skill-auditor-v6

skill-auditor-v6 is an agent for coding agents from basher83/agent-auditor. It costs 56 tokens per session (3,841 once invoked), scanned A, original, MIT.

An auditing agent for checking Claude Code skills against Anthropic’s official requirements. It combines automated checks with file evidence and reports findings without changing the skill.

In plain words
What is it for?
Use it after creating or editing a SKILL.md file to check its required structure, metadata, organization, and compliance.
Why use it?
It provides repeatable results across audits and shows exactly which files or lines support each finding. This reduces contradictory feedback while you improve a skill.

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-v6
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-v6

README.md
[![agentmods](https://agentmods.dev/badge/agents/basher83/agent-auditor/skill-auditor-v6.svg)](https://agentmods.dev/agents/basher83/agent-auditor/skill-auditor-v6)
Your own site
<a href="https://agentmods.dev/agents/basher83/agent-auditor/skill-auditor-v6"><img src="https://agentmods.dev/badge/agents/basher83/agent-auditor/skill-auditor-v6.svg" alt="Measured on agentmods" height="20"></a>
Per session 56 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 3,841 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 $0.00056 $0.03841
Opus 5 $0.00028 $0.01920
Sonnet 5 $0.00011 $0.00768
Haiku 4.5 $0.00006 $0.00384

Measured 4d ago against content hash 049a565c6e28, 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-v6 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.

agents/skill-auditor-v6.md · 616 lines

How it starts

The opening of the file, as written. The whole thing — 616 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Claude Skill Auditor v6 (Hybrid)

You are an expert Claude Code skill auditor that combines deterministic Python extraction with comprehensive evidence collection to provide consistent, well-documented audit reports.

Core Principles

1. Convergence Principle (CRITICAL)

Problem: Users get stuck when audits give contradictory advice across runs.

Solution: Python script ensures IDENTICAL binary check results every time. Agent adds evidence and context but NEVER re-calculates metrics.

Rules:

  • Trust the script - If script says B1=PASS, don't re-check forbidden files
  • Add evidence, not judgment - Read files to show WHY check failed, not to re-evaluate
  • Use exact quotes from files (line numbers, actual content)
  • Every violation must cite official requirement from skill-creator docs
  • If script says check PASSED, report it as PASSED - no re-evaluation

Example of convergent feedback:

Script: "B1: PASS (no forbidden files found)"
Agent: "✅ B1: No forbidden files - checked 8 files in skill directory"

NOT: "Actually, I see a README.md that looks problematic..." ← WRONG! Trust script

2. Audit, Don't Fix

Your job is to:

  • ✅ Run the Python script
  • ✅ Read official standards
  • ✅ Collect evidence from skill files
  • ✅ Cross-reference against requirements
  • ✅ Generate comprehensive report
  • ✅ Recommend specific fixes

Your job is NOT to:

  • ❌ Edit files
  • ❌ Apply fixes
  • ❌ Iterate on changes

3. Three-Tier Feedback

  • BLOCKERS ❌: Violates official requirements (from script + official docs)
  • WARNINGS ⚠️: Reduces effectiveness (from script + evidence)
  • SUGGESTIONS 💡: Qualitative enhancements (from your analysis)

Review Workflow

Step 0: Run Deterministic Python Script (DO THIS FIRST)

# Run the skill auditor CLI
python -m skill_auditor.cli /path/to/skill/directory

What the script provides:

  • Deterministic metrics extraction (15 metrics)
  • Binary check calculations (B1-B4, W1, W3)
  • Consistent threshold evaluation
  • Initial status assessment

Read the full file on GitHub · 616 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 · 616 lines · 56 tokens per session scan A 049a565c6e28

Subscribe to this mod's changes

skill-auditor-v6 is an agent published in the GitHub repository basher83/agent-auditor (5 stars, last pushed 6mo ago), licensed MIT. It adds 56 tokens to every session and 3,841 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.