skill-audit

skill-audit is a skill for Claude Code from JeonJe/claude-plugins. It costs 67 tokens per session (785 once invoked), scanned A, original, MIT.

A quality checker for Claude skills and commands before they are shared with others. It compares them with Anthropic’s published best practices and reports readiness, safety, and concrete fixes.

In plain words
What is it for?
Use it to audit a skill or command, review its quality, and prepare it for publication.
Why use it?
It helps catch unclear instructions, unsafe behavior, and publishing problems before other people use the skill. By default, it checks only project files unless you explicitly include personal Claude files.

Skill for Claude Code

Written for Claude Code: $ARGUMENTS substitution. Also seen: reads .claude/ paths.

Part of the skill-audit plugin — 1 skill shipped together

Good fit Use it to audit a skill or command, review its quality, and…

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/jeonje/claude-plugins/skill-audit
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 JeonJe/claude-plugins --skill skill-audit
Clone the repo
git clone --depth 1 https://github.com/JeonJe/claude-plugins

Made for: Claude Code.

Or install skill-audit, the plugin that ships this one along with the rest of its 1 skill.

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-audit

README.md
[![agentmods](https://agentmods.dev/badge/skills/jeonje/claude-plugins/skill-audit.svg)](https://agentmods.dev/skills/jeonje/claude-plugins/skill-audit)
Your own site
<a href="https://agentmods.dev/skills/jeonje/claude-plugins/skill-audit"><img src="https://agentmods.dev/badge/skills/jeonje/claude-plugins/skill-audit.svg" alt="Measured on agentmods" height="20"></a>
Per session 67 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 785 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00067 $0.00785
Opus 5 $0.00034 $0.00392
Sonnet 5 $0.00013 $0.00157
Haiku 4.5 $0.00007 $0.00078

Measured 6d ago against content hash ff8791f59aba, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

skill-audit 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 6d 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/skill-audit/skills/skill-audit/SKILL.md · 77 lines

How it starts

The opening of the file, as written. The whole thing — 77 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Skill Audit

Audit Claude skills and commands before sharing. Applies Anthropic skill best practices and reports quality, safety, and publish readiness.

Source of truth:

Input

  • $ARGUMENTS: Optional target name and/or flags.

Argument Parsing Rules

Parse $ARGUMENTS in this order:

  1. Detect supported flags first.
  2. Remaining non-flag token (if any) is treated as target name.
  3. If multiple non-flag tokens exist, join with spaces as the target name.

Supported flags:

  • --include-user-home: Include ~/.claude/* paths in audit scope.
  • --project-only: Force project-only scope (default).

Conflict handling:

  • If both flags present, --project-only wins.
  • Unknown flags MUST be reported as warnings and ignored.

Scope Defaults

Default behavior is privacy-safe for sharing prep:

  • Scan project-local paths only: .claude/skills/, .claude/commands/

Optional expanded scan (explicit opt-in):

  • --include-user-home: also scan ~/.claude/skills/, ~/.claude/commands/

Use Cases

Input Scope Output
/skill-audit All project skills/commands Summary table + prioritized fixes
/skill-audit my-skill Single target (deep audit) Detailed checklist + rewrite suggestions
/skill-audit --include-user-home Project + user-level paths Cross-scope quality report + conflict notes

Files

  • read: rubric/scoring.md (6-category rubric + scoring consistency rules)
  • read: rubric/security-checks.md (security/sharing checks + anti-patterns)
  • read: templates/output-format.md (output format template)

Grades

  • A (90-100): Ready to share
  • B (80-89): Share after minor fixes
  • C (70-79): Needs targeted rewrite
  • D (<70): Redesign before sharing

Workflow

  1. Discover targets from selected scope.
  2. Detect naming/trigger collisions.
  3. Read rubric/scoring.md and score with the 6-category rubric.
  4. Apply anti-pattern deductions from rubric/security-checks.md.
  5. Run security/share checks.
  6. Verify score bounds (0-100). If out of range, clamp to 0-100 and report calculation error.
  7. Report findings using templates/output-format.md.
  8. If user requests fixes: apply → re-audit → verify score improved → repeat until grade A or user satisfied.

Read the full file on GitHub · 77 lines

Files

What ships with it

3 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. 6d ago First seen · 77 lines · 67 tokens per session scan A ff8791f59aba

Subscribe to this mod's changes

skill-audit is a skill published in the GitHub repository JeonJe/claude-plugins (3 stars, last pushed 1mo ago), licensed MIT. It adds 67 tokens to every session and 785 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.