agentsclimarketplace
Sign in

Requesting code review

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

Use when completing tasks, implementing major features, or before merging to verify work meets requirementsFrom its SKILL.md

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.

2 things 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.
  • runs commandsInstructs the agent to run 3 commands, including `git merge-base main HEAD` and 2 more.

SKILL.md

3.6 KB, 807 tokens by cl100k_base, 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

What ships with it: 2 files

6.3 KB alongside SKILL.md

Gives 3 of the 12 instructions most code review skills give in 807 tokens

Counted across 668 of the 814 authors here whose files we hold, read 2026-09-06

  • Provide technical reasoning when pushing backin 84 of 668, across 70 files
  • Fix critical issues immediatelyhere, and in 77 of 668, across 60 files
  • Dispatch a code reviewer subagenthere, and in 76 of 668, across 59 files
  • Fix important issues before proceedinghere, and in 73 of 668, across 56 files
  • Ask for clarification on unclear itemsin 68 of 668, across 56 files
  • Verify feedback against codebase before implementationin 66 of 668, across 55 files
  • Implement fixes one at a timein 64 of 668, across 53 files
  • Test each fix individuallyin 62 of 668, across 51 files
  • Restate technical requirements in own wordsin 57 of 668, across 46 files
  • Reply to inline comments in the specific threadin 51 of 668, across 40 files
  • Note minor issues for laterin 49 of 668, across 34 files
  • Group findings by severityin 48 of 668, across 47 files

Said here and by no other author read

  • close the subagent after handling results

Grouped from the skills themselves: near-identical wordings counted once, and counted by distinct author, so one author publishing three of these counts once. Length counted with cl100k_base; the agent that loads this file may tokenize it differently.

Keep looking

Skills are one crate of 325,949. 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.