skill-audit

A command for reviewing a skill directory against the Agent Skills standard and related platform rules.

In plain words
What is it for?
Use it to run mechanical checks, assess the skill’s purpose and entry point, inspect evaluations and distribution details, and report each result with file-and-line evidence.
Why use it?
It produces one evidence-based gap report before any changes are made, so missing requirements are visible and fixes can be planned safely.

Command

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 commands/ssheleg/make-skill/skill-audit
Clone the repo
git clone --depth 1 https://github.com/ssheleg/make-skill
Per session 26 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 305 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 $0.00026 $0.00305
Opus 5 $0.00013 $0.00152
Sonnet 5 $0.00005 $0.00061
Haiku 4.5 $0.00003 $0.00030

Measured 2d ago against content hash 3d281657b832, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, 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 2d 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/make-skill/commands/skill-audit.md · 31 lines

What it actually says

Audit the skill at $ARGUMENTS (default: the skill directory in the current working directory, or every skills/*/ under plugins/*/ if this is a plugin repo).

  1. Run the bundled auditor — it does the mechanical half deterministically. This plugin puts it on your PATH:

    make-skill-audit <skill-dir> --house
    

    No python3? The wrapper says so and exits 2. Record the mechanical items as NOT-RUN with that reason and check them by hand from the spec reference — never as PASS.

  2. Then work the judgement half from ${CLAUDE_PLUGIN_ROOT}/skills/make-skill/references/retrofit.md — one job, entry point, evaluations, distribution, repo meta. The script cannot answer those. Read the file; do not reconstruct it from memory.

  3. Report one gap table: PASS / GAP / NOT-RUN per item, each with file:line or the command output that proves it. End with exactly ONE suggested next action.

Do not fix anything until the table is reported.

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. 2d ago First seen · 31 lines · 26 tokens per session scan A 3d281657b832

Subscribe to this mod's changes

skill-audit is a command published in the GitHub repository ssheleg/make-skill (3 stars, last pushed 2d ago), licensed MIT. It adds 26 tokens to every session and 305 once invoked, about $0.0001 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.