agentmods.dev

fit-audit

fit-audit is a command for Claude Code from leee880619-commits/ClaudeCode-Harness-Setup-Assistant. It costs 120 tokens per session (1,933 once invoked), scanned A, original, Apache-2.0.

A read-only check of whether an existing Claude Code harness still matches the project it supports. It compares the harness with the project's current structure, complexity, permissions, instructions, and external connections.

In plain words
What is it for?
Use it to inspect whether the harness's assumptions are still valid, including its agent setup, permission paths, project instructions, MCP servers, and hooks.
Why use it?
Projects change, so a harness can gradually stop matching them. This check finds that drift without changing anything.

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 120 tokens original Apache-2.0

Good fit Use it to inspect whether the harness's assumptions are still valid, including its agent setup, permission paths, project instructions, MCP servers, and hooks.

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 fit-audit

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

Your own site · 80×15
<a href="https://agentmods.dev/commands/leee880619-commits/claudecode-harness-setup-assistant/fit-audit"><img src="https://agentmods.dev/badge/commands/leee880619-commits/claudecode-harness-setup-assistant/fit-audit.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 120 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,933 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 $0.00120 $0.01933
Opus 5 $0.00060 $0.00966
Sonnet 5 $0.00024 $0.00387
Haiku 4.5 $0.00012 $0.00193

Measured 10d ago against content hash 577ef0697a5c, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

fit-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 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.

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/fit-audit.md · 100 lines

How it starts

The opening of the file, as written. The whole thing — 100 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Harness Fit Audit

💡 대부분의 경우 /harness-architect:audit 통합 커맨드 사용을 권장합니다. 본 커맨드는 프로젝트 적합성(드리프트) 만 단독으로 보고 싶은 고급 사용자용입니다. /harness-architect:audit 은 harness-audit + ops-audit + 본 커맨드를 병렬 실행해 단일 통합 보고서를 제공합니다.

이미 배포된 하네스가 현재 대상 프로젝트의 특성·복잡도·도메인에 여전히 적합한지 감사합니다. /harness-architect:ops-audit 가 "하네스 자체가 운영 건전한가"를 묻는다면, 이 커맨드는 "빌드 시점의 전제가 지금도 유효한가" 를 묻는 시간축 드리프트 감사입니다.

범위 비교

측면 harness-audit ops-audit fit-audit (본 커맨드)
실행 시점 기존 하네스 (harness-setup 재진입 분기) 기존 하네스 (독립 실행) 기존 하네스 (독립 실행)
주 관심사 구성 정합성 (4-scope, JSON, anti-pattern, agent↔playbook 매핑) 런타임 부채 (세션 복구·retry 상한·덮어쓰기·Jaccard) 프로젝트 적합성 (빌드 전제 vs 현재 프로젝트 실상)
데이터 소스 하네스 파일만 하네스 파일만 하네스 파일 + 대상 프로젝트 실제 스캔 + 외부 인터페이스(MCP·훅) 정적 검증
출력 등급 CRITICAL/HIGH/MEDIUM/LOW RISK-HIGH/MED/LOW MAJOR-DRIFT/MINOR-DRIFT/ALIGN
근본 질문 "파일 구조가 올바른가" "실행할 때 실패하는가" "이 프로젝트에 여전히 맞는가"

세 감사는 독립이며 상호 보완입니다. 권장 순서: harness-audit → ops-audit → fit-audit. 구성·운영 문제를 먼저 해소한 후 적합성을 판정해야 드리프트 신호가 왜곡되지 않습니다.

등급 체계 매핑

  • MAJOR-DRIFT ≈ 전면 재구축 권장 — /harness-architect:harness-setup 재실행이 유지보수 누적 비용보다 저렴한 수준의 괴리
  • MINOR-DRIFT ≈ 부분 수정 권장 — settings.json 권한 범위 업데이트, 에이전트 1~2개 추가/제거, CLAUDE.md 섹션 리프레시 등 국소 리팩터
  • ALIGN ≈ 현 하네스 유지 — 드리프트 없음

RISK 등급(ops-audit) 과 BLOCK 등급(Phase 9 Advisor) 과는 직접 대응되지 않습니다. DRIFT 는 "프로덕션에서 실패"를 의미하지 않으며, "하네스가 이 프로젝트를 계속 돕는 정도"를 평가합니다.

Pre-flight Gate — 하네스·baseline 존재 여부 검증

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

이 커맨드는 진단 전용입니다. 드리프트가 발견되어도 fit-audit 자체가 하네스를 수정하지 않습니다. 개선은 보고서의 Recommendation 섹션 안내를 따라 /harness-architect:harness-setup 재실행, /harness-architect:ops-audit, 또는 사용자가 직접 .claude/ 편집으로 수행합니다.

이후 다음을 확인합니다:

  1. 대상 경로 수집: $ARGUMENTS 또는 AskUserQuestion 으로 대상 프로젝트 절대 경로 수집. 경로 유효성 검증(test -d).
  2. 하네스 최소 존재 검증: 다음 중 하나라도 존재해야 적합성 감사가 의미 있음:
    • {대상}/CLAUDE.md
    • {대상}/.claude/settings.json
    • {대상}/.claude/agents/ (파일 1개 이상)
  3. 모두 미존재 시 AskUserQuestion 분기:
    • 먼저 harness-setup 실행 — /harness-architect:harness-setup 안내 후 종료
    • 취소 — 종료
  4. Baseline 모드 결정:
    • {대상}/docs/*/01-discovery-answers.md 존재 → baseline-mode (전제 vs 현재 비교 가능)
    • 부재 (수동 구축 하네스·baseline 소실) → heuristic-only-mode (현재 스캔만으로 추정 baseline 재구성, Coverage Gaps 에 한계 명시)
  5. 결정된 모드를 에이전트 프롬프트의 [Audit Mode] 필드로 전달.

Read the full file on GitHub · 100 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 · 100 lines · 120 tokens per session scan A 577ef0697a5c

Subscribe to this mod's changes

fit-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 120 tokens to every session and 1,933 once invoked, about $0.0006 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.

Claude 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

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

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