Requesting code review
Hands finished work to a fresh reviewer subagent through a template: the commit range, the plan or requirements, findings by severity and a verdict on merging. Use when a task or feature is done and a merge to main is next.
requesting-code-review- Author
- Jesse Vincent
- Source
- obra/superpowers/skills/requesting-code-review @ 22f0b46
- License
- MIT · Copyright (c) 2025 Jesse Vincent
About this skill
What it does
The skill makes the agent hand finished work to a separate reviewer subagent instead of reviewing its own diff. The agent fills a prompt template with the commit range (base and head SHA), a short description of what was built and the plan or requirements, and dispatches a general-purpose subagent. The reviewer never sees the session history, so it judges the code, not the reasoning behind it. Critical findings are fixed at once, Important ones before moving on, Minor ones noted for later; a wrong finding gets pushback with technical reasons.
The template ships as code-reviewer.md. It has the reviewer check plan alignment, code quality, architecture, tests and production readiness; treat what a reasonable user would expect as a requirement even where the spec is silent; list every behavior it set aside as out of scope; and stay read-only on the checkout. It ends with a verdict: ready to merge — yes, no or with fixes.
When to use it, and when not
The skill makes review mandatory after each task in subagent-driven development, after a major feature and before a merge to main, and suggests it when the agent is stuck, before a refactor and after a tricky bug fix.
It needs subagent support and committed work: the template reviews a SHA range, not uncommitted changes. It also forbids skipping review because a change looks simple, so it is a poor default if small fixes should go through unreviewed.
How to run it
The install command below puts the whole folder in place: SKILL.md, code-reviewer.md and the licence. The agent picks the skill up by its description when it finishes a task or a feature; to call it yourself:
- Claude Code:
/requesting-code-review, or ask for the skill by name. - Codex:
$requesting-code-review. - Cursor: type
/in the Agent chat and pickrequesting-code-review.
Example: /requesting-code-review The rate limiter is committed. Review everything since origin/main against the requirements in issue 42.
The same template runs the final whole-branch review in executing-plans and subagent-driven-development, so install it alongside them; receiving-code-review covers the other side of the review.
How it differs from similar skills
PR review from our catalog makes the current agent the reviewer and reports only bugs it can back with a failure scenario. Requesting code review covers the author's side: preparing the context, handing it to a fresh subagent and acting on the verdict. Self-review before PR is the author checking its own diff, which this skill avoids on purpose: an inline review burns the coordinating agent's context. Doubt-driven development also hands work to a fresh-context subagent, but for each non-trivial decision while the work is still in progress, with a prompt to find what is wrong. Code review against standards and spec runs two fresh subagents in parallel, one for the repo's written standards and one for the spec, and keeps their reports apart. The template gives security one line; for code that handles input, auth or payments, add Security review.
Install
Run one command — it saves SKILL.md and the files it uses into your agent's skills folder. Claude Code and Codex pick up a new skill without a restart; if it does not show up, restart the agent.
curl -fsSL --create-dirs -o ~/.claude/skills/requesting-code-review/SKILL.md https://anymodel.org/en/skills/superpowers/requesting-code-review/SKILL.md -o ~/.claude/skills/requesting-code-review/LICENSE https://anymodel.org/en/skills/superpowers/requesting-code-review/LICENSE -o ~/.claude/skills/requesting-code-review/code-reviewer.md https://anymodel.org/en/skills/superpowers/requesting-code-review/code-reviewer.md
curl -fsSL --create-dirs -o ~/.agents/skills/requesting-code-review/SKILL.md https://anymodel.org/en/skills/superpowers/requesting-code-review/SKILL.md -o ~/.agents/skills/requesting-code-review/LICENSE https://anymodel.org/en/skills/superpowers/requesting-code-review/LICENSE -o ~/.agents/skills/requesting-code-review/code-reviewer.md https://anymodel.org/en/skills/superpowers/requesting-code-review/code-reviewer.md
foreach ($f in 'SKILL.md','LICENSE','code-reviewer.md') { $p = Join-Path "$HOME\.claude\skills\requesting-code-review" $f; New-Item -ItemType Directory -Force (Split-Path $p) | Out-Null; Invoke-WebRequest "https://anymodel.org/en/skills/superpowers/requesting-code-review/$f" -UseBasicParsing -OutFile $p }foreach ($f in 'SKILL.md','LICENSE','code-reviewer.md') { $p = Join-Path "$HOME\.agents\skills\requesting-code-review" $f; New-Item -ItemType Directory -Force (Split-Path $p) | Out-Null; Invoke-WebRequest "https://anymodel.org/en/skills/superpowers/requesting-code-review/$f" -UseBasicParsing -OutFile $p }Any other agent: save the file into its skills folder, or give it the link to the file: https://anymodel.org/en/skills/superpowers/requesting-code-review/SKILL.md
SKILL.md
Requesting Code Review
Dispatch a code reviewer subagent to catch issues before they cascade. The reviewer gets precisely crafted context for evaluation — never your session's history.
Core principle: Review early, review often.
When to Request Review
Mandatory:
- After each task in subagent-driven development
- After completing major feature
- Before merge to main
Optional but valuable:
- When stuck (fresh perspective)
- Before refactoring (baseline check)
- After fixing complex bug
How to Request
1. Get git SHAs:
BASE_SHA=$(git rev-parse HEAD~1) # or: git merge-base origin/main HEAD
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 | cut -d' ' -f1)
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
Connect through AnyModel API
This skill runs on whatever model your agent uses. Point Claude Code, Codex or Cursor at AnyModel to run it on Claude, GPT, Gemini and more with one key — pay per token, no subscription.
AnyModel