Borrowing it
Nothing to install: this file belongs to cookyman74/my_harness. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/cookyman74/my_harness/main/.claude/skills/repo-maintainer/SKILL.mdgit clone --depth 1 https://github.com/cookyman74/my_harnessWrote 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/cookyman74/my_harness/repo-maintainer)<a href="https://agentmods.dev/skills/cookyman74/my_harness/repo-maintainer"><img src="https://agentmods.dev/badge/skills/cookyman74/my_harness/repo-maintainer/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/cookyman74/my_harness/repo-maintainer"><img src="https://agentmods.dev/badge/skills/cookyman74/my_harness/repo-maintainer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 5.1 | $0.00241 | $0.01859 |
| Opus 5 | $0.00120 | $0.00929 |
| Sonnet 5 | $0.00048 | $0.00372 |
| Haiku 4.5 | $0.00024 | $0.00186 |
Grade A, and why
repo-maintainer 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 12d 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.
How it starts
The opening of the file, as written. The whole thing — 79 lines — stays where its author put it; the contents beside it link to each section on GitHub.
repo-maintainer — 레포 유지보수 오케스트레이터
이 레포(harness 플러그인) 유지보수를 에이전트 팀으로 조율한다. 실행 모드: 에이전트 팀 (생성-검증 + 파이프라인 하이브리드).
트리거
- 활성: 여러 파일·여러 전문성이 얽힌 레포 유지보수/릴리스/스킬 배포/안정화 요청(예: "레포 유지보수", "릴리스 준비", "문서/버전 정합성 점검", "하네스 스킬 개선해서 배포", "팩토리 고도화", "안정화", "회귀 방지", "정책 감사").
- 비활성(near-miss): 단순 1파일 수정·오타 교정·단일 문서 질문·코드 설명/읽기·이 레포와 무관한 작업. 이런 요청은 오케스트레이션 없이 직접 처리한다(유사해 보여도 팀을 띄우지 않음).
절차
Phase 0(컨텍스트 확인) → Phase 1(작업 분류 → 실행 경로) → Phase 2(팀 실행) → Phase 3(데이터 전달 프로토콜) → 에러 핸들링 → Phase 4(완료 + 진화). 각 단계의 상세는 아래 해당 절을 따른다.
팀 구성
| 에이전트 | 타입 | 담당 | 스킬 |
|---|---|---|---|
doc-syncer |
general-purpose | README 3개국어 + 뱃지 동기 | doc-sync |
release-manager |
general-purpose | 버전·CHANGELOG·태그 | release-flow |
skill-maintainer |
general-purpose | skills/harness 본문 개선 | skill-authoring |
stabilizer |
general-purpose | 안정화·회귀 게이트(정책감사·외부리뷰·회귀 드라이런) | external-review-loop + run-policy-audit.sh |
repo-qa |
general-purpose | 교차 파일 정합성 검증 | (에이전트 + check-version.sh) |
모든 Agent 호출(팀원 spawn 포함)은
model: "opus".
Phase 0: 컨텍스트 확인
_workspace/존재 여부 확인.- 존재 + 부분 수정 요청 → 부분 재실행 (해당 에이전트만).
- 존재 + 새 작업 → 기존
_workspace/를_workspace_prev/로 이동 후 새 실행. - 미존재 → 초기 실행.
bash .claude/skills/release-flow/scripts/check-version.sh로 현 정합성 스냅샷.
Phase 1: 작업 분류 → 실행 경로
요청을 분류하고 필요한 에이전트만 활성화한다 (불필요한 팀원 = 조율 오버헤드):
| 요청 유형 | 활성 에이전트 | 패턴 |
|---|---|---|
| 문서만 동기화 | doc-syncer → repo-qa | 파이프라인 |
| 버전 릴리스 | release-manager → doc-syncer → repo-qa | 파이프라인+검증 |
| 스킬 본문 개선(정본 변경·중대 blast-radius) | skill-maintainer → stabilizer(정책감사→외부리뷰→회귀 드라이런) → (영향 시 doc-syncer) → repo-qa | 생성-검증+안정화 게이트 |
| 팩토리 안정화·회귀 점검 | stabilizer 단독(run-policy-audit + external-review-loop) → FAIL 시 skill-maintainer 호출 | 검증 |
| 종합 점검 | repo-qa 단독 (FAIL 시 해당 에이전트 호출) | 검증 |
안정화 게이트(중대): 팩토리
skills/myharness/정본 변경은 모든 생성 하네스에 전파(blast-radius) → skill-maintainer 변경 후 stabilizer 게이트 필수. 정책감사(run-policy-audit.sh)·외부리뷰(external-review-loop·러너 제외 codex+agy)·회귀 드라이런을 리스크 등급으로 조절(문구=감사만 / 로직=+외부리뷰 / 아키텍처=+드라이런). 상세:.claude/agents/stabilizer.md.
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.
- 12d ago First seen · 79 lines · 241 tokens per session scan A f381cfa9411c
repo-maintainer is a skill published in the GitHub repository cookyman74/my_harness (80 stars, last pushed today), licensed Apache-2.0. It adds 241 tokens to every session and 1,859 once invoked, about $0.0012 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
recipe-create-meet-space
Create a Google Meet meeting space and share the join link.
atmos-config
Atmos root configuration: atmos.yaml discovery, precedence, deep merging, basepath, imports, minimal bootstrap, and routing to narrower Atmos skills.
workthreads
SpecStory Workthreads - a weekly work-thread rollup across a team's repos from SpecStory coding histories (any agent - Claude Code, Codex, Cursor, Gemini, and more). It groups the window's sessions into threads of work per project and labels each new / open / recently closed, so a lead sees what shipped, what is still…
story-readiness
Validate that a story file is implementation-ready. Checks for embedded GDD requirements, ADR references, engine notes, clear acceptance criteria, and no open design questions. Produces READY / NEEDS WORK / BLOCKED verdict with specific gaps. Use when user says 'is this story ready', 'can I start on this story', 'is…
projects
List all managed projects with status, branch, open PRs, and open issue counts — portfolio-level view.
magpie-security-issue-import-from-md
Open one or more tracking issues from a markdown file containing a batch of security findings. Each finding becomes one tracker landing in the Needs triage board column. The file itself is the full report — there is no inbound reporter to reply to and no PR to inspect.