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.
npx agentmods add skills/nodnarbnitram/claude-code-extensions/code-reviewernpx skills add nodnarbnitram/claude-code-extensions --skill code-reviewergit clone --depth 1 https://github.com/nodnarbnitram/claude-code-extensionsWhat 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 | $0.00036 | $0.00508 |
| Opus 5 | $0.00018 | $0.00254 |
| Sonnet 5 | $0.00007 | $0.00102 |
| Haiku 4.5 | $0.00004 | $0.00051 |
Grade A, and why
code-reviewer 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 2d 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.
How it starts
The opening of the file, as written. The whole thing — 81 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Code Reviewer
Perform comprehensive code reviews focusing on quality, security, and maintainability.
Instructions
- Read the target files using the Read tool
- Search for patterns and related code using Grep
- Find related files using Glob
- Analyze code against the review checklist
- 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
### 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
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.
- 2d ago First seen · 81 lines · 36 tokens per session scan A df444a49ba9c
code-reviewer is a skill published in the GitHub repository nodnarbnitram/claude-code-extensions (16 stars, last pushed 4mo ago), licensed MIT. It adds 36 tokens to every session and 508 once invoked, about $0.0002 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 2026-08-30.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…
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…
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…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…