skill-auditor

skill-auditor is an agent for Claude Code from Vibe-Marketer/plugins-and-skills. It costs 262 tokens per session (1,734 once invoked), scanned A, original, MIT.

A review agent for checking SKILL.md files, the instruction files that define coding-agent skills, against stated best practices.

In plain words
What is it for?
Use it to audit a skill’s structure, rules, references, workflows, and supporting files.
Why use it?
It helps find structural problems, missing references, malformed metadata, and unclear or noncompliant instructions before a skill is used.

Agent for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: model in frontmatter; mentions subagents; mentions Claude Code.

Part of the create-plugins plugin — 12 skills, 6 commands, 9 agents shipped together

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/vibe-marketer/plugins-and-skills/skill-auditor
Clone the repo
git clone --depth 1 https://github.com/Vibe-Marketer/plugins-and-skills

Made for: Claude Code.

Or install create-plugins, the plugin that ships this one along with the rest of its 12 skills, 6 commands, 9 agents.

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

README.md
[![agentmods](https://agentmods.dev/badge/agents/vibe-marketer/plugins-and-skills/skill-auditor.svg)](https://agentmods.dev/agents/vibe-marketer/plugins-and-skills/skill-auditor)
Your own site
<a href="https://agentmods.dev/agents/vibe-marketer/plugins-and-skills/skill-auditor"><img src="https://agentmods.dev/badge/agents/vibe-marketer/plugins-and-skills/skill-auditor.svg" alt="Measured on agentmods" height="20"></a>
Per session 262 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,734 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 5.1 $0.00262 $0.01734
Opus 5 $0.00131 $0.00867
Sonnet 5 $0.00052 $0.00347
Haiku 4.5 $0.00026 $0.00173

Measured 5d ago against content hash 31e9b0970c2d, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

skill-auditor 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 5d 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.

create-plugins/agents/skill-auditor.md · 191 lines

How it starts

The opening of the file, as written. The whole thing — 191 lines — stays where its author put it; the contents beside it link to each section on GitHub.

<critical_workflow> MANDATORY: Read best practices FIRST, before auditing:

  1. Read @shared/rules/CORE-PRINCIPLES.md for XML structure, conciseness, progressive disclosure
  2. Read @shared/rules/ANTI-PATTERNS.md for common mistakes to detect
  3. Read @shared/rules/XML-TAG-GUIDE.md for required/conditional tags and nesting rules
  4. Handle edge cases:
    • If reference files are missing or unreadable, note in findings under "Configuration Issues"
    • If YAML frontmatter is malformed, flag as critical issue
    • If skill references external files that don't exist, flag as critical issue
    • If skill is <100 lines, note as "simple skill" and evaluate accordingly
  5. Read the skill files (SKILL.md and any references/, workflows/, scripts/ subdirectories)
  6. Evaluate against best practices from steps 1-3

Use ACTUAL patterns from shared rules, not memory. </critical_workflow>

<evaluation_areas>

  • name: Lowercase-with-hyphens, max 64 chars, matches directory name, follows verb-noun convention
  • description: Max 1024 chars, third person, includes BOTH what it does AND when to use it, no XML tags in description

<contextual_judgment> Apply judgment based on skill complexity:

Simple skills (single task, <100 lines):

  • Required tags only is appropriate -- don't flag missing conditional tags
  • Minimal examples acceptable
  • Light validation sufficient

Complex skills (multi-step, external APIs, security concerns):

  • Missing conditional tags (security_checklist, validation, error_handling) is a real issue
  • Comprehensive examples expected
  • Thorough validation required

Delegation skills (invoke subagents):

  • Success criteria can focus on invocation success
  • Pre-validation may be redundant if subagent validates

Read the full file on GitHub · 191 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. 5d ago First seen · 191 lines · 262 tokens per session scan A 31e9b0970c2d

Subscribe to this mod's changes

skill-auditor is an agent published in the GitHub repository Vibe-Marketer/plugins-and-skills (2 stars, last pushed 6mo ago), licensed MIT. It adds 262 tokens to every session and 1,734 once invoked, about $0.0013 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.