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.
npx agentmods add commands/hbkdad/arc/acr-auditgit clone --depth 1 https://github.com/hbkdad/arcWrote 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.
[](https://agentmods.dev/commands/hbkdad/arc/acr-audit)<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>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.
| Model | Per session | Once 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 |
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.
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.
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.
- 4d ago First seen · 18 lines · 24 tokens per session scan A 87f8b3b5ffb5
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.
Other commands, from other repositories
test-coverage
Analyze and improve test coverage.
ship-and-babysit
Commit, push to origin (fork), open PR to tinyhumansai/openhuman:main, then poll every 5min for CodeRabbit comments and CI failures, resolve them, and exit when clean.
rp-build-cli
Build with rp-cli context builder → chat → implement.
test
Generate comprehensive tests.
test
运行测试并分析失败原因.
start-feature
Command "start-feature" from melagiri/code-insights, covering /start-feature — auto-setup feature development team, step 1: create git worktree, example (adapt the slug from $arguments), step 2: create named team and step 3: spawn pm agent.