agentmods.dev

audit-skill

audit-skill is a skill for Claude Code, Codex from richfrem/agent-plugins-skills. It costs 35 tokens per session (697 once invoked), scanned A, original, MIT.

An auditing tool for checking whether an agent skill follows defined structure, documentation, testing, and isolation rules. It examines files such as SKILL.md and evals.json.

In plain words
What is it for?
Use it to check line limits, evaluation formats, naming, required reference documents, script locations, and unwanted state files.
Why use it?
It finds compliance and maintenance problems before a skill is shared or updated.

Skill for Claude CodeCodex

Part of the agent-scaffolders plugin — 33 skills, 2 plugins shipped together

not rated 6 yesterday A scan 35 tokens original MIT
View the source file richfrem/agent-plugins-skills
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 skills/richfrem/agent-plugins-skills/audit-skill
Any agent
npx skills add richfrem/agent-plugins-skills --skill audit-skill
Clone the repo
git clone --depth 1 https://github.com/richfrem/agent-plugins-skills

Made for: Claude Code, Codex.

Or install agent-scaffolders, the plugin that ships this one along with the rest of its 33 skills, 2 plugins.

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 audit-skill

README.md
[![agentmods](https://agentmods.dev/badge/skills/richfrem/agent-plugins-skills/audit-skill.svg)](https://agentmods.dev/skills/richfrem/agent-plugins-skills/audit-skill)
Your own site
<a href="https://agentmods.dev/skills/richfrem/agent-plugins-skills/audit-skill"><img src="https://agentmods.dev/badge/skills/richfrem/agent-plugins-skills/audit-skill.svg" alt="Measured on agentmods" height="20"></a>
Per session 35 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 697 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 $0.00035 $0.00697
Opus 5 $0.00017 $0.00349
Sonnet 5 $0.00007 $0.00139
Haiku 4.5 $0.00003 $0.00070

Measured yesterday against content hash 5ce666998e21, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

audit-skill 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 yesterday.

The scan reads SKILL.md. This mod also ships 1 executable file (scripts/audit_skill.py), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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/agent-scaffolders/skills/audit-skill/SKILL.md · 62 lines

How it starts

The opening of the file, as written. The whole thing — 62 lines — stays where its author put it; the contents beside it link to each section on GitHub.

audit-skill: Skill Alignment & Evolution Auditor

Audits an individual skill against the 6 ecosystem evolution invariants and provides automated refactoring recommendations to achieve full compliance.

The 6 Alignment Invariants

  1. Layer 1 Procedural Core: SKILL.md target $\le 100$ lines. Offload domain depth to references/ via Progressive Disclosure.
  2. Boolean Evals Schema: evals/evals.json must be a root JSON list with should_trigger: true/false.
  3. Hub-and-Spoke Script Isolation (ADR-002/003): All scripts reside in plugin root scripts/ and are symlinked into skills/<skill>/scripts/. Zero un-symlinked real files.
  4. Frontmatter Standards: name matches directory slug exactly; description is third-person active verb and $\le 1024$ chars.
  5. Contract & Fallback Links: Must provide acceptance-criteria.md and fallback-tree.md in references/.
  6. Spoke Hygiene: Zero session logs, raw wiki traces, or .agent/ state in skill folders.

Quick Execution

Run the bundled alignment script directly against any skill directory:

# Audit a single skill
python3 plugins/agent-scaffolders/scripts/audit_skill.py plugins/<plugin>/skills/<skill-name>

# Auto-repair fixable schema deviations (e.g. migrate evals.json)
python3 plugins/agent-scaffolders/scripts/audit_skill.py plugins/<plugin>/skills/<skill-name> --fix

# JSON output for automated pipelines
python3 plugins/agent-scaffolders/scripts/audit_skill.py plugins/<plugin>/skills/<skill-name> --json

Alignment & Refactoring Procedure

Phase 1: Diagnostic Assessment

  1. Run audit_skill.py <path>. Note all errors and warnings.
  2. If SKILL.md exceeds 100 lines:
    • Identify detailed background, multi-page tables, or complex workflows.
    • Extract them into references/<topic>.md.
    • Replace in SKILL.md with concise procedural steps and markdown links.

Phase 2: Hub-and-Spoke Remediation (ADR-002/003)

If real scripts are found inside skills/<skill>/scripts/:

  1. Move the real script to plugins/<plugin>/scripts/<script-name>.py.
  2. Register the symlink in symlinks.json.
  3. Run python3 .agents/skills/symlink-manager/scripts/symlink_manager.py restore.
  4. Run symlink_manager.py diagnose to confirm zero imposters.

Read the full file on GitHub · 62 lines

Files

What ships with it

4 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.

  1. yesterday First seen · 62 lines · 35 tokens per session scan A 5ce666998e21

Subscribe to this mod's changes

audit-skill is a skill published in the GitHub repository richfrem/agent-plugins-skills (6 stars, last pushed yesterday), licensed MIT. It adds 35 tokens to every session and 697 once invoked, about $0.0002 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 2026-09-03.

Building agentsagent-skillsagentic-frameworkagentic-osclaude-code-skillclaude-pluginsclaude-skills
Related

Other skills, from other repositories

composio

Use Composio from Agent Swarm through the agent-swarm x composio CLI route, the swarmx MCP tool, or a registered ctx.api.composio script connection. Trigger when a task needs connected third-party app tools such as Gmail, Google Calendar, Google Docs, Google Drive, GitHub, Slack, Notion, or HubSpot through Tool Router…

desplega-ai/agent-swarm · 128 tokens

soul

Embody this digital identity. Read SOUL.md first, then STYLE.md, then examples/. Become the person—opinions, voice, worldview.

aeonfun/soul.md · 33 tokens

close-issue

Close a GitHub or GitLab issue with a summary comment.

desplega-ai/agent-swarm · 16 tokens

implement-issue

Implement a GitHub issue or GitLab issue and create a PR/MR.

desplega-ai/agent-swarm · 19 tokens

bbc-skill

Fetch Bilibili (哔哩哔哩) video comments for UP主 self-analysis. Use when the user asks to collect, download, export, or analyze comments on a Bilibili video (BV号 / URL / UID). Produces JSONL + summary.json suitable for further Claude Code analysis (sentiment, keywords, audience trends). Read-only; does not…

Agents365-ai/bbc-skill · 86 tokens

team-coordination

Coordinate software development work by analyzing requirements, delegating tasks to specialized sub-agents (developer, code-reviewer, tester), and synthesizing their work into cohesive deliverables. Use this for complex projects that require multiple specialized perspectives.

KarmaloopAI/Jiva · 50 tokens