hyperflow in a new project, refreshing the .hyperflow/ cache, or installing auto-detection shims (AGENTS.md, CLAUDE.md). One-shot project setup; does not start the spec → scope → dispatch chain. Trigger with /hyperflow:scaffold, "init hyperflow", "set up hyperflow", "refresh hyperflow", "install…
install-openviking-memory
Install and configure the OpenViking long-term memory plugin for OpenClaw via natural conversation. Once installed, the plugin automatically captures facts from chats and recalls relevant context before each reply (auto-capture + auto-recall, cross-session). Covers prerequisites, install through OpenClaw's plugin…
environment-discovery
Systematic exploration of unknown environments before starting work.
forgetful-cli-setup
Set up the Forgetful CLI and connect from a terminal — install, local or remote mode, auth, and verification. Use when connecting a human or headless agent via shell, wiring CI with token auth, or operating a local server (serve, database selection, feature flags, re-embedding). Also covers the machine contract…
forgetful-mcp-setup
Set up an MCP client for Forgetful — wire Claude Code, Cursor, Copilot, Codex, Gemini, or OpenCode to the server and verify the connection behaves. Covers stdio vs HTTP transport, auth and scopes, the three meta-tools every client sees, and delegation to subagents.