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 skills add testzugang/pi-plugins --skill audit-agents-mdgit clone --depth 1 https://github.com/testzugang/pi-pluginsWrote 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/skills/testzugang/pi-plugins/audit-agents-md)<a href="https://agentmods.dev/skills/testzugang/pi-plugins/audit-agents-md"><img src="https://agentmods.dev/badge/skills/testzugang/pi-plugins/audit-agents-md/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.
<a href="https://agentmods.dev/skills/testzugang/pi-plugins/audit-agents-md"><img src="https://agentmods.dev/badge/skills/testzugang/pi-plugins/audit-agents-md.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00038 | $0.00776 |
| Opus 5.5 | $0.00015 | $0.00310 |
| Sonnet 5.5 | $0.00008 | $0.00155 |
| Haiku 4.5 | $0.00004 | $0.00078 |
Grade A, and why
audit-agents-md 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 1mo 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.
How it starts
The opening of the file, as written. The whole thing — 82 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Audit AGENTS.md
Core Rule
Audit only AGENTS.md. Do not read, summarize, validate, or suggest changes to CLAUDE.md unless the user explicitly changes the task.
This skill exists because default audit behavior tends to drift into CLAUDE.md comparison. Do not do that.
Workflow
- Locate
AGENTS.mdin the current project root.- If absent, report that no root
AGENTS.mdwas found and stop. - Do not search for
CLAUDE.md.
- If absent, report that no root
- Read
AGENTS.mdcompletely. - Audit using the checklist below.
- Produce a prioritized report.
- Do not edit files automatically. If the user asks for fixes after the report, make a focused plan first.
Audit Checklist
| Area | Check |
|---|---|
| Structure | Clear title, headings, and readable markdown. |
| Scope | Instructions are relevant for coding agents working in this repository. |
| Precedence | No claims to override system, developer, or direct user instructions. |
| Consistency | No duplicated, conflicting, or circular rules. |
| Actionability | Agents can tell what to do, when to do it, and what to avoid. |
| Tooling | Tool names and commands match the intended harness, or are written generically. |
| Safety | No overly broad destructive automation, secret exposure, or unreviewed deployment instructions. |
| Freshness | No stale references to removed commands, renamed files, or old workflows. |
Stale Harness-Specific Leftovers
Flag Claude Code-specific content when it appears in AGENTS.md but the file is intended for pi or generic coding agents:
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.
- 1mo ago First seen · 82 lines · 38 tokens per session scan A 6f23aca5304e
audit-agents-md is a skill published in the GitHub repository testzugang/pi-plugins (3 stars, last pushed 3mo ago), licensed MIT. It adds 38 tokens to every session and 776 once invoked, about $0.0002 per session on Opus 5.5. 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 skills, from other repositories
autoreview
Structured code review through the shared OpenClaw agent-skills installation.
omh-code-review
This is an OMH code-review workflow skill, projected for Agent Skills hosts (Claude Code, Codex, Cursor, opencode, OpenClaw, pi).
revdiff-plan
Review the last Codex assistant message (plan, analysis, or proposal) with inline annotations in a TUI overlay. Extracts the most recent response from Codex rollout files and opens it in revdiff for review and annotation. Activates on "revdiff-plan", "review plan with revdiff", "annotate plan", "review last response"…
explore-unknowns
Guide the user through a quadrant walk that maps the unknowns of a task — open by listing the known knowns, then work through known unknowns, unknown knowns, and unknown unknowns one stage at a time, ending with a complete four-quadrant map in the user's hands. Use when a request is ambiguous or underspecified, the…
asplos-writing-style
Use when drafting or revising ASPLOS prose — engineering the first two pages that rapid review actually reads, stating the cross-layer insight as one quotable sentence, structuring per-layer mechanism sections, writing bounded claims, and fitting everything into 11 self-contained pages that include figures and…
re0-merge
Review and land an external contribution the way this suite does: gate it against the thesis, land it with the author's credit intact, complete a new skill rather than merging it raw, then approve, credit, and explain before closing. Use when reviewing a pull request, as any collaborator or maintainer, not only the…