What is auditing-agent-skills?

A review procedure for existing Agent Skills, which are reusable instructions for coding agents. It finds outdated facts, renamed or missing references, weak descriptions, overlap, missing test cases, and unlisted skills, then proposes fixes without applying them.

Use it to audit a group of skills and produce proposed corrections for a person to approve.

Skills can drift as models, names, platform details, and project files change; automatic edits could also break workflows that depend on them.

auditing-agent-skills — Skill for Claude Code by jamesgray-ai

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.

Any agent

npx skills add jamesgray-ai/handsonai-plugins --skill auditing-agent-skills

Clone the repo

git clone --depth 1 https://github.com/jamesgray-ai/handsonai-plugins

Made for: Claude Code.

Or install handsonai, the plugin that ships this one along with the rest of its 16 skills.

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/jamesgray-ai/handsonai-plugins/auditing-agent-skills/github.svg)](https://agentmods.dev/skills/jamesgray-ai/handsonai-plugins/auditing-agent-skills)

Your own site

<a href="https://agentmods.dev/skills/jamesgray-ai/handsonai-plugins/auditing-agent-skills"><img src="https://agentmods.dev/badge/skills/jamesgray-ai/handsonai-plugins/auditing-agent-skills/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/jamesgray-ai/handsonai-plugins/auditing-agent-skills"><img src="https://agentmods.dev/badge/skills/jamesgray-ai/handsonai-plugins/auditing-agent-skills.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 151 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,898 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.

Model	Per session	Once invoked
Fable 5.1	$0.00151	$0.01898
Opus 5.5	$0.00060	$0.00759
Sonnet 5.5	$0.00030	$0.00380
Haiku 4.5	$0.00015	$0.00190

Measured 4d ago against content hash eba92898d1b1, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

auditing-agent-skills 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.

plugins/handsonai/skills/auditing-agent-skills/SKILL.md · 71 lines

How it starts

The opening of the file, as written. The whole thing — 71 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Auditing Agent Skills

This skill checks a set of existing skills against one shared checklist and reports what has gone out of date, with a proposed fix for each finding. It never changes a skill on its own. Every fix is a proposal until the user approves it; a wrong rename inside a skill that runs other skills can break a working workflow.

Platform registry: platform facts (how a skill is installed, where context lives, scheduling, agents) come from the platform registry. Read it from references/platform-registry.json in this skill's own folder; if that file isn't there, from registries/platform-registry.json at the plugin root; if neither exists, fetch https://raw.githubusercontent.com/jamesgray-ai/handsonai/main/plugins/handsonai/registries/platform-registry.json. Read it once per session and reuse it. Find a platform by its key or by any name in its aliases list.

For this skill, the facts that matter are each platform's capabilities.skill_listing (what you can see of the user's skills) and unattended_runs (whether an audit can run on a schedule). Treat a missing value as unknown and say so.

Load the checklist

The audit criteria live in one place, hygiene-criteria.md, owned by the applying-skill-best-practices skill. Never write your own list. Look for it in this order, relative to this skill's own folder, and tell the user which one you used:

references/hygiene-criteria.md in this skill's folder (included when this skill was downloaded as its own file);
../applying-skill-best-practices/references/hygiene-criteria.md (the two skills installed together, as in the Hands-on AI plugin);
https://raw.githubusercontent.com/jamesgray-ai/handsonai/main/plugins/handsonai/skills/applying-skill-best-practices/references/hygiene-criteria.md.

If none of these is available, stop. Tell the user you couldn't load the checklist, list where you looked, and ask them to install applying-skill-best-practices (or share the checklist). Don't audit against criteria you made up.

Read the full file on GitHub · 71 lines

Files

What ships with it

10 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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.

4d ago Changed eba92898d1b1
19d ago First seen · 71 lines · 151 tokens per session scan A 02caf6d635fb

Subscribe to this mod's changes

auditing-agent-skills is a skill published in the GitHub repository jamesgray-ai/handsonai-plugins (8 stars, last pushed yesterday), licensed MIT. It adds 151 tokens to every session and 1,898 once invoked, about $0.0006 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 2026-10-19.

Building agents

auditing-agent-skills next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
auditing-agent-skillsjamesgray-ai/handsonai-plugins	Skill	8	yesterday	MIT	A	151	Claude Code
imagegenopenai/codex	Skill	133k	yesterday	Apache-2.0	A	113	Codex
playwright-climicrosoft/playwright	Skill	99k	yesterday	Apache-2.0	A	19	Claude Code
local-ai-agentsmicrosoft/ai-agents-for-beginners	Skill	79k	4d ago	MIT	A	200	Claude Code, Codex
systematic-debuggingobra/superpowers	Skill	313k	3d ago	MIT	A	21	Claude Code
next-cache-components-adoptionvercel/next.js	Skill	143k	yesterday	MIT	A	95	Claude Code
next-partial-prefetching-adoptionvercel/next.js	Skill	143k	yesterday	MIT	A	103	Claude Code