harness-audit

harness-audit is a command for Claude Code from paladini/harness-score. It costs 14 tokens per session (334 once invoked), scanned A, original, MIT.

A command that scans a repository's AI coding setup and scores its maturity across five levels.

In plain words
What is it for?
Use it to audit AGENTS.md, rules, skills, hooks, sensors, CI, and repository hygiene, then see the highest-priority fixes and their documentation.
Why use it?
It shows what guidance, rules, automation, and safeguards are missing, using repeatable filesystem checks rather than AI judgement.

Command for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the harness-score plugin — 1 skill, 1 command shipped together

Good fit Use it to audit AGENTS.md, rules, skills, hooks, sensors, CI, and repository hygiene, then see the highest-priority fixes and their documentation.

Compare 6 commands from other repositories ↓
Install with agentmods
npx agentmods add commands/paladini/harness-score/harness-audit
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Clone the repo
git clone --depth 1 https://github.com/paladini/harness-score

Made for: Claude Code.

Or install harness-score, the plugin that ships this one along with the rest of its 1 skill, 1 command.

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/paladini/harness-score/harness-audit.svg)](https://agentmods.dev/commands/paladini/harness-score/harness-audit)
Your own site
<a href="https://agentmods.dev/commands/paladini/harness-score/harness-audit"><img src="https://agentmods.dev/badge/commands/paladini/harness-score/harness-audit.svg" alt="Measured on agentmods" height="20"></a>
Per session 14 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 334 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 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 $0.00014 $0.00334
Opus 5 $0.00007 $0.00167
Sonnet 5 $0.00003 $0.00067
Haiku 4.5 $0.00001 $0.00033

Measured 8d ago against content hash 9b6204cb9b89, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, 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 8d 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.

plugins/claude-code/commands/harness-audit.md · 37 lines

What it actually says

/harness-audit

Audit this repository's AI harness maturity. Follow these steps exactly:

  1. Run the deterministic scanner from the workspace root:

    npx -y harness-score . --json
    

    Do not analyze the repository yourself — the scanner's output is the audit. It is fully deterministic (filesystem checks only, no AI, no network), so its numbers are reproducible facts.

  2. Present the results to the user:

    • The maturity level (level.index, level.name) and total score, with one sentence of interpretation.
    • A compact table of the six dimensions with their percentages.
    • The top 3 failed checks by points (checks[] where passed is false, sorted by points descending): for each, give the check id, what is missing (evidence), the concrete fix (remediation), and the guide link (docsUrl).
    • If level.nextLevelGaps is non-empty, state exactly what blocks the next level.
  3. End by offering: "Want me to fix any of these? I can create the missing harness files following the guide's recipes." If the user accepts, use the harness-engineering skill.

If npx fails (offline/registry blocked), say so and suggest installing the CLI locally with npm i -D harness-score; never substitute your own estimate for the scanner's output.

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. 8d ago First seen · 37 lines · 14 tokens per session scan A 9b6204cb9b89

Subscribe to this mod's changes

harness-audit is a command published in the GitHub repository paladini/harness-score (398 stars, last pushed yesterday), licensed MIT. It adds 14 tokens to every session and 334 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.