Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add jh941213/codex-lattice --skill harness-auditgit clone --depth 1 https://github.com/jh941213/codex-latticeWrote 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/jh941213/codex-lattice/harness-audit)<a href="https://agentmods.dev/skills/jh941213/codex-lattice/harness-audit"><img src="https://agentmods.dev/badge/skills/jh941213/codex-lattice/harness-audit/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/jh941213/codex-lattice/harness-audit"><img src="https://agentmods.dev/badge/skills/jh941213/codex-lattice/harness-audit.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 | $0.00059 | $0.00967 |
| Opus 5 | $0.00030 | $0.00483 |
| Sonnet 5 | $0.00012 | $0.00193 |
| Haiku 4.5 | $0.00006 | $0.00097 |
Grade A, and why
harness-audit 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 9d 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
하네스 건강도 진단
Codex 하네스 설정의 전체 건강도를 8개 차원으로 진단합니다.
8개 진단 차원
1. AGENTS.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
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: Codex /goal + custom agents + backpressure
실행 프로세스
- 프로젝트 루트와
~/.codex/디렉토리 전체 스캔 - 각 차원별 점수 산출 (0-3)
- 총점 (0-24) + 등급 산출
등급
| 총점 | 등급 | 설명 |
|---|---|---|
| 21-24 | S | 프로덕션 레벨 하네스 |
| 16-20 | A | 고급 설정. 소수 항목 개선 필요 |
| 11-15 | B | 중급. 핵심 갭 존재 |
| 6-10 | C | 기초. 대부분 수동 |
| 0-5 | D | 미설정. 바닐라 상태 |
출력 형식
📊 하네스 건강도: [등급] ([N]/24)
| 차원 | 점수 | 상태 |
|------|------|------|
| AGENTS.md | [N]/3 | [상/중/하] |
| 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. ...
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.
- 9d ago First seen · 97 lines · 59 tokens per session scan A 3c80eb4332d2
harness-audit is a skill published in the GitHub repository jh941213/codex-lattice (19 stars, last pushed 3mo ago), licensed MIT. It adds 59 tokens to every session and 967 once invoked, about $0.0003 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
debug-optimize-lcp
Guides debugging and optimizing Largest Contentful Paint (LCP) using Chrome DevTools MCP tools. Use this skill whenever the user asks about LCP performance, slow page loads, Core Web Vitals optimization, or wants to understand why their page's main content takes too long to appear. Also use when the user mentions…
systematic-debugging
Use when debugging a failing test, build error, or runtime issue that isn't immediately obvious. Guides a 4-phase root cause analysis instead of random fix attempts.
diagnose
Trace from a reproduced symptom to the source code that causes it. Pin the specific file and approximate line, rate confidence in the cause and clarity of the fix independently, and always propose a concrete fix.
repro-admin
Reproduce an EmDash admin UI bug. Attach a container, start the demo dev server, drive the admin with agent-browser using the dev-bypass session, and capture the reproduction as screenshots plus a replayable transcript.
log-error-digest
Analyze log files to troubleshoot errors, identify peak error periods, and produce error clustering, frequency statistics, and time distribution reports. Supports JSON, syslog, and Nginx formats with automatic detection. Use when a user uploads a .log file and asks to analyze errors, find patterns, debug issues, or…
byted-util-volcengine-detect-retry
An orchestration workflow for Volcengine Cloud Detect, a service that checks websites or network endpoints from test locations.