Harness Audit logo

Harness Audit

Community
jh941213
harness-audit

하네스(hooks, skills, agents, rules) 전체 건강도를 진단하고 점수 산출. 대상: ~/.claude 전역 하네스 (프로젝트 진단은 harness-diagnostics). Triggers on: harness audit, 하네스 진단, 설정 점검, 하네스 점검. NOT for: 코드 작성, 구현.

Overview

Publisherjh941213
Repositorymy-cc-harness
Skill nameharness-audit
Stars
125
Forks
35
Bundled files
Instructions only
Links
Skill sourceRepository
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • Self-contained

    Everything the model needs lives in the instructions — no extra files to sync.

  • Open source

    Published by jh941213 on GitHub. Read the source before you install it.

Installation

Install the Harness Audit AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/jh941213/my-cc-harness.git /tmp/my-cc-harness
mkdir -p .claude/skills
cp -r /tmp/my-cc-harness/skills/harness-audit .claude/skills/harness-audit
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Harness Audit in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Harness Audit on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Harness Audit is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

하네스 건강도 진단

Claude Code 하네스 설정의 전체 건강도를 8개 차원으로 진단합니다.

8개 진단 차원

1. CLAUDE.md 품질 (0-3)

  • 0: 없음
  • 1: 존재하지만 기본만
  • 2: 프로젝트 컨텍스트 + 규칙 포함
  • 3: 상세한 아키텍처 + 패턴 + 안티패턴

2. Skills 커버리지 (0-3)

  • 0: 스킬 없음
  • 1: 1-5개
  • 2: 6-15개 + 트리거/안티트리거 정의
  • 3: 16개+ + 도메인별 분류 + eval 스킬 포함

검사 대상은 고정 스킬 목록이 아니라 skills/ 디렉토리 실물 목록 기준 전수 스캔.

3. Agents 아키텍처 (0-3)

  • 0: 에이전트 없음
  • 1: 1-3개 (기본)
  • 2: 4-8개 + 역할 분리 명확
  • 3: 9개+ + evaluator 분리 + 역할 경계 매트릭스

4. Hooks 자동화 (0-3)

  • 0: 훅 없음
  • 1: 기본 (prettier, lint)
  • 2: 품질 게이트 + 보안 스캔
  • 3: 전체 파이프라인 (coverage + security + e2e + eval)

5. Rules 구조화 (0-3)

  • 0: 규칙 없음
  • 1: 1-2개 일반 규칙
  • 2: 파일 패턴별 규칙 (*.ts, *.py 등)
  • 3: 도메인별 + 보안 + 성능 + 테스트 규칙

6. MCP 서버 (0-3)

  • 0: MCP 없음
  • 1: 1-2개 기본
  • 2: 검색 + 문서 + UI 도구
  • 3: 검색 + 문서 + 코드 분석(code-review-graph 등)

7. Eval 파이프라인 (0-3)

  • 0: eval 없음
  • 1: 수동 verify만
  • 2: 자동 품질 게이트 + 스코어링
  • 3: 독립 evaluator + pass@k + AI 슬롭 감지

8. 팀/멀티에이전트 (0-3)

  • 0: 단독 사용
  • 1: 기본 서브에이전트
  • 2: 역할 기반 팀 + 커뮤니케이션 프로토콜
  • 3: TTH급 사일로 + Ralph Loop + backpressure

실행 프로세스

  1. ~/.claude/ 디렉토리 전체 스캔
  2. 각 차원별 점수 산출 (0-3)
  3. 총점 (0-24) + 등급 산출

등급

총점등급설명
21-24S프로덕션 레벨 하네스
16-20A고급 설정. 소수 항목 개선 필요
11-15B중급. 핵심 갭 존재
6-10C기초. 대부분 수동
0-5D미설정. 바닐라 상태

출력 형식

📊 하네스 건강도: [등급] ([N]/24)

| 차원 | 점수 | 상태 |
|------|------|------|
| CLAUDE.md | [N]/3 | [🟢/🟡/🔴] |
| Skills | [N]/3 | ... |
| Agents | [N]/3 | ... |
| Hooks | [N]/3 | ... |
| Rules | [N]/3 | ... |
| MCP | [N]/3 | ... |
| Eval | [N]/3 | ... |
| Team | [N]/3 | ... |

🔧 개선 제안:
1. [가장 낮은 점수 차원 개선 방안]
2. ...

컨텍스트 파일 프루닝 (분기 루틴)

CLAUDE.md는 지식 저장소가 아니라 편향 교정 프롬프트다 — 밀도가 품질이다. 분기마다 각 줄을 세 가지로 분류한다:

분류기준처분
A에이전트가 파일 탐색으로 스스로 알아낼 수 있는 정보 (구조·패키지·스타일)삭제 후보 — 근거를 한 줄씩 제시
B지시가 없으면 기본 동작이 반대로 가는 항목 (삭제·조사·단순화·의존성 확인)유지
C팀마다 답이 갈리는 선택 (하위 호환·테스트 강도·로깅 수준)유지하되 최신인지 사용자에게 질문

추가 점검:

  • tasks/lessons.md에서 같은 유형의 수정이 3회 이상 반복된 패턴 → CLAUDE.md 한 줄 승격 후보로 보고
  • 모델 세대가 바뀌어 더 이상 발동하지 않는 줄(교정 대상 성향이 사라진 것) → 삭제 후보
  • 분류 결과를 표로 출력하고, 삭제는 사용자 승인 후 실행

Frequently asked questions

What does the Harness Audit AI skill do?

하네스(hooks, skills, agents, rules) 전체 건강도를 진단하고 점수 산출. 대상: ~/.claude 전역 하네스 (프로젝트 진단은 harness-diagnostics). Triggers on: harness audit, 하네스 진단, 설정 점검, 하네스 점검. NOT for: 코드 작성, 구현.

Why use Harness Audit on TypingMind?

Because you install it once and use it with any model. Harness Audit is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Harness Audit in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/jh941213/my-cc-harness/tree/main/skills/harness-audit. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Harness Audit?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Harness Audit?

As many as you like. As long as a model supports skills, you can use Harness Audit with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Harness Audit AI skill free?

It is published on GitHub by jh941213. Check the repository for licensing terms. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

Related AI Skills

View all
thedotmack logo

Cloud Sync

thedotmack
CommunityPopular

Set up or check claude-mem cloud sync with cmem.ai Pro. Use when the user says "set up cloud sync", "sync my memories", "cmem pro", "cloud backup", "sync status", or wants their memory database backed…

8.3K
94.1K
Instructions
View
thedotmack logo

Version Bump

thedotmack
CommunityPopular

Automated semantic versioning and release workflow for Claude Code plugins. Handles version increments across package.json, marketplace.json, plugin.json manifests, build verification, git tagging,…

8.3K
94.1K
1 files
View
bytedance logo

Skill Reviewer

bytedance
OrganizationPopular

Reviews DeerFlow skill packages for readiness, triggers, safety boundaries, resources, and evidence. Invoke when users ask to audit, grade, or production-check an existing skill.

11.4K
82.6K
6 files
View
ComposioHQ logo

Ahrefs Automation

ComposioHQ
OrganizationPopular

Automate SEO research with Ahrefs -- analyze backlink profiles, research keywords, track domain metrics history, audit organic rankings, and perform batch URL analysis through the Composio Ahrefs…

8.7K
75.2K
Instructions
View

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