acr-audit

acr-audit is a command for Claude Code from hbkdad/arc. It costs 24 tokens per session (216 once invoked), scanned A, original, MIT.

A quality-check command that runs code formatting checks, linting, type checking, and tests with coverage. Coverage shows which lines of code the tests exercise.

In plain words
What is it for?
Use it before a release or review to run Ruff, Pyright, and Pytest, then identify modules below 90% coverage and their missing line ranges.
Why use it?
It gives a single report on style, type, test, and under-tested-code problems, stopping at the first failed check.

Command for Claude Code

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.

agentmods
npx agentmods add commands/hbkdad/arc/acr-audit
Clone the repo
git clone --depth 1 https://github.com/hbkdad/arc

Made for: Claude Code.

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 acr-audit

README.md
[![agentmods](https://agentmods.dev/badge/commands/hbkdad/arc/acr-audit.svg)](https://agentmods.dev/commands/hbkdad/arc/acr-audit)
Your own site
<a href="https://agentmods.dev/commands/hbkdad/arc/acr-audit"><img src="https://agentmods.dev/badge/commands/hbkdad/arc/acr-audit.svg" alt="Measured on agentmods" height="20"></a>
Per session 24 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 216 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00024 $0.00216
Opus 5 $0.00012 $0.00108
Sonnet 5 $0.00005 $0.00043
Haiku 4.5 $0.00002 $0.00022

Measured 4d ago against content hash 87f8b3b5ffb5, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

acr-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 4d 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.

.claude/commands/acr-audit.md · 18 lines

What it actually says

Run, from the repo root, in this order (stop and report immediately if any step fails rather than continuing past a broken gate):

uv run ruff format --check .
uv run ruff check .
uv run pyright
uv run pytest --cov=acr --cov-report=term-missing -q

Report:

  • Whether each step passed or failed, with the real error output for any failure (not a paraphrase).
  • From the coverage report: any module below 90%, with the specific missing line ranges. For each one, note briefly whether it looks like real untested business logic worth a test, or an external-failure branch (missing CLI tool, network error, etc.) that's low-value to chase.
  • Do not propose or make any code changes as part of this command -- it's a report, not a fix. If the user wants fixes, that's a separate follow-up.
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. 4d ago First seen · 18 lines · 24 tokens per session scan A 87f8b3b5ffb5

Subscribe to this mod's changes

acr-audit is a command published in the GitHub repository hbkdad/arc (4 stars, last pushed 1mo ago), licensed MIT. It adds 24 tokens to every session and 216 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 2026-08-31.