my_harness: Agent for Claude Code

.claude/agents/repo-qa.md

repo-qa is an agent for Claude Code from cookyman74/my_harness. It costs 145 tokens per session (716 once invoked), scanned A, original, Apache-2.0.

A quality checker for repository changes that must agree across multiple files. It compares versions, translated READMEs, badges, referenced skill files, release notes, and related configuration.

In plain words
What is it for?
Use it after version bumps, documentation updates, skill changes, or before a release to produce a reproducible pass/fail report.
Why use it?
Files can each look correct while disagreeing with one another. Cross-file checks catch mismatched versions, missing references, translation gaps, stale links, and unfinished release information.

Agent for Claude Code

Written for Claude Code: installed under .claude/. Also seen: model in frontmatter; reads .claude/ paths.

This is cookyman74/my_harness's own configuration. It tells Claude Code how to work on my_harness itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything my_harness configures →

Part of the myharness plugin — 7 skills, 6 agents shipped together

Reuse

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.

Copy the file
curl -O https://raw.githubusercontent.com/cookyman74/my_harness/main/.claude/agents/repo-qa.md
Clone the repo
git clone --depth 1 https://github.com/cookyman74/my_harness

Made for: Claude Code.

Or install myharness, the plugin that ships this one along with the rest of its 7 skills, 6 agents.

Wrote 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.

agentmods badge for repo-qa

README.md
[![agentmods](https://agentmods.dev/badge/agents/cookyman74/my_harness/repo-qa/github.svg)](https://agentmods.dev/agents/cookyman74/my_harness/repo-qa)
Your own site
<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.

agentmods 80×15 button for repo-qa

Your own site · 80×15
<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>
Per session 145 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 716 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce 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

Measured 11d ago against content hash 6b5bed960b7c, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

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.

.claude/agents/repo-qa.md · 38 lines

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-purpose 타입 사용 (Explore는 읽기 전용이라 검증 스크립트 실행 불가). Agent 호출 시 subagent_type: "general-purpose", model: "opus".

검증 경계면 (교차 비교 대상)

  1. 버전 3중 일치: plugin.json(기준) vs marketplace.json vs README 3종 뱃지. → scripts/check-version.sh 실행.
  2. 문서 3개국어 구조 일치: README.md ↔ README_KO.md ↔ README_JA.md 의 섹션/표/항목 대응.
  3. 스킬 포인터 무결성: SKILL.md가 가리키는 references/* 파일 실존 + Phase 번호 일관.
  4. CHANGELOG 동기: 최신 버전이 plugin.json 버전과 일치, [Unreleased] 잔여 확인.
  5. 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.
Changes

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.

  1. 11d ago First seen · 38 lines · 145 tokens per session scan A 6b5bed960b7c

Subscribe to this mod's changes

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.

Related

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…

genkovich/sdd · 81 tokens

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…

damusix/atomic-claude · 169 tokens

bt6-pr-auditor

Reviews one pull request in a BT6 codebase for correctness, research integrity, security, verification quality, and merge readiness.

elder-plinius/T3MP3ST · 32 tokens

Reviewer

Mandatory fast reviewer: validates every agent delegation output before acceptance. Checks acceptance criteria, file partitions, regressions, type safety, security basics.

monkilabs/opencastle · 30 tokens

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.

NeoLabHQ/context-engineering-kit · 40 tokens

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.

HirogaKatageri/hirokata · 56 tokens