code-review-patterns
SkillSecurityThis skill gives your AI the ability to review code across four areas: security, quality, performance, and maintainability. Findings are only reported when the assessment reaches at least 80 percent confidence, so the results focus on issues worth your attention. It can also generate router contracts as part of the review output.
Available today. Use it from your connected AI after setup.
No other account needed.
After adding it, ask your AI to review a piece of code and it will return confidence-filtered findings across the four assessment areas.
Then ask your AI: use the code-review-patterns skill
What your AI can do with it
- Review code for security issues
- Check code for quality problems
- Identify performance concerns
- Assess how maintainable the code is
- Show only findings that meet the 80 percent confidence threshold
- Generate router contracts from the review
What this skill tells your AI
The instructions your AI receives, as published by a5c-ai/babysitter in library/methodologies/cc10x/skills/code-review-patterns/SKILL.md and read by ahel’s review.
- Injection vulnerabilities (SQL, XSS, command)
- Authentication and authorization patterns
- Secrets handling (no hardcoded credentials)
- Input validation and sanitization
Quality (weight: 25%)
- Naming conventions and consistency
- Code structure (SRP, cohesion, coupling)
- Error handling completeness
- Type safety (no
anyescapes)
Performance (weight: 20%)
- Algorithmic complexity (flag O(n^2) or worse)
- Resource and memory leaks
- Database query efficiency (N+1)
- Caching opportunities
Maintainability (weight: 25%)
- Documentation (JSDoc/TSDoc for public APIs)
- Test coverage adequacy
- Readability (function length, nesting depth)
- Tech debt markers (TODO, FIXME)
Confidence Gating
- Only report issues with confidence >= 80%
- Empty catch blocks are always critical (100% confidence)
- Classify: critical, high, medium, low
- Include actionable remediation for each issue
Router Contract
Every review must produce: STATUS, BLOCKING, REQUIRES_REMEDIATION, issue counts.
When to Use
- Code review step in BUILD workflow
- Fix review in DEBUG workflow
- Full REVIEW workflow
Agents Used
code-reviewer(primary consumer)silent-failure-hunter(error handling dimension)
Signals
- GitHub stars
- 2k
- Forks
- 106
- Last commit
- Sep 2026
Advanced
- Catalog kind
- skill
- Gateway key
code-review-patterns- Source
- github.com/a5c-ai/babysitter