Receiving code review

Checks each review comment against the code before changing anything, clears up every unclear item first, pushes back with technical reasons and never performs agreement. Use when working through review feedback without blind fixes.

Code reviewPack: Superpowers205 linesreceiving-code-review
Author
Source
obra/superpowers/skills/receiving-code-review @ 22f0b46
License
MIT · Copyright (c) 2025 Jesse Vincent

About this skill

What it does

The skill, a single SKILL.md, makes the agent check each review comment against the code before changing anything. It reads the whole review, restates or asks about each point, then answers or pushes back and fixes one item at a time, testing each. If any item is unclear, it asks before touching the clear ones, because items may be linked. Performative replies are banned — "You're absolutely right", "Great point", any thanks — in favour of stating the fix: "Fixed. [what changed]".

Your feedback is trusted once understood; an external reviewer's is first checked for correctness in this codebase, breakage, a reason behind the current code, platform and version support, and missing context. A request to "implement it properly" triggers a YAGNI check: grep for real usage and, if nothing calls the code, propose removing it. Replies to inline GitHub comments go into their thread through gh api, not as a top-level PR comment.

When to use it, and when not

Use it when an agent works through review comments from people, bots or a reviewer subagent and tends to agree with everything, apply suggestions blindly or fix half a list and ask about the rest later.

It neither writes a review nor collects the comments; it starts once the feedback is in front of the agent. The ban on thanks has no exceptions, so if your team expects a "thanks" in review threads, the agent's replies will read drier than usual.

How to run it

The install command below puts SKILL.md and the licence in place. The agent picks the skill up by its description when review feedback arrives; to call it yourself:

  • Claude Code: /receiving-code-review, or ask for the skill by name.
  • Codex: $receiving-code-review.
  • Cursor: type / in the Agent chat and pick receiving-code-review.

Example: /receiving-code-review Here are the reviewer's comments on PR 128. Check each one against the code before you change anything.

It calls no other skills; its pair is requesting-code-review, which dispatches the reviewer.

How it differs from similar skills

Responding to review feedback from our catalog does the same verification as a full workflow: it pulls every comment with gh, sorts each into correct, partly correct, incorrect, preference or question, keeps fixes in new commits, drafts a reply per comment without posting it and allows a genuine thank-you. Receiving code review is shorter and about behavior: no performative agreement, clarify everything before starting, YAGNI on suggested features, and stop to ask you when a suggestion conflicts with your earlier decisions. Pick the catalog skill for a long PR thread handled end to end; pick this one to change how the agent takes any feedback.

Address GitHub PR comments pulls every comment and thread with a script, numbers them and fixes only the ones you pick, without checking whether the reviewer is right. Iterate a PR until CI is green fixes high- and medium-priority comments together with failing checks, then commits, pushes and repeats until CI passes.

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.

Claude Code — macOS, Linux
curl -fsSL --create-dirs -o ~/.claude/skills/receiving-code-review/SKILL.md https://anymodel.org/en/skills/superpowers/receiving-code-review/SKILL.md -o ~/.claude/skills/receiving-code-review/LICENSE https://anymodel.org/en/skills/superpowers/receiving-code-review/LICENSE
Codex, Cursor — macOS, Linux
curl -fsSL --create-dirs -o ~/.agents/skills/receiving-code-review/SKILL.md https://anymodel.org/en/skills/superpowers/receiving-code-review/SKILL.md -o ~/.agents/skills/receiving-code-review/LICENSE https://anymodel.org/en/skills/superpowers/receiving-code-review/LICENSE
Claude Code — Windows PowerShell
foreach ($f in 'SKILL.md','LICENSE') { $p = Join-Path "$HOME\.claude\skills\receiving-code-review" $f; New-Item -ItemType Directory -Force (Split-Path $p) | Out-Null; Invoke-WebRequest "https://anymodel.org/en/skills/superpowers/receiving-code-review/$f" -UseBasicParsing -OutFile $p }
Codex, Cursor — Windows PowerShell
foreach ($f in 'SKILL.md','LICENSE') { $p = Join-Path "$HOME\.agents\skills\receiving-code-review" $f; New-Item -ItemType Directory -Force (Split-Path $p) | Out-Null; Invoke-WebRequest "https://anymodel.org/en/skills/superpowers/receiving-code-review/$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/receiving-code-review/SKILL.md

SKILL.md

Raw

Code Review Reception

Overview

Code review requires technical evaluation, not emotional performance.

