Skip to main content
skill CX Codex

code-reviewer · nodnarbnitram — Claude Code skill: what it does, how to install

code-reviewer — a review skill that runs a fixed checklist over your code: readability, secrets, error handling, performance, tests. Findings come back sorted by severity.

MIT 298 installs ★ 19 updated 2026-04-20

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

What code-reviewer does

Point it at files and the skill takes over: Read for the contents, Grep for patterns and related code, Glob to pull in neighbouring files. Then it walks the checklist. Five areas get covered: naming and duplication, leaked credentials and injection holes, how errors are caught and logged, performance hot spots, and whether tests hit the edge cases.

Results land in three buckets. Critical means an exploit, data loss or a crash. Warning covers bugs and slow paths. Suggestion is style and readability. Every item carries a file and line number, plus what is wrong and how to fix it.

It reports, it does not patch. The tool set stops at Read, Grep and Glob, so the diff stays yours to write. That is what you want when reviewing someone else's branch, or when the agent has no business touching the repo before a merge.

What it helps with

  • run a pull request through a fixed review checklist
  • spot secrets or API keys left in source files
  • catch SQL injection and XSS before merge
  • rank findings by severity so crashes get fixed first
  • confirm errors are not swallowed silently

Example prompts for the agent

  • Review src/api/user_service.py for injection risks and leaked credentials
  • Go through the changes in api_client.py and list findings under Critical, Warning and Suggestion
  • Run the security checklist over src/auth and give me file and line for each issue

How to install code-reviewer

1Skills CLI (Vercel)

npx skills add nodnarbnitram/claude-code-extensions --skill code-reviewer -a claude-code

2Manually: put the files in place

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

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

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

Questions about code-reviewer

How do I install code-reviewer in Claude Code?

Run npx skills add nodnarbnitram/claude-code-extensions --skill code-reviewer -a claude-code. The skill file lands at ~/.claude/skills/code-reviewer/SKILL.md.

What does code-reviewer do?

It reads the files you name, searches them and the surrounding code, then checks everything against a list covering quality, security, error handling, performance and tests. Feedback is grouped into Critical, Warning and Suggestion.

Can it edit my code?

No. Its allowed tools are Read, Grep and Glob, so it only reads and searches — you apply the fixes.

Source text

SKILL.md · MIT
---
name: code-reviewer
description: Review code for best practices, security issues, and potential bugs. Use when reviewing code changes, checking PRs, analyzing code quality, or performing security audits.
allowed-tools: Read, Grep, Glob
---

# Code Reviewer

Perform comprehensive code reviews focusing on quality, security, and maintainability.

## Instructions

1. Read the target files using the Read tool
2. Search for patterns and related code using Grep
3. Find related files using Glob
4. Analyze code against the review checklist
5. Provide structured feedback with severity levels

## Review Checklist

### Code Quality
- [ ] Code is simple and readable
- [ ] Functions and variables are well-named
- [ ] No duplicated code (DRY principle)
- [ ] Appropriate comments for complex logic
- [ ] Consistent code style

### Security
- [ ] No exposed secrets or API keys
- [ ] Input validation implemented
- [ ] SQL injection prevention
- [ ] XSS prevention for web code
- [ ] Proper authentication/authorization checks

### Error Handling
- [ ] Errors are caught and handled appropriately
- [ ] Meaningful error messages
- [ ] No silent failures
- [ ] Proper logging for debugging

### Performance
- [ ] No obvious performance bottlenecks
- [ ] Efficient algorithms and data structures
- [ ] Appropriate caching where needed
- [ ] Database queries are optimized

### Testing
- [ ] Adequate test coverage
- [ ] Edge cases are tested
- [ ] Tests are readable and maintainable

## Output Format

Organize feedback by severity:

### Critical (Must Fix)
Issues that could cause security vulnerabilities, data loss, or crashes.

### Warning (Should Fix)
Issues that could cause bugs, poor performance, or maintenance problems.

### Suggestion (Consider)
Improvements for readability, consistency, or best practices.

## Example Feedback

```markdown
### Critical
- **SQL Injection vulnerability** in `user_service.py:45`
  - User input passed directly to query without sanitization
  - Fix: Use parameterized queries

### Warning
- **Missing error handling** in `api_client.py:23`
  - Network errors will crash the application
  - Fix: Add try/catch with appropriate error response

### Suggestion
- Consider extracting the validation logic in `validators.py:78-95` into a separate function for reusability
```

© nodnarbnitram · MIT · nodnarbnitram/claude-code-extensions

Similar skills

All skills for Code review and refactoring →

code-reviewer by other authors comes first.

code-reviewer https://github.com/Jeffallan code-reviewer analyzes code diffs and files to spot bugs, security vulnerabilities (SQL injection, XSS), code smells, N+1 queries, and returns a prioritized review report. Use for pull request reviews and code audits. CX Codex +1 7,100installs code-reviewer rmyndharis The code-reviewer Claude Code skill reviews code for security risks, performance issues, and maintainability concerns. Ask it to assess a change or inspect a production configuration. CX Codex +1 104installs code-reviewer Alireza Rezvani code-reviewer reviews pull requests, git diffs, and source files for security vulnerabilities and code smells before merging in Claude Code. CX Codex +1 1,130installs code-reviewer waybarrios code-reviewer is a Claude Code skill that checks code changes for bugs, security issues, and project-rule violations. It covers local diffs, files, and feature-dev review tasks. CX Codex +1 135installs code-reviewer zhaono1 code-reviewer reviews Git diffs and pull requests for security vulnerabilities, logic flaws, test coverage, and code quality. CX Codex +1 760installs audit-project Community audit-project — a Claude Code plugin running multi-agent iterative code review. Sub-agents scan, fix, and re-check until the issue list is empty. ★ 2,003repo stars Agent Governance Reviewer official github Agent Governance Reviewer is a GitHub Copilot subagent that checks AI agent code for safety gaps and missing governance controls. It also helps add policy enforcement, trust scoring, and audit trails. CX Codex +1 ★ 41,430repo stars deep-app-audit frappe deep-app-audit is a Claude Code skill for auditing Frappe apps for security issues, logic errors, and customization defects. Parallel agents check separate code aspects in fresh contexts and compile one report. CX Codex +1 458installs gjalla-code-review gjalla gjalla-code-review reviews PRs and diffs before merge from the perspective of an architect, security analyst, and QA engineer. Groups findings by severity. CX Codex +1 865installs code-review jwynia code-review is a Claude Code skill for finding defects and assessing code quality. It activates on requests to review code, check a PR, or evaluate changes systematically. CX Codex +1 505installs verify OrchestKit verify is a skill that checks whether work is ready to merge by running tests, security and type checks, then assigns a 0–10 score. CX Codex +1 210installs

From the same set6

Project sponsors

Companies that keep this analytics open