agentsclimarketplace

Requesting code review

Skill smallocean43658/codex-superpowers/skills/requesting-code-review

Codex-first fork of Superpowers skills with Codex-native tool guidance

Install
npx -y skills add smallocean43658/codex-superpowers --skill requesting-code-review

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

One thing to look at

  • 5 stars5 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

What its author says it does

Copied from the file, not written here

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

SKILL.md

3.6 KB, as published. Nobody here has run it

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:

# For task review, use the commit recorded before the task started.
# For whole-branch review, use the branch merge-base.
BASE_SHA=$(git merge-base main HEAD 2>/dev/null || git merge-base master HEAD)
HEAD_SHA=$(git rev-parse HEAD)

Do not use HEAD~1 unless you are certain the work is exactly one commit. For multi-commit work, HEAD~1 silently drops earlier commits from review.

2. Dispatch code reviewer subagent:

Dispatch a worker-capable reviewer subagent, filling the template at code-reviewer.md.

In Codex, use the worker-capable multi-agent tool exposed in the active session (see codex-tools.md). Wait for the reviewer result and close the finished subagent after handling it.

If no worker-capable multi-agent tool is available, do not claim independent review was performed. Stop and tell your human partner which review path is blocked. Ask them to enable Codex multi-agent support or provide another review channel before proceeding past Critical or Important work.

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=<commit recorded before Task 2 started>
HEAD_SHA=$(git rev-parse HEAD)

[Dispatch code reviewer subagent; in Codex, use the active worker subagent tool]
  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

Keep looking

Skills are one crate of 328,083. Ordering is by how many stacks a row turns up in, so the top of any crate is what has actually been picked rather than what has the most stars.