Requesting Code Review

Dispatch a code-reviewer subagent to review changes against plans and requirements.

146|31|Updated Jul 25, 2025
One-click install
npx skills add https://github.com/bobmatnyc/claude-mpm --skill requesting-code-review-bobmatnyc
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: Requesting Code Review
Source: https://github.com/bobmatnyc/claude-mpm/tree/main/src/claude_mpm/skills/bundled/collaboration/requesting-code-review
Command: npx skills add https://github.com/bobmatnyc/claude-mpm --skill requesting-code-review-bobmatnyc

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

This Skill prevents critical bugs, architectural flaws, or unmet requirements from slipping through due to manual, inconsistent, or delayed code reviews. It dispatches a specialized subagent to perform thorough, automated code reviews, saving developer time and improving code quality.

Core Features & Use Cases

  • Automated Review Dispatch: Quickly initiates a code review by providing git SHAs and a clear description of changes, streamlining the review process.
  • Severity-Based Feedback: Categorizes issues as Critical, Important, or Minor, guiding immediate action and prioritization, ensuring critical problems are addressed first.
  • Workflow Integration: Seamlessly fits into various development workflows: after each task in subagent-driven development, after batches in executing plans, or as a mandatory pre-merge step in ad-hoc development.
  • Use Case: After implementing a new feature, use this Skill to get an automated review against the original plan, ensuring all requirements are met and no critical issues are introduced before merging to main.

Quick Start

Use the Requesting Code Review skill to review the changes between abc123def and xyz789uvw for the "user login flow" feature, comparing it against docs/plans/auth-plan.md.

Frequently Asked Questions about Requesting Code Review

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I automate code reviews before merging to main?

Automate code reviews by dispatching a specialized subagent with your git range and a Code Reviewer Template. The subagent analyzes changes against your plan, categorizes issues by severity (Critical, Important, Minor), and produces a production readiness assessment before you merge.

What does a code review subagent check for?

A code review subagent examines implementation against your original plan and requirements, identifying architectural flaws, bugs, unmet requirements, and code quality issues. It returns structured feedback organized by severity to guide prioritization.

When should I request a code review in my development workflow?

Request code reviews after each task in subagent-driven development, after major feature completion, before merging to main, or when stuck on implementation or planning refactoring. Timing ensures issues surface early and requirements stay aligned.

What do I need to provide for a code review?

Provide a git range (start and end SHAs), a clear description of your changes, and a Code Reviewer Template with placeholders for comparison against requirements. These inputs let the subagent perform thorough, structured analysis.

Can I use code reviews in different development workflows?

Yes. Code reviews fit subagent-driven workflows (after each task), batch execution (after feature groups), and ad-hoc development (as a mandatory pre-merge step). The severity-based categorization works across all workflow styles.

What happens if a code review finds critical issues?

Critical issues are flagged first in severity-based feedback, letting you address them immediately before proceeding. This prevents architectural flaws and bugs from reaching production while other issues are prioritized by importance.