Claude Skills
Curated SkillsRepositoriesNominate
Sign inSign up
© 2026 Claude Skills·Learn more about Agent Skills
Back to repository

review-opus

stale

Deep code/plan review for architecture, subtle bugs, and test quality. Use after sonnet review for thorough analysis.

View on GitHub

Marketplace

claude-codex

Z-M-Huang/claude-codex

Plugin

claude-codex

development

Repository

Z-M-Huang/claude-codex
18stars

plugins/claude-codex/skills/review-opus/SKILL.md

Last Verified

January 24, 2026

Install Skill

Select agents to install to:

Scope:
npx add-skill https://github.com/Z-M-Huang/claude-codex/blob/main/plugins/claude-codex/skills/review-opus/SKILL.md -a claude-code --skill review-opus

Installation paths:

Claude
.claude/skills/review-opus/
Powered by add-skill CLI

Instructions

# Review Opus (Deep Review)

You are a thorough reviewer providing deep analysis. Your job is to catch subtle issues that fast reviews miss.

## Reference

Read `${CLAUDE_PLUGIN_ROOT}/docs/standards.md` for the complete review checklist.

## Your Focus (Deep Analysis)

- **Depth**: Thorough analysis of design and edge cases
- **Subtlety**: Catch issues that quick reviews miss
- **Long-term**: Consider maintainability and technical debt

## Determine Review Type

Check which files exist:

1. If `.task/plan-refined.json` exists and no `.task/impl-result.json` → **Plan Review**
2. If `.task/impl-result.json` exists → **Code Review**

## For Plan Reviews

1. Read `.task/plan-refined.json`
2. Deep analysis of:
   - Technical approach soundness
   - Edge cases and failure modes
   - Security implications
   - Long-term maintainability
   - Over/under-engineering concerns

## For Code Reviews

1. Read `.task/impl-result.json` to get changed files
2. Review each changed file against the checklist below

### Opus Review Checklist

#### Security - OWASP Top 10 (Deep Analysis)
- [ ] **Injection**: Subtle injection vectors (second-order, blind)
- [ ] **Broken Auth**: Session fixation, token leakage, weak crypto
- [ ] **Sensitive Data**: Data exposure through side channels, timing attacks
- [ ] **XXE**: XML parsing with external entities enabled
- [ ] **Broken Access Control**: IDOR, path traversal, privilege escalation
- [ ] **Security Misconfiguration**: Default credentials, verbose errors
- [ ] **XSS**: Stored XSS, DOM-based XSS, template injection
- [ ] **Insecure Deserialization**: Object injection, gadget chains
- [ ] **Vulnerable Components**: CVEs in dependencies (run `npm audit`, `pip-audit`, etc.)
- [ ] **Insufficient Logging**: Security events not captured

#### Error Handling (Edge Cases)
- [ ] Error recovery mechanisms
- [ ] Cascading failure prevention
- [ ] Graceful degradation under failure
- [ ] Error messages useful for debugging but safe for users

#### Resour

Validation Details

Front Matter
Required Fields
Valid Name Format
Valid Description
Has Sections
Allowed Tools
Instruction Length:
5954 chars

Issues Found:

  • placeholder_text