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.
/plugin marketplace add leee880619-commits/ClaudeCode-Harness-Setup-Assistant/plugin install harness-architectWrote 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/commands/leee880619-commits/claudecode-harness-setup-assistant/harness-audit)<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.
<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>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 | $0.00099 | $0.01619 |
| Opus 5 | $0.00049 | $0.00809 |
| Sonnet 5 | $0.00020 | $0.00324 |
| Haiku 4.5 | $0.00010 | $0.00162 |
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.
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:audit통합 커맨드 사용을 권장합니다. 본 커맨드는 구성 정합성만 단독으로 보고 싶은 고급 사용자용입니다./harness-architect:audit은 이 커맨드 +ops-audit+fit-audit을 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-audit → ops-audit → fit-audit.
등급 체계
CRITICAL≈ 보안 침해 직결 + 즉시 수정 —Bash(*)/Bash(sudo *)allow, 필수 deny 부재, 비밀값 노출HIGH≈ 구조·권한 손상 — 조속 수정 — CLAUDE.md 200줄 초과, settings.json 파싱 실패, dangerous allow 패턴, playbook 참조 불일치, D-1 가시성 위반MEDIUM≈ 운영 품질 저하 — 개선 권장 — settings.local.json 비대, .gitignore 누락, path 패턴 mismatch, mixed location without hybrid intentLOW≈ 정보성 / 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:audit을 사용하세요.
이 커맨드는 진단 전용입니다. 발견된 구성 문제를 harness-audit 자체가 수정하지 않습니다. 개선은
/harness-architect:harness-setup재실행 또는 사용자가 직접.claude/편집으로 수행합니다.
이후 다음을 확인합니다:
$ARGUMENTS또는 AskUserQuestion 으로 대상 프로젝트 절대 경로 수집. 경로 유효성 검증 (test -d).- 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)
- 모두 미존재 시 AskUserQuestion 분기:
먼저 harness-setup 실행—/harness-architect:harness-setup안내 후 종료취소— 종료
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.
- 10d ago First seen · 93 lines · 99 tokens per session scan A 557b9a4c6a29
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.
Other commands, from other repositories
send
Send a message to a running agent session. Use this to correct or direct a live agent mid-stream without killing and respawning it.
discover
Search the Everruns(Dev) API catalog for available operations.
me-figure-discussion
Write or review thermal-fluid figure discussion with observation, physical mechanism, comparison, uncertainty, and claim limits.
agent-wizard
Build a Claude Agent SDK agent by answering 9 illustrated questions, then run it.
cleanup
Run a systematic cleanup on the provided code to resolve smells, simplify complexity, and enforce best practices.
pn-audit-api
Surgical API design review — REST conventions, status codes, response shapes, validation, and schema leaks. Use standalone or as part of pn-backend-audit. Outputs a scored fix roadmap.