audit-harness-deps

audit-harness-deps is a skill for Claude Code from clomia/claude-automata. It costs 71 tokens per session (825 once invoked), scanned A, original, Apache-2.0.

A full-cycle guide for checking whether agent hooks, plugins, and other integrations still match the current observed behavior of Claude Code. It focuses on undocumented dependencies, evidence from recent local records, fixes, tests, documentation, and deployment.

In plain words
What is it for?
Use it to audit unofficial integrations, compare them with current documentation and machine records, investigate degraded behavior, and correct and deploy verified fixes.
Why use it?
It helps find silent compatibility drift, including cases where a fallback still works but quietly reduces quality.

Skill for Claude Code

Written for Claude Code: installed under .claude/. Also seen: names the AskUserQuestion tool.

Good fit Use it to audit unofficial integrations, compare them with current documentation and machine records, investigate degraded behavior, and correct and deploy verified fixes.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/clomia/claude-automata/audit-harness-deps
Install

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.

Any agent
npx skills add clomia/claude-automata --skill audit-harness-deps
Clone the repo
git clone --depth 1 https://github.com/clomia/claude-automata

Made for: Claude Code.

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 audit-harness-deps

README.md
[![agentmods](https://agentmods.dev/badge/skills/clomia/claude-automata/audit-harness-deps/github.svg)](https://agentmods.dev/skills/clomia/claude-automata/audit-harness-deps)
Your own site
<a href="https://agentmods.dev/skills/clomia/claude-automata/audit-harness-deps"><img src="https://agentmods.dev/badge/skills/clomia/claude-automata/audit-harness-deps/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 audit-harness-deps

Your own site · 80×15
<a href="https://agentmods.dev/skills/clomia/claude-automata/audit-harness-deps"><img src="https://agentmods.dev/badge/skills/clomia/claude-automata/audit-harness-deps.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 71 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 825 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 $0.00071 $0.00825
Opus 5 $0.00036 $0.00413
Sonnet 5 $0.00014 $0.00165
Haiku 4.5 $0.00007 $0.00082

Measured 12d ago against content hash 69744fceba57, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

audit-harness-deps 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 12d 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/skills/audit-harness-deps/SKILL.md · 42 lines

What it actually says

이 코드베이스의 훅·플러그인들은 일부 지점에서 클로드 코드의 공식 레퍼런스가 없는 관측 기반 동작(트랜스크립트 내부 형식, 미문서 훅 거동, 권한 분류기 동작, UI 표면 등)에 의존한다. 클로드 코드가 업데이트되면 이 의존들은 소리 없이 표류한다 — 완전한 고장보다, graceful degrade가 조용히 상시 발동 중인 상태가 가장 놓치기 쉽다. 이 스킬은 그 표류를 실측으로 잡아내고 해소하는 full cycle이다.

목표

모든 비공식 의존이 지금 이 머신에 설치된 클로드 코드가 실제로 내보내는 형식·동작과 일치함을 증거로 실증한 상태. 표류가 발견되면 수정하고 배포까지 마친 상태. 문제가 없으면 무변경 — 검사 결과 보고만 남긴다.

요구사항

  • 전수 식별. 전체 코드베이스에서 공식 레퍼런스가 없는 의존을 정교하게 모두 찾아라. 공식/비공식의 판별 근거는 기억이 아니라 현행 공식 문서다 — 문서 자체도 버전마다 변한다. ARCHITECTURE의 기술 리스크·설계 결정 기록은 알려진 의존의 출발점일 뿐, 전수 목록으로 믿지 마라. 숨은 의존은 항상 있었다 (실례: command_args의 문서-실측 불일치는 목록 밖 전수 감사에서야 발견됐다).
  • 최신 실측 대조. 이 머신에 남아 있는 클로드 코드의 실기록(트랜스크립트, 상태 파일 등)에서 가장 최신의 증거를 찾아 각 의존 로직을 대입 검증하라. 최신 기록일수록 증거력이 높다 — 오래된 기록과의 일치는 현재 버전의 무결성을 보장하지 않는다.
  • degrade도 결함이다. 고장만이 아니라, 형식 표류로 graceful degrade가 실제 발동 중인 상태(조용한 품질 저하)를 찾아내는 것이 이 스킬의 존재 이유다.
  • 기계 검증이 불가능한 표면은 사용자에게 물어라. UI 표시(systemMessage 등)처럼 기록에 남지 않는 표면은 AskUserQuestion으로 간단히 검증한다 — 예: "최근 세션 시작 시 UI에서 이런 메시지를 본 적이 있는가?"
  • 발견 시 해결과 배포까지. 수정은 기존 설계 원칙을 유지하라: 실패 방향은 언제나 기능 저하(오늘의 동작)여야 하고 정지·오종료여선 안 되며, 비공식 의존을 새로 늘리지 마라. 수정에는 문서 정합, 테스트, 레포 규칙에 따른 버전 일관 업데이트, push 배포까지가 한 사이클로 포함된다.

유의사항

  • 모든 판정에 증거를 남겨라: "성립"은 실측 인용(레코드·파일)으로, "공식"은 문서 인용으로.
  • 최종 보고는 의존 전수 목록 + 판정 + 증거 + 조치다.
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. 12d ago First seen · 42 lines · 71 tokens per session scan A 69744fceba57

Subscribe to this mod's changes

audit-harness-deps is a skill published in the GitHub repository clomia/claude-automata (13 stars, last pushed 9d ago), licensed Apache-2.0. It adds 71 tokens to every session and 825 once invoked, about $0.0004 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 skills, from other repositories

release-it

Build production-ready systems with stability patterns: circuit breakers, bulkheads, timeouts, and retry logic. Use when the user mentions "production outage", "circuit breaker", "deployment pipeline", "chaos engineering", "retry storm", "health checks", "my service keeps crashing", "prevent cascading failures", or…

wondelai/skills · 131 tokens

tidewave-integration

Tidewave MCP runtime tools — debugging, smoke testing, live state inspection, SQL queries, hex docs. Use when evaluating code in a running Phoenix app.

oliver-kriska/claude-elixir-phoenix · 38 tokens

debug

Interactive debugging workflow with hypothesis-driven probe loop. Use when: unknown bugs, script errors, silent failures, troubleshooting. Not for: known bugs (use bug-fix), GitHub issue analysis (use issue-analyze), code understanding (use code-explore). Output: debug report with probe journal + root cause + fix.

sd0xdev/sd0x-harness · 67 tokens

resolving-merge-conflicts

Use when a git merge or rebase reports conflicts and the operation is in progress.

romiluz13/cc10x · 25 tokens

git-investigate

Git history investigation. Use when: tracking code changes, finding where bugs were introduced, root cause analysis. Not for: code exploration (use code-explore), issue analysis (use issue-analyze). Output: history trace + root cause report.

sd0xdev/sd0x-harness · 53 tokens

analyze

Deep-dive codebase analysis that explains how things actually work — business rules, architecture patterns, auth flows, data models, integrations, and performance hotspots. Use whenever the user asks "how does X work", "map the Y flow", "what are the business rules for Z", "trace the auth path", "explore the codebase…

rsmdt/the-startup · 118 tokens