A read-only check of a project's Claude Code setup, including context files, permissions, hooks, status-line scripts, custom skills, and specialized agents. It reports missing or incomplete configuration without changing files.

Use it to inspect Claude Code configuration and report the status of required files, permissions, automation, skills, hooks, and agents.

It helps find configuration gaps and safety issues before they cause inconsistent agent behavior or leave important project guidance unused.

audit — Skill for Claude Code and Codex by fschifone: A read-only check of a project's Claude Code setup…

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 skills/fschifone/claude-setup-wizard/audit

Any agent

npx skills add fschifone/claude-setup-wizard --skill audit

Clone the repo

git clone --depth 1 https://github.com/fschifone/claude-setup-wizard

Made for: Claude Code, Codex.

Or install setup-wizard, the plugin that ships this one along with the rest of its 3 skills.

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/skills/fschifone/claude-setup-wizard/audit.svg)](https://agentmods.dev/skills/fschifone/claude-setup-wizard/audit)

Your own site

<a href="https://agentmods.dev/skills/fschifone/claude-setup-wizard/audit"><img src="https://agentmods.dev/badge/skills/fschifone/claude-setup-wizard/audit.svg" alt="Measured on agentmods" height="20"></a>

Per session 15 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 901 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	$0.00015	$0.00901
Opus 5	$0.00008	$0.00451
Sonnet 5	$0.00003	$0.00180
Haiku 4.5	$0.00002	$0.00090

Measured 4d ago against content hash fdcf4be9d099, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, 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 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.

plugins/setup-wizard/skills/audit/SKILL.md · 98 lines

How it starts

The opening of the file, as written. The whole thing — 98 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Claude Config Audit

Run a read-only audit of this project's Claude Code configuration and report gaps. Do not write any files.

Checks

Inspect the filesystem and report the status of each item:

Context files

CLAUDE.md — project context (required)
CLAUDE.local.md — personal overrides (gitignored)
<area>/CLAUDE.md — nested context for sub-modules

Configuration

.claude/settings.json — permissions, hooks, statusLine
.claude/settings.json has permissions.allow entries
.claude/settings.json has permissions.deny entries (safety)
.claude/settings.json has statusLine configured
.claude/settings.json has hooks configured

Automation

.claude/skills/*/SKILL.md — custom skills (slash commands, subagents)
.claude/hooks/*.sh — executable hook scripts
.claude/statusline.sh — executable status line script

Specialized agent team (informational — not scored)

.claude/agents/*.md — role-specialized subagents
For each agent found, report: name, model, and whether tools is restricted (read-only review/audit roles should NOT have Write/Edit).
A description without an explicit trigger phrase (e.g. no "Use when…" or "MUST BE USED…") is flagged ⚠ — Claude relies on the description to auto-delegate, so vague descriptions mean the agent rarely fires.

Safety

.gitignore protects CLAUDE.local.md
.gitignore protects .env*
.gitignore protects .claude/settings.local.json
.gitignore protects .claude/logs/

Token efficiency

.claude/rules/*.md — scoped rules (load only when relevant files touched)
CLAUDE.md is under 150 lines (larger files waste tokens every turn)
No duplicated rules between root CLAUDE.md and nested CLAUDE.md files

Integrations

.mcp.json — MCP server config (optional)

Output format

Print a single report like this:

CLAUDE CONFIG AUDIT

Present:
  ✓ CLAUDE.md
  ✓ .claude/settings.json

Missing:
  ✗ .claude/settings.json — no permissions or hooks; Claude runs ungated
  ✗ Status line — no context/token visibility during sessions

Weak:
  ⚠ CLAUDE.md — missing "Commands" section; Claude will guess how to build/test
  ⚠ .gitignore — doesn't protect CLAUDE.local.md (secrets risk)

Token efficiency:
  ⚠ CLAUDE.md is 210 lines — consider moving scoped rules to .claude/rules/
  ✓ Scoped rules in .claude/rules/ — good separation

Agent team (informational):
  ✓ .claude/agents/code-reviewer-critical.md — opus, read-only (no Edit/Write)
  ⚠ .claude/agents/my-helper.md — description has no trigger phrase ("Use when…")

Score: <X>/10

Next: /setup-wizard --existing
      /setup-wizard agents     — add or regenerate a specialized agent team

Read the full file on GitHub · 98 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.

4d ago First seen · 98 lines · 15 tokens per session scan A fdcf4be9d099

Subscribe to this mod's changes

audit is a skill published in the GitHub repository fschifone/claude-setup-wizard (2 stars, last pushed 4mo ago), licensed MIT. It adds 15 tokens to every session and 901 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

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

chronicle

Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…

microsoft/vscode · 72 tokens

imagegen

Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…

openai/codex · 113 tokens

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens