agentmods.dev

ops-audit

ops-audit is a command for Claude Code from leee880619-commits/ClaudeCode-Harness-Setup-Assistant. It costs 70 tokens per session (1,677 once invoked), scanned A, original, Apache-2.0.

A command that reviews an existing Claude Code harness, meaning the files and workflows that support an agent, for problems during real operation.

In plain words
What is it for?
Use it to audit session continuity, retry termination, failure recovery, artifact overwriting, and duplication across workflows.
Why use it?
It helps reveal runtime assumptions, recovery gaps, duplicated maintenance, unsafe overwrites, and other operational debt after the harness has been built.

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

not rated 2repo 2mo ago A scan 70 tokens original Apache-2.0

Good fit Use it to audit session continuity, retry termination, failure recovery, artifact overwriting, and duplication across workflows.

Compare 6 commands from other repositories ↓
View source ↗ leee880619-commits/ClaudeCode-Harness-Setup-Assistant
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 ops-audit

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

Your own site · 80×15
<a href="https://agentmods.dev/commands/leee880619-commits/claudecode-harness-setup-assistant/ops-audit"><img src="https://agentmods.dev/badge/commands/leee880619-commits/claudecode-harness-setup-assistant/ops-audit.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 70 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,677 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. 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 $0.00070 $0.01677
Opus 5 $0.00035 $0.00839
Sonnet 5 $0.00014 $0.00335
Haiku 4.5 $0.00007 $0.00168

Measured 9d ago against content hash aaa354b3a52b, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

ops-audit scanned grade A with 1 finding 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.

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/ops-audit.md · 99 lines

How it starts

The opening of the file, as written. The whole thing — 99 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Harness Ops Audit

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

기존 Claude Code 하네스의 런타임 가정·운영 부채·실패 복구 미비를 분석합니다. /harness-architect:harness-setup Phase 9가 "구조가 올바른가"를 검증하는 정적 구조 린터라면, 이 커맨드는 "실제 실행할 때 어디서 문제가 생기는가"에 집중한 사후 감사입니다.

범위 비교

측면 Phase 9 final-validation ops-audit
실행 시점 신규 harness-setup 플로우 내부 (빌드 중) 기존 하네스에 독립 실행 (빌드 후, 언제든)
주 관심사 파일 존재·스키마 준수·보안 런타임 가정·운영 부채
대상 프로젝트 harness-architect가 방금 생성한 하네스 과거에 생성된 하네스 (타 도구 생성 하네스 포함)
출력 등급 BLOCK/ASK/NOTE RISK-HIGH/RISK-MED/RISK-LOW

중복 항목(W4 절대 경로, W7 크로스 구조 중복)은 두 곳 모두에서 검사하되, 판정 충돌 시 ops-audit가 더 최신 상태이므로 우선합니다. (playbooks/final-validation.md #15·#16에 SSoT 주석 명시)

관련 커맨드 (See also)

커맨드 역할 실행 시점 출력 등급
/harness-architect:harness-setup 신규 하네스 구축 (9-Phase) 빌드 BLOCK/ASK/NOTE
/harness-architect:harness-audit 구성 진단 (파일·권한·anti-pattern·에이전트-플레이북 매핑) 기존 하네스 CRITICAL/HIGH/MEDIUM/LOW
/harness-architect:ops-audit (본 커맨드) 런타임 감사 (세션 연속성·실패 복구·덮어쓰기·중복) 기존 하네스 RISK-HIGH/MED/LOW

harness-audit와 ops-audit의 관계: 두 커맨드는 상호 보완적이다. harness-audit은 설계·구성 중심, ops-audit은 런타임·운영 중심. 사용자는 기존 하네스 점검 시 harness-audit → ops-audit 순서로 실행 권장 — 구성 문제를 먼저 해소한 후 운영 부채를 감사해야 RISK 판정의 정확도가 높아진다.

등급 체계 매핑 (RISK ↔ BLOCK)

RISK 등급은 red-team-advisor의 BLOCK/ASK/NOTE와 직접 대응되지 않는다. 의도된 차이:

  • RISK-HIGH ≈ 시급 권장 (프로덕션 운영 시 실패·데이터 손실 가능) — 진행 중단은 아님. 이미 배포된 하네스를 BLOCK으로 멈출 수 없기 때문.
  • RISK-MED ≈ 개선 권장 (운영 고통 누적)
  • RISK-LOW ≈ 정보성 / 선택적 개선
  • red-team-advisor BLOCK ≈ Phase 진행을 막는 게이팅 역할 — 빌드 중에만 의미 있음. ops-audit은 사후 감사이므로 이에 대응하는 등급이 없음.

사용자는 두 보고서를 동시에 받을 때 "RISK-HIGH = 즉시 수정, BLOCK = 진행 불가"로 이해하면 된다.

Pre-flight Gate — harness 존재 여부 검증

커맨드 진입 즉시 대상 프로젝트의 하네스 설치 여부를 확인합니다:

  1. $ARGUMENTS 또는 AskUserQuestion으로 대상 프로젝트 절대 경로 수집
  2. 다음 중 하나라도 존재하면 정상 감사 진행:
    • {대상}/CLAUDE.md
    • {대상}/.claude/settings.json
    • {대상}/.claude/agents/ (파일 1개 이상)
    • {대상}/playbooks/ (파일 1개 이상)
  3. 모두 미존재 시 AskUserQuestion으로 분기:
    • 부분 감사 계속 — .gitignore·README 등 파일만으로 최소 감사 수행 (출력에 "harness 미설치 — 부분 감사" 명시)
    • 먼저 harness-setup 실행 — /harness-architect:harness-setup 안내 후 종료
    • 취소 — 종료

Read the full file on GitHub · 99 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. 9d ago First seen · 99 lines · 70 tokens per session scan A aaa354b3a52b

Subscribe to this mod's changes

ops-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 70 tokens to every session and 1,677 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Building agentsClaude CodeDebuggingagent-teamharnessmeta-toolorchestratorplugin
Related

Other commands, from other repositories

ai-incident

Registrar y analizar incidentes donde recomendaciones de Savia fueron incorrectas.

gonzalezpazmonica/savia · 17 tokens

arch-health

Salud arquitectónica — fitness functions, drift detection, coupling metrics.

gonzalezpazmonica/savia · 16 tokens

get-flow-run

Inspect a Postman Flow run by its Run ID — per-block logs, failing block, and status.

Postman-Devrel/postman-claude-code-plugin · 20 tokens

t800-fix

A command for making a narrow, predefined fix to existing agents, skills, commands, rules, or hooks. A fix-pack is a file listing the exact changes to make.

Khar-AG/t-800-agent · 0 tokens

debug

Systematic root-cause investigation, then fix with TDD — never proposes a fix before finding the cause; resumable diagnosis + regression test in .orc/ state. Workspace-aware. For a quick one-off look without session state, prefer the bundled /debug.

HigorAlves/orc · 53 tokens

t800-doctor

A command that runs a scripts-only health report for a T-800 or target plugin setup. It reports the version, profile, memory location, state, item counts, always-applied items, and recent audits.

Khar-AG/t-800-agent · 0 tokens