harness-audit
Skill0 starsChanged 5 months agoMITView on GitHub
Claude Code 하네스(.claude/agents·skills, CLAUDE.md, 가이드 문서)의 끊긴 배선을 스캔한다. 삭제·리네임된 에이전트/스킬/문서 참조, 존재하지 않는 경로, 고아 항목을 탐지해 리포트한다. 에이전트·스킬을 추가·삭제·이름변경한 직후, 또는 주기 점검 시 사용. 어느 프로젝트에서나 사용 가능. 트리거 키워드: "하네스 감사", "배선 점검", "dangling 참조", "끊긴 참조", "harness audit", "/harness-audit"
22 other projects use a version of this.
Adopted by
Most recently taken up by
- venhdev/skillstheir own version, first seen Nov 8, 2026
- DaeSeokSong/oh-my-ouroborostheir own version, first seen Nov 1, 2026
- AnastasiyaW/codex-claude-code-configtheir own version, first seen Oct 30, 2026
- fernandopetry/keelsontheir own version, first seen Oct 23, 2026
- Jason-hub-star/model-orchestratortheir own version, first seen Oct 20, 2026
- simp5layer/harness-audit-plugintheir own version, first seen Oct 20, 2026
Used with
Projects with it also use autopilot, test and 2 more.
Other files people use alongside this one.
Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
ibahgatSkillautopilot
Run autonomous multi-stage execution loops until acceptance criteria pass or blockers are reached.
Also in 3 projects that use this
Microsoft AzureSkilltest
Also in 3 projects that use this
nicolasestremSkillbrainstorm
Structured idea generation and solution exploration with systematic analysis.
Also in 3 projects that use this
GoogleSkilltdd
Test-driven development. Use when the user wants to build features or fix bugs test-first, mentions "red-green-refactor", or wants integration tests.
Also in 3 projects that use this
Other versions22 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 22
- AnastasiyaW/claude-code-config★ 214same name
- AnastasiyaW/codex-claude-code-config★ 214same name
- Kanevry/session-orchestrator★ 53same name
- fabianmartinelli-fm/harness-audit★ 7same name
- fmslutions/harness-audit★ 7same name
- fernandopetry/keelson★ 5same name
- DaeSeokSong/oh-my-ouroboros★ 3same name
- Sagargupta16/agent-brain★ 2same name
- sattva2020/skills★ 2same name
- contextosai/skills★ 1same name
12 more not listed
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository8 other files it gives its agents.
- doc-driftSkill
- document-reviewSkill
- project-fixSkill
- project-initSkill
- project-issueSkill
- project-prSkill
- release-notesSkill
- session-closeSkill
The file
Files
Harness Audit
읽기 전용 — 탐지만. 수정은 발견 후 사용자 확인 하에.
저장소 루트에서 실행. 스캔 대상은 CLAUDE.md·.claude/agents·.claude/skills·하네스 가이드 문서(있으면 docs/).
쉘 호환: 모든 쉘(bash·zsh·sh/dash) 동작 보장. 금지 —
for x in $var/for x in $(...)(zsh 단어분리 안 함, 첫 항목만 돔),< <(...)(POSIX sh 미지원).... | while IFS= read -r파이프 패턴만 사용(아래 검사는 출력 전용이라 서브셸 무관).
아래 예시는 스캔 범위를 SCAN으로 둔다. 프로젝트 구조에 맞게 조정한다:
SCAN="CLAUDE.md $(ls .claude/agents/*.md 2>/dev/null) $(ls .claude/skills/*/SKILL.md 2>/dev/null) $(ls docs/**/*.md 2>/dev/null)"스캔 절차
1. 정의 없는 에이전트 참조
existing=$(ls .claude/agents/*.md 2>/dev/null | xargs -n1 basename | sed 's/\.md//')
grep -hoE '`[a-z][a-z0-9-]+`' $SCAN 2>/dev/null \
| tr -d '`' | sort -u \
| grep -E '(-dev|-writer|-reviewer|debugger|architect|refactor|reviewer|validator|designer|tester)$' \
| while read r; do echo "$existing" | grep -qx "$r" || echo "❌ 정의없음: $r"; done오탐: 하위 디렉터리(모노레포 패키지)의
<pkg>/.claude/agents/에 정의된 에이전트는 루트에 없어도 정상.
2. 정의 없는 스킬 참조
skills=$(ls -d .claude/skills/*/ 2>/dev/null | xargs -n1 basename)
grep -hoE '/[a-z][a-z0-9-]+|`[a-z][a-z0-9-]+`' $SCAN 2>/dev/null \
| tr -d '`/' | sort -u \
| while read s; do [ -d ".claude/skills/$s" ] || echo "$s"; done위는 후보가 많다(일반 단어 포함). 슬래시 커맨드로 참조된 것(
/skill-name) 위주로 좁혀 판단. 전역/플러그인 스킬은 오탐.
3. 존재하지 않는 경로 참조
grep -hoE '\.claude/[A-Za-z0-9_./-]+' $SCAN 2>/dev/null \
| grep -vE '<|\*' | sort -u | while read p; do [ -e "$p" ] || echo "❌ MISSING: $p"; done
grep -hoE 'docs/[A-Za-z0-9_./-]+\.md' $SCAN 2>/dev/null \
| sort -u | while read p; do [ -f "$p" ] || echo "❌ MISSING: $p"; done오탐:
~/.claude/...(글로벌,~탈락), 프로젝트별 상대경로(모노레포 하위 패키지 기준)는 루트에 없어도 정상.
4. 고아 에이전트 (정의됐으나 참조처 없음)
ls .claude/agents/*.md 2>/dev/null | xargs -n1 basename | sed 's/\.md//' | while IFS= read -r a; do
cnt=$(grep -rl "$a" $SCAN 2>/dev/null | grep -v "agents/$a.md" | wc -l)
[ "$cnt" -eq 0 ] && echo "⚠️ 고아: $a"
done고아 ≠ 즉시 삭제. 직접 호출용일 수 있으니 의도 확인 후 판단.
5. 폐기 항목 잔존 확인 (인자 = 폐기한 이름들)
echo "$ARGS" | tr ' ' '\n' | while IFS= read -r name; do
[ -z "$name" ] && continue
echo "=== $name ==="
grep -rn "$name" $SCAN 2>/dev/null || echo "0 ✓"
done리포트 형식
[하네스 감사 결과]
- 정의 없는 에이전트/스킬 참조: <목록 또는 0>
- 끊긴 경로: <목록 또는 0>
- 고아 에이전트: <목록 또는 0>
- 오탐 제외 실제 조치 필요: <N건>
권장 조치: <파일:줄 → 수정안>Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

