audit-skills

audit-skills is a command for Claude Code from kumaran-is/claude-code-onboarding. It costs 88 tokens per session (1,920 once invoked), scanned A, original, MIT.

A health-audit command for reviewing skills and software agents against a fixed set of quality and readiness criteria.

In plain words
What is it for?
Use it to score skills and agents, assign production-readiness grades, and create a prioritized list of fixes.
Why use it?
It reveals missing instructions, unclear triggers, overlap, and other weaknesses that can make add-ons unreliable.

Command for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: reads .claude/ paths.

Good fit Use it to score skills and agents, assign production-readiness grades, and create a prioritized list of fixes.

Compare 6 commands from other repositories ↓
Install with agentmods
npx agentmods add commands/kumaran-is/claude-code-onboarding/audit-skills
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.

Clone the repo
git clone --depth 1 https://github.com/kumaran-is/claude-code-onboarding

Made for: Claude Code.

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 audit-skills

README.md
[![agentmods](https://agentmods.dev/badge/commands/kumaran-is/claude-code-onboarding/audit-skills.svg)](https://agentmods.dev/commands/kumaran-is/claude-code-onboarding/audit-skills)
Your own site
<a href="https://agentmods.dev/commands/kumaran-is/claude-code-onboarding/audit-skills"><img src="https://agentmods.dev/badge/commands/kumaran-is/claude-code-onboarding/audit-skills.svg" alt="Measured on agentmods" height="20"></a>
Per session 88 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,920 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 $0.00088 $0.01920
Opus 5 $0.00044 $0.00960
Sonnet 5 $0.00018 $0.00384
Haiku 4.5 $0.00009 $0.00192

Measured 4d ago against content hash 616f930521e9, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

audit-skills 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.

.claude/commands/audit-skills.md · 144 lines

How it starts

The opening of the file, as written. The whole thing — 144 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Audit all skills in .claude/skills/ and agents in .claude/agents/. Score each against the 16-criterion rubric below. Output a graded report with prioritised fixes.

Scoring Rubric (16 criteria × 2 points = 32 points max)

Each criterion scores 0 (fail), 1 (partial), or 2 (pass).

Category A — Iron Law & Trigger (8 pts)

# Criterion 2 (pass) 1 (partial) 0 (fail)
A1 Iron Law present ## Iron Law, **Iron Law:**, or > **Iron Law:** found in body Mandatory action present but not labelled Iron Law Absent
A2 Description has CSO trigger words Contains specific trigger verbs: "Use when", "Triggers when", "Invoke for" + concrete scenario Has trigger words but vague ("use for general...") Missing or < 10 words
A3 Trigger is unambiguous Would NOT fire on tasks outside its domain Could plausibly fire on 2+ unrelated task types Fires on everything / too broad
A4 No overlap with peer skills No functional duplication with another skill in .claude/skills/ Minor overlap, clearly differentiated Significant duplication — consolidate

Category B — Structure & Size (8 pts)

# Criterion 2 (pass) 1 (partial) 0 (fail)
B1 Frontmatter complete name, description, allowed-tools all present 2 of 3 present Missing or malformed frontmatter
B2 Body ≤ 500 lines ≤ 450 lines 451–500 lines > 500 lines
B3 Progressive disclosure Content ordered: summary → key rules → examples → reference Mostly ordered, minor issues Dumps everything upfront with no structure
B4 References section references/ dir present OR inline links to MCP/docs Referenced in body but dir missing No references anywhere

Category C — Content Quality (8 pts)

# Criterion 2 (pass) 1 (partial) 0 (fail)
C1 MCP server named explicitly Specific MCP server listed (e.g. dart-mcp-server, context7, angular-cli) Generic "use MCP" without naming which No MCP reference for a tech that has one
C2 Code examples present ≥ 1 concrete code block showing correct usage Examples described in prose only No examples
C3 Anti-patterns documented ≥ 1 explicit "don't do this" section or callout Anti-patterns implied but not explicit Absent
C4 Stack version pinned Specific version referenced (e.g. "NestJS 11.x", "Flutter 3.41.x") Stack named without version No stack version

Read the full file on GitHub · 144 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 · 144 lines · 0 tokens per session scan A 616f930521e9

Subscribe to this mod's changes

audit-skills is a command published in the GitHub repository kumaran-is/claude-code-onboarding (35 stars, last pushed 2mo ago), licensed MIT. It adds 88 tokens to every session and 1,920 once invoked, about $0.0004 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 2026-09-03.