review-code

Review Code Command

Perform comprehensive code review by orchestrating specialist agents. This command analyzes code quality, identifies bugs, suggests improvements, and provides actionable feedback through parallel delegation to language-specific experts.

Step 1: Gather Context

Run git commands to identify what files need review:

# Check git status for staged and unstaged changes
git status --short

# Show staged changes with stats
git diff --cached --stat

# Show unstaged changes with stats
git diff --stat

# Show recent commits on current branch
git log --oneline -10

# Show changes in last commit
git diff HEAD~1 --stat

Step 2: Clarify Scope

If the scope is ambiguous, ask the user to specify:

Questions to ask:

• Review staged changes?
• Review specific files or directories?
• Review recent commits (how many)?
• Review all uncommitted changes?
• Review specific pull request changes?

If the scope is clear from context (e.g., user said "review my staged changes"), proceed automatically.

Step 3: Classify Files by Language

Group the files to review by their primary language/technology:

File Extension Mapping:

• .ts, .tsx, .js, .jsx, .mjs, .cjs → principal-engineer-typescript
• .go → principal-engineer-go
• .py → principal-engineer-python
• Prompt files (.md in src/profiles/, agent profiles, commands, tasks) → prompt-engineer
• Other extensions → principal-engineer (generic fallback)

Step 4: Delegate to Specialist Agents

For each language group, spawn the appropriate specialist agent using the Task tool with this standardized review task:

## Code Review Task

**Files to Review:**
- [list of file paths for this language]

**Review Criteria:**

Analyze the code changes and provide feedback in these categories:

1. **Critical Issues** 🔴 - Must fix before merging
   - Bugs, logic errors, edge case failures
   - Security vulnerabilities
   - Breaking changes or regressions

2. **Important Improvements** 🟡 - Should address
   - Code quality and readability issues
   - Performance concerns
   - Maintainability problems
   - Missing error handling

3. **Minor Suggestions** 🟢 - Optional improvements
   - Style and formatting
   - Documentation enhancements
   - Minor optimizations

4. **Positive Highlights** ✅ - What was done well
   - Good patterns and practices
   - Clever solutions
   - Excellent test coverage

**Output Format:**

Use this exact structure:

```markdown