Skip to main content
skill CX Codex

code-auditor — Claude Code skill: audit a whole codebase

Walks a repository through architecture, code quality, security, performance, testing and maintainability, then hands back a report. Useful when you inherit code and need to know what hurts.

Install into Claude Code · Skills CLI (Vercel) All methods and platforms ↓
npx skills add mhattingpete/claude-skills-marketplace --skill code-auditor -a claude-code
Open on GitHub

What code-auditor does

The skill explores the repo and returns a health score, a count of critical issues and the top three priorities. Findings are grouped by category and tagged High, Medium or Low, each with a file:line reference, the impact and a recommendation. The report closes with an action plan split by effort and metrics: files analyzed, lines of code, test coverage and complexity hotspots.

Six areas get checked. Architecture covers structure, design patterns, module boundaries and dependencies. Quality looks at cyclomatic complexity, duplication, naming, docs and anti-patterns. Security covers OWASP Top 10, input validation, auth, secrets and vulnerable dependencies. Performance covers algorithmic complexity, database queries, memory, caching and resource leaks. Testing weighs coverage, scenario quality and the unit-to-integration balance. Maintainability covers technical debt, coupling and how easy future changes will be.

It works through an Explore agent plus Grep, Glob, Read and Bash for linters and coverage tools. Pick the depth up front: Quick runs 15–30 minutes on critical issues only, Standard 30–60 minutes across all six dimensions, Deep 60+ minutes with detailed examples. You can narrow it to one area too — security only, performance only, testing only. One caveat: the report leans on static analysis, so with no linters or coverage tooling configured some metrics come back empty.

What it helps with

  • size up an unfamiliar repo before joining the project
  • rank technical debt so you know what to fix first
  • check code against the OWASP Top 10
  • spot which test scenarios are missing
  • list complexity hotspots by cyclomatic score

Example prompts for the agent

  • audit the codebase in this repo
  • run a security-only audit
  • quick architecture review, 15 minutes

How to install code-auditor

1Skills CLI (Vercel)

npx skills add mhattingpete/claude-skills-marketplace --skill code-auditor -a claude-code

2Manually: put the files in place

~/.claude/skills/code-auditor/SKILL.md

Copy the whole skill folder; for one project use .claude/skills/code-auditor/

Step by step, with commands for each platform: How to install skills in Claude Code: five ways

Questions about code-auditor

How do I install code-auditor in Claude?

Run npx skills add mhattingpete/claude-skills-marketplace --skill code-auditor -a claude-code. The skill file lands at ~/.claude/skills/code-auditor/SKILL.md.

What does code-auditor do?

It runs the codebase through six dimensions and produces a report: a health score, critical issues, per-category findings with file:line references and a prioritised action plan.

Can I limit the audit to one area?

Yes. It supports security-only, performance-only and testing-only modes, plus a quick architecture review.

Source text

SKILL.md · Apache-2.0
---
name: code-auditor
description: Performs comprehensive codebase analysis covering architecture, code quality, security, performance, testing, and maintainability. Use when user wants to audit code quality, identify technical debt, find security issues, assess test coverage, or get a codebase health check.
---

# Code Auditor

Comprehensive codebase analysis covering architecture, code quality, security, performance, testing, and maintainability.

## When to Use

- "audit the code"
- "analyze code quality"
- "check for issues"
- "review the codebase"
- "find technical debt"
- "security audit"
- "performance review"

## What It Analyzes

### 1. Architecture & Design
- Overall structure and organization
- Design patterns in use
- Module boundaries and separation of concerns
- Dependency management
- Architectural decisions and trade-offs

### 2. Code Quality
- Complexity hotspots (cyclomatic complexity)
- Code duplication (DRY violations)
- Naming conventions and consistency
- Documentation coverage
- Code smells and anti-patterns

### 3. Security
- Common vulnerabilities (OWASP Top 10)
- Input validation and sanitization
- Authentication and authorization
- Secrets management
- Dependency vulnerabilities

### 4. Performance
- Algorithmic complexity issues
- Database query optimization
- Memory usage patterns
- Caching opportunities
- Resource leaks

### 5. Testing
- Test coverage assessment
- Test quality and effectiveness
- Missing test scenarios
- Testing patterns and practices
- Integration vs unit test balance

### 6. Maintainability
- Technical debt assessment
- Coupling and cohesion
- Ease of future changes
- Onboarding friendliness
- Documentation quality

## Approach

1. **Explore** using Explore agent (thorough mode)
2. **Identify patterns** with Grep and Glob
3. **Read critical files** for detailed analysis
4. **Run static analysis tools** if available
5. **Synthesize findings** into actionable report

## Thoroughness Levels

- **Quick** (15-30 min): High-level, critical issues only
- **Standard** (30-60 min): Comprehensive across all dimensions
- **Deep** (60+ min): Exhaustive with detailed examples

## Output Format

```markdown
# Code Audit Report

## Executive Summary
- Overall health score
- Critical issues count
- Top 3 priorities

## Findings by Category

### Architecture & Design
#### 🔴 High Priority
- [Finding with file:line reference]
  - Impact: [description]
  - Recommendation: [action]

#### 🟡 Medium Priority
...

### [Other categories]

## Prioritized Action Plan
1. Quick wins (< 1 day)
2. Medium-term improvements (1-5 days)
3. Long-term initiatives (> 5 days)

## Metrics
- Files analyzed: X
- Lines of code: Y
- Test coverage: Z%
- Complexity hotspots: N
```

## Tools Used

- **Task (Explore agent)**: Thorough codebase exploration
- **Grep**: Pattern matching for issues
- **Glob**: Find files by type/pattern
- **Read**: Detailed file analysis
- **Bash**: Run linters, coverage tools

## Success Criteria

- Comprehensive coverage of all six dimensions
- Specific file:line references for all findings
- Severity/priority ratings (Critical/High/Medium/Low)
- Actionable recommendations (not just observations)
- Estimated effort for fixes
- Both quick wins and long-term improvements

## Integration

- **feature-planning**: Plan technical debt reduction
- **test-fixing**: Address test gaps identified
- **project-bootstrapper**: Set up quality tooling

## Configuration

Can focus on specific areas:
- Security-only audit
- Performance-only audit
- Testing-only assessment
- Quick architecture review

© mhattingpete · Apache-2.0 · mhattingpete/claude-skills-marketplace

Similar skills

Everything for Code review and refactoring →

From the same set7

Project sponsors

Companies that keep this analytics open
Gold sponsor

Impressions, clicks and code copies — open statistics. We keep the numbers public for the same reason NeBlask itself is public. Become a sponsor