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/imgompanda/fireauto/fireauto-team-guidenpx skills add imgompanda/fireauto --skill fireauto-team-guidegit clone --depth 1 https://github.com/imgompanda/fireautoWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/imgompanda/fireauto/fireauto-team-guide)<a href="https://agentmods.dev/skills/imgompanda/fireauto/fireauto-team-guide"><img src="https://agentmods.dev/badge/skills/imgompanda/fireauto/fireauto-team-guide.svg" alt="Measured on agentmods" height="20"></a>What 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 | $0.00099 | $0.00832 |
| Opus 5 | $0.00049 | $0.00416 |
| Sonnet 5 | $0.00020 | $0.00166 |
| Haiku 4.5 | $0.00010 | $0.00083 |
Grade A, and why
fireauto-team-guide scanned grade A with 0 findings 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 4d 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.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
컴퍼니 모델 팀 시스템
Claude Code 빌트인 팀 기능을 활용한 멀티 에이전트 협업 패턴.
핵심 개념: 컴퍼니 모델
회사처럼 동작하는 에이전트 조직:
- CEO (메인 에이전트): 방향 설정, 태스크 분배, 승인/반려, 최종 검토
- 팀원 (서브 에이전트): 각자 담당 업무 수행, 서로 SendMessage로 실시간 논의
- 공유 태스크 보드: TaskCreate/TaskUpdate로 진행 상황 관리
빌트인 도구
| 도구 | 역할 |
|---|---|
TeamCreate |
팀 생성, 공유 태스크 보드 초기화 |
TeamDelete |
팀 삭제 및 리소스 정리 |
TaskCreate |
태스크 등록 (담당자 지정) |
TaskUpdate |
태스크 상태 변경 |
TaskList |
전체 태스크 조회 |
TaskGet |
개별 태스크 상세 조회 |
SendMessage |
에이전트 간 DM (자동 전달, 유휴 에이전트도 깨움) |
Agent |
팀원 에이전트 스폰 (team_name 파라미터 필수) |
Git Worktree 격리
Agent 호출 시 isolation: "worktree" 옵션을 사용하면:
- 각 에이전트가 독립된 git 브랜치 + 작업 디렉토리에서 작업
- 서로의 코드 변경이 충돌하지 않음
- 완료 후 메인 브랜치에 순차적으로 병합
- 마치 각 개발자가 자기 PC에서 독립적으로 개발하는 것과 같음
에이전트 간 대화 (SendMessage)
핵심 차별점: 에이전트들이 파일이 아닌 SendMessage로 직접 대화합니다.
frontend-dev -> backend-dev:
"UserProfile에 avatarUrl 필드 추가해줄 수 있어?"
backend-dev -> frontend-dev:
"추가했어. nullable이니 fallback 처리 부탁."
frontend-dev -> CEO:
"pagination 방식을 결정해주세요. offset vs cursor."
CEO -> all:
"offset으로 가겠습니다."
병렬 vs 순차 판단
병렬 (컴퍼니 모델 적합)
- 독립적인 기능/페이지/API 개발
- 프론트엔드/백엔드 분리
- 대규모 리팩토링 (모듈별)
순차 (단일 에이전트 적합)
- 강한 의존성 (앞선 작업 결과가 다음 입력)
- 동일 파일 집중 수정
- 분할 오버헤드 > 작업 자체
팀 구성 가이드
| 시나리오 | 팀원 | 분할 기준 |
|---|---|---|
| API + 프론트 | 2명 | backend-dev, frontend-dev |
| 풀스택 기능 | 3명 | backend, frontend, tester |
| 대규모 리팩토링 | 4명 | type-lead, core, ui, test |
커맨드
/fireauto-team- 팀 구성, 실행, 대화 관리 (대화 기능 통합)/fireauto-team-status- 태스크 보드 및 진행 상태 확인
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.
- 4d ago First seen · 86 lines · 99 tokens per session scan A 03cb32e2f430
fireauto-team-guide is a skill published in the GitHub repository imgompanda/fireauto (140 stars, last pushed 4mo ago), licensed MIT. It adds 99 tokens to every session and 832 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
flow-next-pilot
Single-tick autonomous build-loop conductor. One spec or the backlog, one stage per tick (pipeline.chainStages chains qa into make-pr), emits PILOTVERDICT. Use when asked to pilot a spec or backlog.
backlog
Read, work, and maintain a Git repo's deferred-work items in docs/backlog/, one file per item. Use when the user says "backlog", "check backlog", "what's on my backlog", "work the backlog", "address the backlog", "add to backlog", "clean up backlog", or when a review or task produced items that are real but not being…
graduate-backlog
Graduate a project's in-repo backlog (roadmap phases, sprint deliverables, ADRs) onto a forge issue tracker at a thin-hybrid default, once the backlog outgrows a single contributor. Use when a team needs to see and claim work that currently lives only in docs/roadmap and docs/sprints, when a repo has a mature in-repo…
st-setup-project
Smalltalk (Pharo/Squeak) project boilerplate creator. Use when the user asks to create a new Pharo/Smalltalk project from scratch, when project structure is missing (no src/ directory or .project file), when the user wants to start a new Smalltalk development project, or when setting up BaselineOf, Core, and Tests…
plan-sprint
Create a sprint plan for a new development cycle. Use when starting a new sprint, after completing wrapup-sprint, or when initializing Sprint 1 for a new project.
speckit-workflow
Manage and run Spec Kit automation workflows via specify workflow. USE FOR: running a workflow by ID or local YAML, resuming a paused/failed run, checking run status, listing/installing/removing workflows, searching the workflow catalog, showing a workflow step graph. DO NOT USE FOR: extensions (use…