A command that checks Claude Code agents, skills, commands, and hooks for quality, security, compliance, and schema issues.

Use it to audit agents, skills, commands, or hooks, either separately or together. Use deep analysis when reviewing one component in detail.

It helps find problems across one component type or the whole project, and can give detailed scores and improvement suggestions for a specific component.

audit — Command for coding agents by C0ntr0lledCha0s: A command that checks Claude Code agents, skills, commands…

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/c0ntr0lledcha0s/claude-code-plugin-automations/audit

Clone the repo

git clone --depth 1 https://github.com/C0ntr0lledCha0s/claude-code-plugin-automations

Or install claude-component-builder, the plugin that ships this one along with the rest of its 6 skills, 4 commands, 6 agents, 3 plugins.

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.

README.md

[![agentmods](https://agentmods.dev/badge/commands/c0ntr0lledcha0s/claude-code-plugin-automations/audit.svg)](https://agentmods.dev/commands/c0ntr0lledcha0s/claude-code-plugin-automations/audit)

Your own site

<a href="https://agentmods.dev/commands/c0ntr0lledcha0s/claude-code-plugin-automations/audit"><img src="https://agentmods.dev/badge/commands/c0ntr0lledcha0s/claude-code-plugin-automations/audit.svg" alt="Measured on agentmods" height="20"></a>

Per session 11 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 1,320 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.

Model	Per session	Once invoked
Fable 5.1	$0.00011	$0.01320
Opus 5	$0.00005	$0.00660
Sonnet 5	$0.00002	$0.00264
Haiku 4.5	$0.00001	$0.00132

Measured 5d ago against content hash cd2940b63ca1, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

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 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.

claude-component-builder/commands/audit.md · 212 lines

How it starts

The opening of the file, as written. The whole thing — 212 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Audit Components

Audit Claude Code components for quality, security, and schema compliance.

Arguments:

$1 (optional): Component type OR --all OR --deep
- Types: agent, skill, command, hook - audit all of that type
- --all: Audit all component types (default if omitted)
- --deep: Deep single-component analysis with scoring and recommendations
$2 (required for --deep): Path to specific component

Full arguments: $ARGUMENTS

Workflow

Single Type Audit

/claude-component-builder:audit agent
    ↓
Task → agent-builder
    ↓
Audit all agents in project

Full Audit (--all)

/claude-component-builder:audit --all
    ↓
Parallel Task invocations
    ↓
├─ agent-builder: Audit agents
├─ skill-builder: Audit skills
├─ command-builder: Audit commands
└─ hook-builder: Audit hooks
    ↓
Consolidated report

Deep Single-Component Analysis (--deep)

/claude-component-builder:audit --deep agents/code-reviewer.md
    ↓
Detect type → agent
    ↓
Task → agent-builder: "Deep quality analysis"
    ↓
Detailed scoring + recommendations

Audit Categories

Agents

Schema compliance
Naming conventions
Tool permissions
Model selection
Content quality

Skills

Directory structure
No model field (critical)
{baseDir} usage
Auto-invoke triggers
Resource organization

Commands

Model format (version alias, not short)
Argument documentation
Security (Bash validation)
Description clarity

Hooks

Security (7 categories)
Matcher specificity
JSON schema
Script validation

Examples

Audit All Components

/claude-component-builder:audit --all

Audit Only Agents

/claude-component-builder:audit agent

Audit Only Skills

/claude-component-builder:audit skill

Audit Only Commands

/claude-component-builder:audit command

Audit Only Hooks

/claude-component-builder:audit hook

Deep Analysis of Single Component

/claude-component-builder:audit --deep agents/code-reviewer.md
/claude-component-builder:audit --deep skills/building-agents/
/claude-component-builder:audit --deep commands/validate.md

Read the full file on GitHub · 212 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.

5d ago First seen · 212 lines · 11 tokens per session scan A cd2940b63ca1

Subscribe to this mod's changes

audit is a command published in the GitHub repository C0ntr0lledCha0s/claude-code-plugin-automations (3 stars, last pushed 6mo ago), licensed MIT. It adds 11 tokens to every session and 1,320 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.

Building agents Security

audit