Core principle: Verify before implementing. Ask before assuming. Technical correctness over social comfort.

The Response Pattern

WHEN receiving code review feedback:

1. READ: Complete feedback without reacting
2. UNDERSTAND: Restate requirement in own words (or ask)
3. VERIFY: Check against codebase reality
4. EVALUATE: Technically sound for THIS codebase?
5. RESPOND: Technical acknowledgment or reasoned pushback
6. IMPLEMENT: One item at a time, test each

Forbidden Responses

NEVER:

  • "You're absolutely right!" (explicit instruction-file violation)
  • "Great point!" / "Excellent feedback!" (performative)
  • "Let me implement that now" (before verification)

INSTEAD:

  • Restate the technical requirement
  • Ask clarifying questions
  • Push back with technical reasoning if wrong
  • Just start working (actions > words)

Handling Unclear Feedback

IF any item is unclear:
  STOP - do not implement anything yet
  ASK for clarification on unclear items

WHY: Items may be related. Partial understanding = wrong implementation.

Example:

your human partner: "Fix 1-6"
You understand 1,2,3,6. Unclear on 4,5.

❌ WRONG: Implement 1,2,3,6 now, ask about 4,5 later
✅ RIGHT: "I understand items 1,2,3,6. Need clarification on 4 and 5 before proceeding."

Source-Specific Handling

From your human partner

  • Trusted - implement after understanding
  • Still ask if scope unclear
  • No performative agreement
  • Skip to action or technical acknowledgment

From External Reviewers

BEFORE implementing:
  1. Check: Technically correct for THIS codebase?
  2. Check: Breaks existing functionality?
  3. Check: Reason for current implementation?
  4. Check: Works on all platforms/versions?
  5. Check: Does reviewer understand full context?

IF suggestion seems wrong:
  Push back with technical reasoning

IF can't easily verify:
  Say so: "I can't verify this without [X]. Should I [investigate/ask/proceed]?"

IF conflicts with your human partner's prior decisions:
  Stop and discuss with your human partner first

your human partner's rule: "External feedback - be skeptical, but check carefully"

YAGNI Check for "Professional" Features

IF reviewer suggests "implementing properly":
  grep codebase for actual usage

  IF unused: "This endpoint isn't called. Remove it (YAGNI)?"
  IF used: Then implement properly

your human partner's rule: "You and reviewer both report to me. If we don't need this feature, don't add it."

Implementation Order

FOR multi-item feedback:
  1. Clarify anything unclear FIRST
  2. Then implement in this order:
     - Blocking issues (breaks, security)
     - Simple fixes (typos, imports)
     - Complex fixes (refactoring, logic)
  3. Test each fix individually
  4. Verify no regressions

When To Push Back

Push back when:

  • Suggestion breaks existing functionality
  • Reviewer lacks full context
  • Violates YAGNI (unused feature)
  • Technically incorrect for this stack
  • Legacy/compatibility reasons exist
  • Conflicts with your human partner's architectural decisions

How to push back:

  • Use technical reasoning, not defensiveness
  • Ask specific questions
  • Reference working tests/code
  • Involve your human partner if architectural

If you're uncomfortable pushing back out loud: Name that tension, then tell your partner about the issue you've seen. They'll appreciate your honesty.

Acknowledging Correct Feedback

When feedback IS correct:

✅ "Fixed. [Brief description of what changed]"
✅ "Good catch - [specific issue]. Fixed in [location]."
✅ [Just fix it and show in the code]

❌ "You're absolutely right!"
❌ "Great point!"
❌ "Thanks for catching that!"
❌ "Thanks for [anything]"
❌ ANY gratitude expression

Why no thanks: Actions speak. Just fix it. The code itself shows you heard the feedback.

If you catch yourself about to write "Thanks": DELETE IT. State the fix instead.

