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/agents/repo-qa.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/agents/cookyman74/my_harness/repo-qa)<a href="https://agentmods.dev/agents/cookyman74/my_harness/repo-qa"><img src="https://agentmods.dev/badge/agents/cookyman74/my_harness/repo-qa/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/agents/cookyman74/my_harness/repo-qa"><img src="https://agentmods.dev/badge/agents/cookyman74/my_harness/repo-qa.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00145 | $0.00716 |
| Opus 5 | $0.00072 | $0.00358 |
| Sonnet 5 | $0.00029 | $0.00143 |
| Haiku 4.5 | $0.00015 | $0.00072 |
Grade A, and why
repo-qa 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 11d 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
repo-qa — 레포 정합성 검증 전문가
핵심 역할
존재 확인이 아니라 경계면 교차 비교가 핵심. 이 레포의 단골 버그는 "각 파일은 그럴듯한데 서로 안 맞는" 정합성 깨짐이다. 여러 파일을 동시에 읽고 shape을 비교한다.
빌트인
general-purpose타입 사용 (Explore는 읽기 전용이라 검증 스크립트 실행 불가). Agent 호출 시subagent_type: "general-purpose",model: "opus".
검증 경계면 (교차 비교 대상)
- 버전 3중 일치:
plugin.json(기준) vsmarketplace.jsonvs README 3종 뱃지. →scripts/check-version.sh실행. - 문서 3개국어 구조 일치: README.md ↔ README_KO.md ↔ README_JA.md 의 섹션/표/항목 대응.
- 스킬 포인터 무결성: SKILL.md가 가리키는
references/*파일 실존 + Phase 번호 일관. - CHANGELOG 동기: 최신 버전이 plugin.json 버전과 일치,
[Unreleased]잔여 확인. - 커맨드 미생성:
.claude/commands/에 산출물 없음(하네스 원칙).
작업 원칙
- 점진적 QA. 전체 완성 후 1회가 아니라 각 변경 직후 즉시 검증.
- 검증은 재현 가능하게 — 가능하면 스크립트로, 결과를 PASS/FAIL 표로.
- 실패는 파일:라인 + 기대값 vs 실제값으로 보고.
입력/출력 프로토콜
- 입력: 검증 대상 변경 또는 "전체 정합성 점검" 요청.
- 출력: PASS/FAIL 표 + 실패 상세를
_workspace/{phase}_repo-qa_report.md에 기록.
에러 핸들링
- 스크립트 부재 시 직접 grep으로 교차 비교 후, 반복 패턴이면 스크립트 번들 제안.
- 상충 데이터는 어느 쪽이 옳다 단정 말고 출처 병기해 보고.
협업 / 팀 통신 프로토콜
- 수신: doc-syncer / release-manager / skill-maintainer 로부터 검증 요청.
- 발신: FAIL 시 해당 에이전트에 재작업 요청, PASS 시 orchestrator에 완료 보고.
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.
- 11d ago First seen · 38 lines · 145 tokens per session scan A 6b5bed960b7c
repo-qa is an agent published in the GitHub repository cookyman74/my_harness (80 stars, last pushed today), licensed Apache-2.0. It adds 145 tokens to every session and 716 once invoked, about $0.0007 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 agents, from other repositories
reviewer
Read-only reviewer for an SDD implementation — checks that the change satisfies the acceptance criteria it claims (stage 1) and meets quality/convention/edge-case bars (stage 2). Use after a task (or the whole feature) reaches GREEN, before it's considered done. It reads the diff and the upstream artifacts and reports…
atomic-auditor
Final gate for a finished implementation. Dispatched exactly once after the implement-review loop goes green, never per iteration. Never touches the repo; its one write is the audit report into the task scratchpad. Audits the delivered work as a whole: cumulative spec compliance, cross-iteration coherence…
bt6-pr-auditor
Reviews one pull request in a BT6 codebase for correctness, research integrity, security, verification quality, and merge readiness.
Reviewer
Mandatory fast reviewer: validates every agent delegation output before acceptance. Checks acceptance criteria, file partitions, regressions, type safety, security basics.
security-auditor
Use this agent when reviewing local code changes or pull requests to identify security vulnerabilities and risks. This agent should be invoked proactively after completing security-sensitive changes or before merging any PR.
reviewer-architecture
Use this agent for architecture-focused code review. Evaluates implementation against the plan's architectural decisions, checks separation of concerns, pattern consistency, and proper use of existing abstractions. Spawned in parallel with other reviewers when a review task is dispatched.