code-reviewer
Use when explicitly asked to run the code-reviewer subagent or when another skill requires the code-reviewer agent card.
When & Why to Use This Skill
The Code Reviewer subagent is a specialized Claude skill designed to automate and enhance the software auditing process. By leveraging a dedicated agentic workflow, it provides deep analysis of code changes, identifies potential bugs, and ensures adherence to best practices, significantly reducing the manual workload for senior developers and improving overall code quality.
Use Cases
- Pull Request Analysis: Automatically evaluate code submissions for logic errors, security vulnerabilities, and performance bottlenecks before they are merged.
- Coding Standards Enforcement: Ensure that all new code contributions strictly follow project-specific style guides and industry-standard architectural patterns.
- Technical Debt Reduction: Use the subagent to scan existing modules and suggest refactoring opportunities to improve maintainability and readability.
- Context-Aware Debugging: Provide the subagent with specific issue numbers or PR context to get targeted feedback on complex bug fixes.
| name | code-reviewer |
|---|---|
| description | Use when explicitly asked to run the code-reviewer subagent or when another skill requires the code-reviewer agent card. |
Code Reviewer Subagent
Use the code-reviewer agent card to handle this specialized task.
Run
codex-subagent code-reviewer <<'EOF'
[Provide the task context, scope, and any issue/PR numbers.]
EOF
Notes
- Include concrete scope and constraints in the context block.
- Fold the subagent output back into the main workflow.