harness-audit

harness-audit is a command for Claude Code from leee880619-commits/ClaudeCode-Harness-Setup-Assistant. It costs 99 tokens per session (1,619 once invoked), scanned A, original, Apache-2.0.

A diagnostic command for checking whether an existing Claude Code harness has a sound configuration. A harness is the project setup that controls agent instructions, permissions, files, and supporting workflows.

In plain words
What is it for?
Use it to inspect file structure, JSON validity, permission safety, common configuration mistakes, and links between agents and playbooks. It is intended as a standalone configuration audit.
Why use it?
It finds configuration problems that can make the agent unsafe, inconsistent, or unable to follow its mapped workflows. It checks the harness itself and reports issues without changing it.

Command for Claude Code

Written for Claude Code: ${CLAUDE_PLUGIN_ROOT} variable. Also seen: mentions CLAUDE.md; names the AskUserQuestion tool; mentions Claude Code.

Runs only inside its plugin — its command needs a path that Claude Code sets for a plugin’s own hooks and for nothing else. Install the plugin, not this.

Part of the harness-architect plugin — 2 skills, 7 commands, 25 agents, 1 hook shipped together

Good fit Use it to inspect file structure, JSON validity, permission safety, common configuration mistakes, and links between agents and playbooks. It is intended as a standalone configuration audit.

Compare 6 commands from other repositories ↓
Install

Getting it into your agent

This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.

Claude Code
/plugin marketplace add leee880619-commits/ClaudeCode-Harness-Setup-Assistant
Claude Code
/plugin install harness-architect

Made for: Claude Code.

Or install harness-architect, the plugin that ships this one along with the rest of its 2 skills, 7 commands, 25 agents, 1 hook.

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 harness-audit

README.md
[![agentmods](https://agentmods.dev/badge/commands/leee880619-commits/claudecode-harness-setup-assistant/harness-audit/github.svg)](https://agentmods.dev/commands/leee880619-commits/claudecode-harness-setup-assistant/harness-audit)
Your own site
<a href="https://agentmods.dev/commands/leee880619-commits/claudecode-harness-setup-assistant/harness-audit"><img src="https://agentmods.dev/badge/commands/leee880619-commits/claudecode-harness-setup-assistant/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.

agentmods 80×15 button for harness-audit

Your own site · 80×15
<a href="https://agentmods.dev/commands/leee880619-commits/claudecode-harness-setup-assistant/harness-audit"><img src="https://agentmods.dev/badge/commands/leee880619-commits/claudecode-harness-setup-assistant/harness-audit.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 99 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,619 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 2 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 $0.00099 $0.01619
Opus 5 $0.00049 $0.00809
Sonnet 5 $0.00020 $0.00324
Haiku 4.5 $0.00010 $0.00162

Measured 10d ago against content hash 557b9a4c6a29, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

harness-audit scanned grade A with 2 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 10d 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.

Asks for rootlowPrivilege escalation

A mod that escalates privileges can change anything on the machine, not only the project.

- `CRITICAL` ≈ **보안 침해 직결 + 즉시 수정** — `Bash(*)` / `Bash(sudo *)` allow, 필수 deny 부재, 비밀값 노출

Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.

Reads agent configuration directorieslowAgent snooping

.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.

- `{대상}/.claude/settings.json`

Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.

commands/harness-audit.md · 93 lines

How it starts

The opening of the file, as written. The whole thing — 93 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Harness Configuration Audit

💡 대부분의 경우 /harness-architect:audit 통합 커맨드 사용을 권장합니다. 본 커맨드는 구성 정합성만 단독으로 보고 싶은 고급 사용자용입니다. /harness-architect:audit 은 이 커맨드 + ops-audit + fit-audit 을 병렬 실행해 단일 통합 보고서를 제공합니다.

이미 배포된 Claude Code 하네스의 구성 정합성 을 진단합니다. 파일 구조·JSON 유효성·권한 안전성·anti-pattern·에이전트↔플레이북 매핑을 4-scope 전수 스캔합니다.

범위 비교

측면 harness-audit (본 커맨드) ops-audit fit-audit
근본 질문 "파일 구조가 올바른가" "실행할 때 실패하는가" "이 프로젝트에 여전히 맞는가"
데이터 소스 하네스 파일만 하네스 파일만 하네스 파일 + 프로젝트 스캔
출력 등급 CRITICAL/HIGH/MEDIUM/LOW RISK-HIGH/MED/LOW MAJOR-DRIFT-CRITICAL/MAJOR-DRIFT-MED/MINOR-DRIFT/ALIGN
주 관심사 구성 정합성 — anti-pattern, JSON, 매핑, 권한 런타임 부채 — 세션 복구·retry 상한·덮어쓰기 프로젝트 적합성 — 드리프트

세 감사는 독립이며 상호 보완입니다. 통합 실행은 /harness-architect:audit 한 번이면 병렬 감사 + 단일 통합 보고서를 제공합니다. 개별 실행 시 권장 순서: harness-auditops-auditfit-audit.

등급 체계

  • CRITICAL보안 침해 직결 + 즉시 수정Bash(*) / Bash(sudo *) allow, 필수 deny 부재, 비밀값 노출
  • HIGH구조·권한 손상 — 조속 수정 — CLAUDE.md 200줄 초과, settings.json 파싱 실패, dangerous allow 패턴, playbook 참조 불일치, D-1 가시성 위반
  • MEDIUM운영 품질 저하 — 개선 권장 — settings.local.json 비대, .gitignore 누락, path 패턴 mismatch, mixed location without hybrid intent
  • LOW정보성 / 선택적 개선 — rules/ 디렉터리 부재, Ask-first directive 부재 등

Pre-flight Gate — 하네스 존재 여부 검증

커맨드 진입 시 사용자에게 먼저 안내 (AskUserQuestion 없이 텍스트로 출력):

⚠️ 이 커맨드는 구성 정합성만 진단합니다 (4-scope·JSON·anti-pattern·권한·매핑). 런타임 부채(ops-audit) 와 프로젝트 적합성(fit-audit) 은 포함되지 않습니다. 3개 축을 통합으로 받으려면 /harness-architect:audit 을 사용하세요.

이 커맨드는 진단 전용입니다. 발견된 구성 문제를 harness-audit 자체가 수정하지 않습니다. 개선은 /harness-architect:harness-setup 재실행 또는 사용자가 직접 .claude/ 편집으로 수행합니다.

이후 다음을 확인합니다:

  1. $ARGUMENTS 또는 AskUserQuestion 으로 대상 프로젝트 절대 경로 수집. 경로 유효성 검증 (test -d).
  2. 하네스 최소 존재 검증: 다음 중 하나라도 존재해야 감사 진행:
    • {대상}/CLAUDE.md
    • {대상}/.claude/settings.json
    • {대상}/.claude/agents/ (파일 1개 이상)
    • {대상}/playbooks/ (파일 1개 이상)
  3. 모두 미존재 시 AskUserQuestion 분기:
    • 먼저 harness-setup 실행/harness-architect:harness-setup 안내 후 종료
    • 취소 — 종료

Read the full file on GitHub · 93 lines

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. 10d ago First seen · 93 lines · 99 tokens per session scan A 557b9a4c6a29

Subscribe to this mod's changes

harness-audit is a command published in the GitHub repository leee880619-commits/ClaudeCode-Harness-Setup-Assistant (2 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 99 tokens to every session and 1,619 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it A with 2 findings (asks for root, reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.