Requesting code review
Skill yangshu2087/Codex/.agents/skills/requesting-code-review
Meta workspace for Codex configuration, shared skills, and maintenance scripts.
npx -y skills add yangshu2087/Codex --skill requesting-code-reviewAssembled from the repository path, not quoted from the project. Check it against their README if it does not work.
2 things to look at
- no licenseNo license file was found in the repository. Code published without one is not open source by default, so using it at work is a question for whoever answers licensing questions where you are.
- 0 stars0 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
3.3 KB, 758 tokens by cl100k_base, as published. Nobody here has run it
Requesting Code Review
Use this skill to run a focused review before moving on, opening a PR, or declaring a change done. Prefer a review that is grounded in the actual git diff and requirements, not in vague recollection.
Core principle: Review early, review often.
When to Request Review
Mandatory:
- After each major implementation batch
- 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=$(git merge-base HEAD origin/main 2>/dev/null || git rev-parse HEAD~1)
HEAD_SHA=$(git rev-parse HEAD)
If origin/main is unavailable, replace it with the right base branch or explicit commit.
2. Gather review context:
git diff --stat "$BASE_SHA..$HEAD_SHA"
git diff "$BASE_SHA..$HEAD_SHA"
Also collect the requirement source you are reviewing against:
- plan doc
- ticket
- acceptance criteria
- user request in this thread
3. Run the review in Codex:
- Default: ask for a review in the current Codex session and use the checklist in
code-reviewer.md - If
/reviewis available and the repo is ready, use it - Only use a separate reviewer agent when the user explicitly asks for delegation or subagents
Placeholders:
{WHAT_WAS_IMPLEMENTED}- What you just built{PLAN_OR_REQUIREMENTS}- What it should do{BASE_SHA}- Starting commit{HEAD_SHA}- Ending commit{DESCRIPTION}- Brief summary
4. 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=$(git merge-base HEAD origin/main)
HEAD_SHA=$(git rev-parse HEAD)
[Run review using code-reviewer.md checklist against BASE_SHA..HEAD_SHA]
WHAT_WAS_IMPLEMENTED: Verification and repair functions for conversation index
PLAN_REFERENCE: Task 2 from docs/superpowers/plans/deployment-plan.md
BASE_SHA: a7981ec
HEAD_SHA: 3df7661
DESCRIPTION: Added verifyIndex() and repairIndex() with 4 issue types
[Review 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
Implementation Batches:
- Review after EACH task
- Catch issues before they compound
- Fix before moving to next task
Executing Plans:
- Review after each batch (3 tasks)
- 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
- Review against memory alone instead of the actual diff
If reviewer wrong:
- Push back with technical reasoning
- Show code/tests that prove it works
- Request clarification
See checklist at: requesting-code-review/code-reviewer.md
Gives 2 of the 12 instructions most code review skills give in 758 tokens
Counted across 610 of the 674 authors here whose files we hold, read 2026-08-06
- push back with technical reasoning if wrongin 60 of 610, across 24 files
- ask for clarification on unclear itemsin 51 of 610, across 16 files
- fix critical issues immediatelyhere, and in 45 of 610, across 29 files
- implement one item at a timein 45 of 610, across 11 files
- group findings by severityin 44 of 610, across 43 files
- verify feedback against the codebasein 42 of 610, across 8 files
- dispatch a code reviewer subagentin 39 of 610, across 23 files
- fix important issues before proceedinghere, and in 37 of 610, across 22 files
- test each fix individuallyin 35 of 610, across 7 files
- reply in github comment threadsin 33 of 610, across 5 files
- check for security vulnerabilitiesin 31 of 610, across 27 files
- factualize corrections without over-explainingin 30 of 610, across 2 files
Said here and by no other author read
- gather git diff and review context
- collect requirement sources for review
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.