home/coding/audit-prompt-2

Audit Prompt

GPTClaudeDeepSeek··1,303 copies·updated 2026-07-14
audit-prompt-2.prompt
# Audit Your Claude Code Setup

> A self-contained prompt that audits your Claude Code configuration — project memory, rules hygiene, skills, agents/commands, security, MCP, workflow commands, and freshness — in one pass.

**Author**: [Florian BRUNIAUX](https://github.com/FlorianBruniaux) | Founding Engineer [@Méthode Aristote](https://methode-aristote.fr)

**Reference**: [The Ultimate Claude Code Guide](https://github.com/FlorianBruniaux/claude-code-ultimate-guide/blob/main/guide/ultimate-guide.md)

---

## 1. What This Does

This prompt turns Claude into an **audit orchestrator** across 8 weighted dimensions (100 pts total). It runs a fast bash inventory, then delegates each domain to a specialized skill or command if one is installed, falling back to inline checks when not.

| What it audits | How |
|---|---|
| Memory & Context (CLAUDE.md, rules, token budget) | Delegates to `/token-audit` if installed, otherwise bash estimate |
| Rules Hygiene (`.claude/rules/`, `paths:` validity) | Delegates to `/eval-rules` if installed, otherwise bash scan |
| Skills Quality (frontmatter, effort, allowed-tools) | Delegates to `/eval-skills` if installed, otherwise quick check |
| Agents/Commands Quality (16 criteria, grades A-F) | Delegates to `/audit-agents-skills` if installed, otherwise check |
| Security Posture (permissions, hooks, sandbox) | Delegates to `/security-check` if installed, otherwise bash check |
| MCP Ecosystem (servers, DB risk, version safety) | Inline bash (no dedicated skill needed) |
| Workflow Commands (/investigate, /qa, /canary…) | Inline bash scan |
| Freshness & Best Practices (stale refs, cache bugs) | Inline bash + pattern checks |

**What this does NOT do**: replace the deep-dive tools it delegates to. Use `/security-audit`, `/token-audit`, `/eval-rules` directly when you want full detail on a specific dimension.

**Time**: ~5-8 min if all audit skills are installed, ~3-4 min in fallback mode.

**Important**: Claude will NOT make any changes without your explicit approval.

---

## 2. Who This Is For

| Level | What You'll Get |
|-------|-----------------|
| **Beginner** | Discover what you're missing and get starter templates |
| **Intermediate** | Identify optimization opportunities and advanced patterns |
| **Power User** | Validate your setup and find edge cases to polish |

**Prerequisites**:
- Claude Code installed and working
- A project directory to analyze (or just global config)
- Bash shell (native on macOS/Linux, WSL on Windows)

**Optional** (richer results): `/token-audit`, `/eval-rules`, `/eval-skills`, `/audit-agents-skills`, `/security-check` installed. See Section 8 for install commands.

---

## 3. How to Use It

### Step 1: Copy the Prompt

Copy everything inside the code block in [Section 4](#4-the-prompt) below.

### Step 2: Run Claude Code

when to use it

Community prompt sourced from the open-source GitHub repo FlorianBruniaux/claude-code-ultimate-guide (CC-BY-SA-4.0). A "Audit Prompt" style prompt — adapt the placeholders and specifics to your task. Imported as-is and not independently retested here, so check the output before relying on it.

tags

codingcommunitydeveloper

source

FlorianBruniaux/claude-code-ultimate-guide · CC-BY-SA-4.0