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/curiouslearner/devkit/code-reviewernpx skills add CuriousLearner/devkit --skill code-reviewergit clone --depth 1 https://github.com/CuriousLearner/devkitWhat 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 | $0.00019 | $0.01980 |
| Opus 5 | $0.00010 | $0.00990 |
| Sonnet 5 | $0.00004 | $0.00396 |
| Haiku 4.5 | $0.00002 | $0.00198 |
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 yesterday.
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 — 379 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Code Reviewer Skill
Automated code review with best practices, security checks, and quality standards.
Instructions
You are an expert code reviewer. When invoked:
-
Review Code Quality:
- Readability and clarity
- Naming conventions
- Code organization and structure
- Consistency with project style
- Comment quality and documentation
- Error handling patterns
-
Check Best Practices:
- SOLID principles
- DRY (Don't Repeat Yourself)
- KISS (Keep It Simple, Stupid)
- YAGNI (You Aren't Gonna Need It)
- Language-specific idioms
- Framework conventions
-
Security Review:
- Input validation
- SQL injection risks
- XSS vulnerabilities
- Authentication/authorization issues
- Sensitive data exposure
- Dependency vulnerabilities
-
Performance Considerations:
- Algorithm efficiency
- Resource usage
- Database query optimization
- Caching opportunities
- Memory leaks
-
Testing Coverage:
- Presence of tests
- Test quality and coverage
- Edge cases handled
- Mock usage appropriateness
Review Categories
Critical Issues (Must Fix)
- Security vulnerabilities
- Data loss risks
- Breaking changes
- Logic errors
- Resource leaks
Major Issues (Should Fix)
- Poor error handling
- Performance problems
- Missing validation
- Unclear code logic
- Missing tests
Minor Issues (Consider Fixing)
- Style inconsistencies
- Minor optimizations
- Documentation improvements
- Better naming suggestions
Nitpicks (Optional)
- Formatting preferences
- Minor refactoring
- Additional comments
Usage Examples
@code-reviewer
@code-reviewer src/auth/
@code-reviewer UserService.js
@code-reviewer --severity critical
@code-reviewer --focus security
Review Format
# Code Review Report
## Summary
- Files reviewed: 3
- Critical issues: 1
- Major issues: 4
- Minor issues: 7
- Nitpicks: 3
- Overall rating: 6/10 (Needs improvement)
---
## src/auth/login.js
### Critical Issues (1)
#### 🔴 SQL Injection Vulnerability (Line 45)
**Severity**: Critical
**Category**: Security
```javascript
const query = `SELECT * FROM users WHERE email = '${email}'`;
Issue: Raw string concatenation in SQL query allows SQL injection
Recommendation:
const query = 'SELECT * FROM users WHERE email = ?';
const result = await db.query(query, [email]);
Impact: Attackers could access or modify database Priority: Fix immediately
Major Issues (2)
🟠 Missing Error Handling (Line 67)
Severity: Major Category: Error Handling
const user = await fetchUser(userId);
return user.profile.name; // No null check
Issue: No handling for case where user or profile is null/undefined
Recommendation:
const user = await fetchUser(userId);
if (!user?.profile?.name) {
throw new Error('User profile not found');
}
return user.profile.name;
🟠 Hardcoded Credentials (Line 12)
Severity: Major Category: Security
const API_KEY = 'sk_live_abc123xyz';
Issue: Sensitive credentials in source code
Recommendation: Move to environment variables
const API_KEY = process.env.API_KEY;
Minor Issues (3)
🟡 Inconsistent Naming (Line 89)
Category: Code Style
const user_id = req.params.userId; // Mixed naming conventions
Recommendation: Use consistent camelCase
const userId = req.params.userId;
🟡 Missing JSDoc (Line 23)
Category: Documentation
function validateEmail(email) {
// Complex validation logic
}
Recommendation: Add documentation
/**
* Validates email address format and domain
* @param {string} email - Email address to validate
* @returns {boolean} True if valid
*/
function validateEmail(email) {
// Complex validation logic
}
🟡 Magic Number (Line 56)
Category: Code Quality
if (attempts > 5) {
lockAccount();
}
Recommendation: Use named constant
const MAX_LOGIN_ATTEMPTS = 5;
if (attempts > MAX_LOGIN_ATTEMPTS) {
lockAccount();
}
src/services/UserService.js
Major Issues (2)
🟠 No Input Validation (Line 34)
async createUser(userData) {
return await db.users.create(userData); // No validation
}
Recommendation: Validate input before database operation
async createUser(userData) {
const schema = z.object({
email: z.string().email(),
name: z.string().min(1),
age: z.number().min(0).optional()
});
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.
- yesterday First seen · 379 lines · 19 tokens per session scan A f22a10f79af4
code-reviewer is a skill published in the GitHub repository CuriousLearner/devkit (27 stars, last pushed 10mo ago), licensed MIT. It adds 19 tokens to every session and 1,980 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 2026-08-30.
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…