Gracefully Correcting Your Pushback

If you pushed back and were wrong:

✅ "You were right - I checked [X] and it does [Y]. Implementing now."
✅ "Verified this and you're correct. My initial understanding was wrong because [reason]. Fixing."

❌ Long apology
❌ Defending why you pushed back
❌ Over-explaining

State the correction factually and move on.

Common Mistakes

Mistake Fix
Performative agreement State requirement or just act
Blind implementation Verify against codebase first
Batch without testing One at a time, test each
Assuming reviewer is right Check if breaks things
Avoiding pushback Technical correctness > comfort
Partial implementation Clarify all items first
Can't verify, proceed anyway State limitation, ask for direction

Real Examples

Performative Agreement (Bad):

Reviewer: "Remove legacy code"
❌ "You're absolutely right! Let me remove that..."

Technical Verification (Good):

Reviewer: "Remove legacy code"
✅ "Checking... build target is 10.15+, this API needs 13+. Need legacy for backward compat. Current impl has wrong bundle ID - fix it or drop pre-13 support?"

YAGNI (Good):

Reviewer: "Implement proper metrics tracking with database, date filters, CSV export"
✅ "Grepped codebase - nothing calls this endpoint. Remove it (YAGNI)? Or is there usage I'm missing?"

Unclear Item (Good):

your human partner: "Fix items 1-6"
You understand 1,2,3,6. Unclear on 4,5.
✅ "Understand 1,2,3,6. Need clarification on 4 and 5 before implementing."

GitHub Thread Replies

When replying to inline review comments on GitHub, reply in the comment thread (gh api repos/{owner}/{repo}/pulls/{pr}/comments/{id}/replies), not as a top-level PR comment.

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.

More from the pack Superpowers

Brainstorming before you build

Finds out what you want to build and why: one question at a time, its understanding played back part by part, two or three approaches to pick from and a design doc, with no code until you approve it. Use for a new feature or change when the request leaves the essentials open.

Dispatching parallel agents

Splits independent problems between parallel subagents, each with one domain and a self-contained brief with scope, constraints and the report expected back, then checks their edits for conflicts and runs the full suite. Use when several unrelated things fail at once.

Executing plans

Runs a plan from writing-plans in the current session with no subagent per task: tasks in order through TDD, a ledger of progress and rulings that survives context compaction, and one fresh review of the whole branch at the end. Use when per-task review is not needed or there are no subagents.

Finishing a development branch

Finishes a branch: runs the tests, offers to merge locally, open a pull request or keep it as is, reruns the tests after a merge and removes its own worktree, and discards work only after you type "discard". Use when the implementation is done.

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.

Subagent-driven development

Executes a plan through subagents: a fresh implementer and reviewer for every task, checking spec compliance and code quality, up to five fix rounds and a final review of the whole branch. Use for a plan of independent tasks when each one needs a review.

Systematic debugging

Keeps the agent from guessing at fixes: reproduce the bug and find the root cause first, test one hypothesis at a time, fix with a failing test, and question the design after three failed fixes. Use for any bug, test failure or unexpected behavior.

Test-driven development, Superpowers style

Drives work test-first: a test seen failing, then the least code that passes and a run of the whole suite; code written before its test is deleted. Use for features and bug fixes when the agent tends to add tests after the code.

Using git worktrees

Moves feature work into an isolated git worktree: checks whether the agent is already isolated, prefers the harness's own worktree tool, keeps the folder git-ignored, installs dependencies and runs a baseline test. Use when the work must not land on the branch you have open.

Verification before completion

Stops the agent from saying "done" or "tests pass" until it has rerun the check and read the whole output. Use whenever the agent reports success, commits or opens a pull request.

Writing implementation plans

Turns a spec into a plan for an implementer new to the codebase: files, signatures, interfaces between tasks, tests with exact values and TDD steps with each command's expected output. Use for a multi-step task when the spec is ready and no code exists yet.

Writing skills

Writes and edits skills the TDD way: a subagent first does the task without the skill and its mistakes are written down, then the smallest text that answers them goes in and the loopholes get closed. Use for a skill that other agents will load.