receiving-code-review
An agent skill by obra, from obra/superpowers. Tags: api, developer-tools, web.
What it does
Use when receiving code review feedback, before implementing suggestions, especially if feedback seems unclear or technically questionable - requires technical rigor and verification, not performative agreement or blind implementation
Install
With the skills CLI, which installs into Claude Code, Codex, Cursor and other agents:
npx skills add obra/superpowers --skill receiving-code-review
Or copy the skill folder into Claude Code's skills directory by hand (~/.claude/skills for every project, or .claude/skills inside one):
git clone --depth 1 https://github.com/obra/superpowers
cp -r superpowers/skills/receiving-code-review ~/.claude/skills/receiving-code-review
Safety box score
Grade B, low risk: 12 of 100 risk points, rated 2026-10-21. The grade rates what the skill and its scripts can reach on the machine of whoever installs it, across eight categories from shell execution to secrets access. How the score works.
This skill is documentation-only: it teaches an agent how to respond to code review feedback and optionally reply in GitHub review threads. It does not ship runnable scripts or access local secrets, but it does strongly constrain the agent’s wording and behavior and can trigger outbound GitHub API replies.
| Category | Level | Why |
|---|---|---|
| Code & shell execution | 0 (none) | The only file is plain markdown; there are no scripts, shell commands, or code execution paths shipped with the skill. |
| Network access | 1 (low) | The GitHub thread-reply guidance mentions `gh api repos/{owner}/{repo}/pulls/{pr}/comments/{id}/replies`, which can send data to GitHub when used. |
| Filesystem reach | 0 (none) | It does not instruct the agent to read, write, or delete files outside the normal code-review workflow. |
| Secrets & credentials | 0 (none) | There is no request to access tokens, passwords, `.env` files, keychains, or other credential stores. |
| Privilege & persistence | 0 (none) | No sudo, global installs, services, shell startup edits, or OS-level changes are requested. |
| Instruction hijack surface | 1 (low) | The skill is highly prescriptive about agent phrasing and behavior (for example, `NEVER:` and `Just start working`), but it does not instruct prompt evasion or hidden instructions. |
| Irreversible actions | 1 (low) | It can drive a bounded outward action—posting inline GitHub review replies—but only within the narrow context of responding to code review. |
| Transparency | 0 (none) | All content is readable markdown; there are no binaries, encoded payloads, or remote fetches. |
Before installing
- Confirm you want the agent to use this terse, no-thanks review style.
- If GitHub replies are expected, verify the agent’s token is limited to the intended repo/org.
- Check that there are no shipped scripts or binaries beyond `SKILL.md`.
Rated 2026-10-21 by an automated review of 1 file from the skill's repository.
Source
- Repository
- obra/superpowers (all skills from this repository)
- Path
- skills/receiving-code-review/SKILL.md
- Branch
- main
- Updated
- 2026-09-19
Related skills
- executing-plans — Use when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution.
- finishing-a-development-branch — Use when implementation is complete, all tests pass, and you need to decide how to integrate the work
- requesting-code-review — Use when completing tasks, implementing major features, or before merging to verify work meets requirements
- systematic-debugging — Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes
- test-driven-development — Use when implementing any feature or bugfix, before writing implementation code
- using-git-worktrees — Use when starting feature work that needs isolation from current workspace or before executing implementation plans - ensures an isolated workspace exists via.