Catalog
obra/requesting-code-review

obra

requesting-code-review

Use when completing tasks, implementing major features, or before merging to verify work meets requirements

NewUpdated Sep 9, 2026

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.

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]

Common Rationalizations

Excuse Reality
"I'll just review the diff myself instead of dispatching a reviewer" You're the coordinator — reviewing the diff inline burns the context window you need to keep driving the work. Dispatch a reviewer subagent: the diff and the evaluation live in its context, and only the findings come back to you.
"The reviewer needs my whole session history to understand the change" Hand it precisely crafted context, never your session's history. That keeps the reviewer on the work product, not your thought process.

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

Files2
2 files · 6.6 KB

Select a file to preview

Overall Score

88/100

Grade

A

Excellent

Grades are signals, not a certification. Always review a skill yourself before use.

Safety

92

Quality

87

Clarity

88

Completeness

83

Summary

This skill guides agents to dispatch a code reviewer subagent for evaluating completed work before merge. It provides a structured workflow for requesting reviews (gathering git SHAs, dispatching a reviewer with templated context, and acting on feedback), plus a detailed prompt template for the reviewer subagent to follow when assessing code quality, plan alignment, testing, and production readiness.

Detected Capabilities

git command executionsubagent dispatchcontext templatingcode diff analysis instruction (read-only)

Trigger Keywords

Phrases that agents use to match this skill to user intent.

request code reviewbefore mergecode quality checkreview completed workcatch issues earlyverify requirementsarchitecture review

Use Cases

  • Request code review before merging to main
  • Evaluate completed features against requirements
  • Catch architecture and quality issues early
  • Get fresh perspective when stuck on implementation
  • Baseline code quality check before refactoring
  • Verify complex bug fixes
  • Ensure testing and error handling are complete

Quality Notes

  • Skill provides a complete end-to-end workflow: when to review, how to request, how to act on feedback, with a practical example
  • Supporting template (code-reviewer.md) is comprehensive with clear categorization of issue severity and explicit rules (DO/DON'T)
  • Reviewer subagent template includes strong guardrails: read-only review instruction, explicit prohibition on spawning nested subagents, clear output format
  • Example output demonstrates realistic feedback with specific file:line references and actionable fixes
  • Skill explicitly addresses common rationalizations (self-review burns context, unnecessary full session history) with reasoning
  • Clear red flags section sets expectations for rigor (don't skip because simple, don't ignore Critical issues)
  • Well-structured markdown with table, code blocks, and clear sections for readability
Model: claude-haiku-4-5-20251001Analyzed: Sep 9, 2026

Reviews

Add this skill to your library to leave a review.

No reviews yet

Be the first to share your experience.

Version History

  1. v1.2

    Content updated

    ✦ AIRewrites guidance to emphasize isolated reviewer context and dispels common rationalizations for skipping code review.

    2026-09-09

    LATEST
  2. v1.1

    Content updated

    ✦ AIChanges subagent dispatch method from superpowers:code-reviewer to general-purpose type; refines template field names and review frequency.

    2026-06-28

    View This Version
  3. v1.0

    2026-05-02

    View This VersionInitial version

Use obra/requesting-code-review in your dev environment

Command Palette

Search for a command to run...