requesting-code-review
obra/superpowers
Dispatch a code reviewer subagent to catch issues before they cascade.
What is requesting-code-review?
Request focused code review from a subagent reviewer with precise context about your changes. Use after completing tasks, implementing major features, or before merging to verify work meets requirements. The reviewer receives only the work product and diff, not your session history, keeping them focused and preserving your context.
- Dispatch a general-purpose subagent configured as a code reviewer
- Pass precise context (description, requirements, git SHAs) to the reviewer
- Receive structured feedback categorized by severity (Critical, Important, Minor)
- Keep reviewer focused on work product, not session history
- Preserve your own context for continued development
How to install requesting-code-review
npx skills add https://github.com/obra/superpowers --skill requesting-code-review- Git repository with commit history
- Ability to dispatch general-purpose subagents
- Access to code-reviewer.md template
How to use requesting-code-review
- 1.Get the base commit SHA (e.g., previous commit or origin/main)
- 2.Get the head commit SHA (current HEAD)
- 3.Dispatch a general-purpose subagent using the code-reviewer.md template
- 4.Fill in DESCRIPTION (what you built), PLAN_OR_REQUIREMENTS (what it should do), BASE_SHA, and HEAD_SHA
- 5.Review the subagent's feedback categorized by severity
- 6.Fix Critical issues immediately, Important issues before proceeding, and note Minor issues for later
- 7.Push back with technical reasoning if you disagree with feedback
Use cases
- After completing each task in subagent-driven development workflows
- Before merging code to main branch
- After implementing a major feature to catch architectural issues
- When stuck on a problem to get a fresh perspective
- Before refactoring to establish a baseline of current behavior
- Developers using subagent-driven development
- Teams implementing multi-agent workflows
- Engineers working on complex features or refactors
- Anyone wanting structured code review before merge
requesting-code-review FAQ
Mandatory: after each task in subagent-driven development, after completing major features, and before merge to main. Optional but valuable: when stuck, before refactoring, or after fixing complex bugs.
It keeps the reviewer focused on evaluating the work product itself, not your thought process. This also preserves your own context for continued development without bloating it.
Push back with technical reasoning. Show code or tests that prove it works, and request clarification. Never ignore Critical issues, but you can dispute feedback if you have valid justification.
No. The skill emphasizes never skipping review because 'it's simple.' Review early and often to catch issues before they cascade.
Critical (fix immediately), Important (fix before proceeding), and Minor (note for later). Always fix Critical and Important issues before moving forward.
Full instructions (SKILL.md)
Source of truth, from obra/superpowers.
name: requesting-code-review description: Use when completing tasks, implementing major features, or before merging to verify work meets requirements
Requesting Code Review
Dispatch a code reviewer subagent to catch issues before they cascade. The reviewer gets precisely crafted context for evaluation — never your session's history. This keeps the reviewer focused on the work product, not your thought process, and preserves your own context for continued work.
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=$(git rev-parse HEAD~1) # or origin/main
HEAD_SHA=$(git rev-parse HEAD)
2. Dispatch code reviewer subagent:
Dispatch a general-purpose subagent, filling the template at code-reviewer.md
Placeholders:
{DESCRIPTION}- Brief summary of what you built{PLAN_OR_REQUIREMENTS}- What it should do{BASE_SHA}- Starting commit{HEAD_SHA}- Ending commit
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)
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]
DESCRIPTION: Added verifyIndex() and repairIndex() with 4 issue types
PLAN_OR_REQUIREMENTS: Task 2 from docs/superpowers/plans/deployment-plan.md
BASE_SHA: a7981ec
HEAD_SHA: 3df7661
[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]
Integration with Workflows
Subagent-Driven Development:
- Review after EACH task
- Catch issues before they compound
- Fix before moving to next task
Executing Plans:
- Review after each task or at natural checkpoints
- Get feedback, apply, continue
Ad-Hoc Development:
- Review before merge
- Review when stuck
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
See template at: code-reviewer.md
Related skills
More from obra/superpowers and the wider catalog.
brainstorming
Explore user intent and design before implementation—mandatory first step for any creative work.
systematic-debugging
Find root cause before fixing—systematic debugging prevents wasted effort and masked problems.
writing-plans
Create detailed implementation plans for multi-step tasks before writing code.
using-superpowers
Establish skill-first workflow—invoke relevant skills before any response, even with 1% applicability.
test-driven-development
Write tests first, watch them fail, then implement—the disciplined way to build reliable code.
executing-plans
Execute a written implementation plan with review checkpoints and task verification.