agentmods.dev

harness-audit

harness-audit is a command for Claude Code from multiplex-ai/muggle-ai-teams. It costs 0 tokens per session (526 once invoked), scanned A, a copy of harness-audit, MIT.

A repeatable audit of a coding-agent setup that produces scores and a prioritized list of findings. It can inspect the whole repository or selected areas such as hooks, skills, commands, and agents.

In plain words
What is it for?
Use it to assess tool coverage, context use, quality checks, saved memory, evaluation coverage, security safeguards, and cost efficiency, with text or JSON output.
Why use it?
It provides the same checks for the same code revision, making weaknesses easier to compare and address instead of relying on informal judgment.

Command for Claude Code

Written for Claude Code: $ARGUMENTS substitution. Also seen: mentions OpenCode.

Needs its repository: it runs a file that does not travel with it, so clone the repository first. The line is node scripts/harness-audit.js <scope> --format <text|json>.

Part of the muggle-ai-teams plugin — 28 commands, 29 agents shipped together

not rated 2repo 4mo ago A scan 0 tokens copy · 100% MIT

Good fit Use it to assess tool coverage, context use, quality checks, saved memory, evaluation coverage, security safeguards, and cost efficiency, with text or JSON output.

Compare 6 commands from other repositories ↓
View source ↗ multiplex-ai/muggle-ai-teams muggletest.com
Install

Getting it into your agent

It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.

Clone the repo
git clone --depth 1 https://github.com/multiplex-ai/muggle-ai-teams
agentmods
npx agentmods add commands/multiplex-ai/muggle-ai-teams/harness-audit

Made for: Claude Code.

Or install muggle-ai-teams, the plugin that ships this one along with the rest of its 28 commands, 29 agents.

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/multiplex-ai/muggle-ai-teams/harness-audit/github.svg)](https://agentmods.dev/commands/multiplex-ai/muggle-ai-teams/harness-audit)
Your own site
<a href="https://agentmods.dev/commands/multiplex-ai/muggle-ai-teams/harness-audit"><img src="https://agentmods.dev/badge/commands/multiplex-ai/muggle-ai-teams/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/multiplex-ai/muggle-ai-teams/harness-audit"><img src="https://agentmods.dev/badge/commands/multiplex-ai/muggle-ai-teams/harness-audit.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 526 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 100% copy Near-identical to another mod 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 $0.00000 $0.00526
Opus 5 $0.00000 $0.00263
Sonnet 5 $0.00000 $0.00105
Haiku 4.5 $0.00000 $0.00053

Measured 12d ago against content hash 62ea46a413be, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

harness-audit 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.

Origin

This is a copy

100% identical to harness-audit — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

commands/harness-audit.md · 72 lines

How it starts

The opening of the file, as written. The whole thing — 72 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Harness Audit Command

Run a deterministic repository harness audit and return a prioritized scorecard.

Usage

/harness-audit [scope] [--format text|json]

  • scope (optional): repo (default), hooks, skills, commands, agents
  • --format: output style (text default, json for automation)

Deterministic Engine

Always run:

node scripts/harness-audit.js <scope> --format <text|json>

This script is the source of truth for scoring and checks. Do not invent additional dimensions or ad-hoc points.

Rubric version: 2026-03-16.

The script computes 7 fixed categories (0-10 normalized each):

  1. Tool Coverage
  2. Context Efficiency
  3. Quality Gates
  4. Memory Persistence
  5. Eval Coverage
  6. Security Guardrails
  7. Cost Efficiency

Scores are derived from explicit file/rule checks and are reproducible for the same commit.

Output Contract

Return:

  1. overall_score out of max_score (70 for repo; smaller for scoped audits)
  2. Category scores and concrete findings
  3. Failed checks with exact file paths
  4. Top 3 actions from the deterministic output (top_actions)
  5. Suggested ECC skills to apply next

Checklist

  • Use script output directly; do not rescore manually.
  • If --format json is requested, return the script JSON unchanged.
  • If text is requested, summarize failing checks and top actions.
  • Include exact file paths from checks[] and top_actions[].

Example Result

Harness Audit (repo): 66/70
- Tool Coverage: 10/10 (10/10 pts)
- Context Efficiency: 9/10 (9/10 pts)
- Quality Gates: 10/10 (10/10 pts)

Top 3 Actions:
1) [Security Guardrails] Add prompt/tool preflight security guards in hooks/hooks.json. (hooks/hooks.json)
2) [Tool Coverage] Sync commands/harness-audit.md and .opencode/commands/harness-audit.md. (.opencode/commands/harness-audit.md)
3) [Eval Coverage] Increase automated test coverage across scripts/hooks/lib. (tests/)

Arguments

$ARGUMENTS:

  • repo|hooks|skills|commands|agents (optional scope)
  • --format text|json (optional output format)

Read the full file on GitHub · 72 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. 12d ago First seen · 72 lines · 0 tokens per session scan A 62ea46a413be

Subscribe to this mod's changes

harness-audit is a command published in the GitHub repository multiplex-ai/muggle-ai-teams (2 stars, last pushed 4mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 526 tokens. A static security scan graded it A with 0 findings. It is 100% identical to harness-audit, differing in 0 lines, and is treated as a copy.

Building agentsDebuggingai-agent-orchestrationai-agentsai-code-reviewai-developmentai-pair-programmingai-workflow
Related

Other commands, from other repositories

diagnose-runtime

Quickly diagnose runtime performance issues in web applications including freezes, hangs, memory leaks, and slow performance.

rubenCodeforges/codeforges-claude-plugin · 0 tokens

fix-issue

Fixes GitHub issues using parallel analysis agents for root cause investigation, code exploration, and regression detection. Reads issue context from gh CLI, searches codebase and memory for related patterns, generates a fix with tests, and links the resolution back to the issue via PR. Includes prevention analysis to…

yonatangross/orchestkit · 82 tokens

ci-debug

Diagnose a failing CI run against an 11-pattern playbook. Classifies the failure, cites the relevant memory entry, proposes the exact fix command — but NEVER applies without explicit user approval. Use when a specific PR check or GitHub Actions run failed and you want a diagnosis instead of speculation. Don't use for…

yonatangross/orchestkit · 92 tokens

check-cache-bugs

Audit Claude Code setup for cache bugs (CC#40524) — sentinel, --resume/--continue, attribution header + ArkNill B3/B4/B5.

FlorianBruniaux/claude-code-plugins · 39 tokens

investigate

Systematic root-cause debugging — find the cause before writing any fix.

FlorianBruniaux/claude-code-plugins · 17 tokens

time-travel

Debugger de razonamiento que muestra por qué el framework eligió cada modelo, skill y decisión. Usa cuando el usuario dice "time travel", "por qué eligió", "reasoning debug", "decision audit", "why this model", "razonamiento", "debug reasoning", "explain decision", "modelo elegido". Permite ajustar skills…

doncheli/don-cheli-sdd · 78 tokens