audit-claude-components

audit-claude-components is a command for Claude Code from dykyi-roman/awesome-claude-code. It costs 58 tokens per session (8,128 once invoked), scanned A, original, MIT.

A review command for a project's `.claude` folder, which stores Claude Code configuration such as commands, agents, skills, hooks, and rules. It checks how these parts are organised and work together.

In plain words
What is it for?
Use it to inspect Claude Code configuration, verify how components interact, and plan refactoring or cleanup.
Why use it?
It helps find broken references, overlapping responsibilities, poor boundaries, and configuration patterns that may cause inconsistent agent behaviour.

Command for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: model in frontmatter; reads .claude/ paths; mentions CLAUDE.md.

Part of the acc plugin — 101 skills, 26 commands, 68 agents, 1 hook shipped together

Good fit Use it to inspect Claude Code configuration, verify how components interact, and plan refactoring or cleanup.

Compare 6 commands from other repositories ↓
Install with agentmods
npx agentmods add commands/dykyi-roman/awesome-claude-code/audit-claude-components
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/dykyi-roman/awesome-claude-code

Made for: Claude Code.

Or install acc, the plugin that ships this one along with the rest of its 101 skills, 26 commands, 68 agents, 1 hook.

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-claude-components

README.md
[![agentmods](https://agentmods.dev/badge/commands/dykyi-roman/awesome-claude-code/audit-claude-components/github.svg)](https://agentmods.dev/commands/dykyi-roman/awesome-claude-code/audit-claude-components)
Your own site
<a href="https://agentmods.dev/commands/dykyi-roman/awesome-claude-code/audit-claude-components"><img src="https://agentmods.dev/badge/commands/dykyi-roman/awesome-claude-code/audit-claude-components/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for audit-claude-components

Your own site · 80×15
<a href="https://agentmods.dev/commands/dykyi-roman/awesome-claude-code/audit-claude-components"><img src="https://agentmods.dev/badge/commands/dykyi-roman/awesome-claude-code/audit-claude-components.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 58 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 8,128 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 $0.00058 $0.08128
Opus 5 $0.00029 $0.04064
Sonnet 5 $0.00012 $0.01626
Haiku 4.5 $0.00006 $0.00813

Measured 5d ago against content hash 7e68f239e507, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

audit-claude-components 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.

commands/audit-claude-components.md · 1,003 lines

How it starts

The opening of the file, as written. The whole thing — 1,003 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Claude Code Configuration Audit

Perform a comprehensive audit of the .claude/ folder in the current project.

Input Parsing

Parse $ARGUMENTS to extract level and optional meta-instructions:

Format: [level] [-- <meta-instructions>]

Arguments:
- level: Audit depth - quick|standard|deep (optional, default: standard)
- -- meta-instructions: Additional focus areas or filters (optional)

Examples:
- /acc:audit-claude-components
- /acc:audit-claude-components deep
- /acc:audit-claude-components quick
- /acc:audit-claude-components -- focus on God-Agent detection
- /acc:audit-claude-components deep -- check only commands
- /acc:audit-claude-components -- level:deep (backward compatible)

Parsing rules:

  1. Split $ARGUMENTS by -- (space-dash-dash-space)
  2. First part = positional arguments, Second part = meta-instructions
  3. If first positional argument is quick|standard|deep → this is level
  4. Also accept level:quick|standard|deep in meta-instructions (backward compatibility)
  5. Priority: positional > meta-instruction > default (standard)

If meta-instructions provided, adjust audit to:

  • Focus on specific component types (commands/agents/skills)
  • Prioritize specific checks (God-Agent, cross-references, etc.)
  • Skip certain analysis phases

Pre-flight Check

  1. Check if .claude/ folder exists in the current working directory
  2. If missing, skip to Missing Configuration section

Audit Process

Step 1: Scan Structure

Discover all components:

.claude/
├── commands/           # Slash commands (*.md)
├── agents/             # Custom agents (*.md)
├── skills/             # Skills (name/SKILL.md)
├── plans/              # Plan files
├── settings.json       # Project settings
├── settings.local.json # Local settings (gitignored)
├── CLAUDE.md           # Project instructions
└── README.md           # Documentation

Use Glob to find:

  • .claude/commands/*.md
  • .claude/agents/*.md
  • .claude/skills/*/SKILL.md
  • .claude/settings.json
  • .claude/settings.local.json
  • .claude/CLAUDE.md
  • .claude/rules/*.md
  • .claude-plugin/plugin.json
  • CLAUDE.md (project root)
  • CLAUDE.local.md (project root)

Read the full file on GitHub · 1,003 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 · 1,003 lines · 0 tokens per session scan A 7e68f239e507

Subscribe to this mod's changes

audit-claude-components is a command published in the GitHub repository dykyi-roman/awesome-claude-code (96 stars, last pushed 23d ago), licensed MIT. It adds 58 tokens to every session and 8,128 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 2026-09-03.