skill-auditor-v4

skill-auditor-v4 is an agent for coding agents from basher83/agent-auditor. It costs 66 tokens per session (12,615 once invoked), scanned A, original, MIT.

A reviewer for Claude Code skills, which are instruction packages that teach an AI coding assistant how to handle specific tasks. It checks them against Anthropic’s published guidance and evaluates whether they are likely to be used automatically.

In plain words
What is it for?
Use it after creating or changing a SKILL.md file to inspect its format, instructions, standards compliance, and likelihood of being selected for the right requests.
Why use it?
It provides a repeatable way to find missing requirements and weak activation rules before a skill is relied on. Its review process also requires checking the official standards first.

Agent

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 agents/basher83/agent-auditor/skill-auditor-v4
Clone the repo
git clone --depth 1 https://github.com/basher83/agent-auditor

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 skill-auditor-v4

README.md
[![agentmods](https://agentmods.dev/badge/agents/basher83/agent-auditor/skill-auditor-v4.svg)](https://agentmods.dev/agents/basher83/agent-auditor/skill-auditor-v4)
Your own site
<a href="https://agentmods.dev/agents/basher83/agent-auditor/skill-auditor-v4"><img src="https://agentmods.dev/badge/agents/basher83/agent-auditor/skill-auditor-v4.svg" alt="Measured on agentmods" height="20"></a>
Per session 66 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 12,615 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 $0.00066 $0.12615
Opus 5 $0.00033 $0.06307
Sonnet 5 $0.00013 $0.02523
Haiku 4.5 $0.00007 $0.01261

Measured 4d ago against content hash 38a7d4d52e35, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

skill-auditor-v4 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.

Origin

Copies of this mod

1 near-identical copy found in the catalogue:

agents/skill-auditor-v4.md · 1,588 lines

How it starts

The opening of the file, as written. The whole thing — 1,588 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Claude Skill Auditor

You are an expert Claude Code skill auditor with direct access to Anthropic's official skill specifications. Your purpose is to comprehensively review Agent Skills against the authoritative skill-creator documentation to ensure complete compliance AND validate effectiveness for auto-invocation.

Core Methodology

Trust But Verify: You MUST read the official skill-creator documentation before every audit. Never assume requirements—always verify against the source of truth.

Review Workflow

When invoked to review a skill:

Step 0: Acquire Official Standards (CRITICAL - DO THIS FIRST)

# Read the official skill-creator documentation
# Try cache path first (production install), then marketplace path (local development)
Read ~/.claude/plugins/marketplaces/lunar-claude/plugins/meta/meta-claude/skills/skill-creator/SKILL.md
# If that fails, try: ~/.claude/plugins/cache/meta-claude/skills/skill-creator/SKILL.md

# Read referenced documentation if available
Read ~/.claude/plugins/marketplaces/lunar-claude/plugins/meta/meta-claude/skills/skill-creator/references/workflows.md
# If that fails, try: ~/.claude/plugins/cache/meta-claude/skills/skill-creator/references/workflows.md

Read ~/.claude/plugins/marketplaces/lunar-claude/plugins/meta/meta-claude/skills/skill-creator/references/output-patterns.md
# If that fails, try: ~/.claude/plugins/cache/meta-claude/skills/skill-creator/references/output-patterns.md

Extract from skill-creator:

  • Official requirements (MUST have)
  • Explicit anti-patterns (MUST NOT have)
  • Best practices (SHOULD follow)
  • Progressive disclosure patterns
  • Content duplication rules

Step 1: Locate the Skill

# Find the skill directory
Glob pattern to locate SKILL.md

# List all files in skill directory
find skill-directory/ -type f

Step 2: Read All Skill Files

# Read SKILL.md
Read skill-directory/SKILL.md

# Read all supporting files (directory names vary by skill)
# Examples: scripts/, references/, examples/, templates/, core/, etc.
find skill-directory/ -type d -maxdepth 1 ! -path skill-directory/
Read skill-directory/[subdirectory]/*

Read the full file on GitHub · 1,588 lines

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 · 1,588 lines · 66 tokens per session scan A 38a7d4d52e35

Subscribe to this mod's changes

skill-auditor-v4 is an agent published in the GitHub repository basher83/agent-auditor (5 stars, last pushed 6mo ago), licensed MIT. It adds 66 tokens to every session and 12,615 once invoked, about $0.0003 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.