2.8 KiB

Raw Blame History

name	description
requesting-code-review	Use when completing tasks, implementing major features, or before merging to verify work meets requirements

Requesting Code Review

Dispatch a code review subagent to catch issues before they cascade. The reviewer gets precisely crafted context for evaluation — never your session's history.

Core principle: Review early, review often.

When to Request Review

Mandatory:

After each task in subagent-driven development
After completing major feature
Before merge to main

Optional but valuable:

When stuck (fresh perspective)
Before refactoring (baseline check)
After fixing complex bug

How to Request

1. Get git SHAs:

BASE_SHA=$(git rev-parse HEAD~1)
HEAD_SHA=$(git rev-parse HEAD)

2. Dispatch code-reviewer subagent with these inputs:

WHAT_WAS_IMPLEMENTED — What you just built
PLAN_OR_REQUIREMENTS — What it should do (link to plan or task text)
BASE_SHA — Starting commit
HEAD_SHA — Ending commit
DESCRIPTION — Brief summary

3. Act on feedback:

Fix Critical issues immediately
Fix Important issues before proceeding
Note Minor issues for later
Push back if reviewer is wrong (with reasoning)

Code Reviewer Subagent Prompt Template

Review the code changes for quality and correctness.

## What was implemented
{WHAT_WAS_IMPLEMENTED}

## Requirements / Plan
{PLAN_OR_REQUIREMENTS}

## Git diff
BASE_SHA: {BASE_SHA}
HEAD_SHA: {HEAD_SHA}

Review for:
1. Does the code meet the stated requirements?
2. Are there bugs, edge cases, or logic errors?
3. Is error handling adequate?
4. Is the code clear and maintainable?
5. Are there performance concerns?
6. Does it follow project conventions (React 18, Tailwind, Vitest)?

Report:
- Strengths
- Issues by severity (Critical / Important / Minor)
- Overall assessment: Ready to proceed, or needs fixes

Example

[Just completed Task 2: Add verification function]
You: Let me request code review before proceeding.

BASE_SHA=$(git log --oneline | grep "Task 1" | head -1 | awk '{print $1}')
HEAD_SHA=$(git rev-parse HEAD)

[Dispatch code-reviewer subagent]

[Subagent returns]:
Strengths: Clean architecture, real tests
Issues: Important: Missing progress indicators
        Minor: Magic number (100) for reporting interval
Assessment: Ready to proceed

You: [Fix progress indicators]
[Continue to Task 3]

Red Flags

Never:

Skip review because "it's simple"
Ignore Critical issues
Proceed with unfixed Important issues
Argue with valid technical feedback

If reviewer wrong:

Push back with technical reasoning
Show code/tests that prove it works
Request clarification

Integration

Used by:

subagent-driven-development — After each task
executing-plans — After each batch

2.8 KiB Raw Blame History