Autoreview

Runs structured code review from Codex (default) or five other engines before you commit or ship. The contract is blunt about what matters: verify every finding yourself, reject speculative edge cases and broad rewrites, fix the bug class not just the instance, and keep running until nothing actionable comes back. It handles dirty work, branches, PRs, and single commits, supports parallel test runs during review, and can take up to 30 minutes on large bundles. The guidance on regression provenance and automerge bot attribution is unusually detailed. Think of it as a paranoid reviewer that reads docs and checks dependencies, but you still own the accept/reject call on every line.

skills.sh installs: 3.1K
GitHub stars: 1.1K
last updated: Jun 11, 2026

View on GitHub

Install

$ npx -y skills add openclaw/agent-skills --skill autoreview --agent claude-code

Installs into .claude/skills of the current project.

Files

Auto Review

Run an independent review when the user or owning workflow asks. This is code review, not Guardian approval routing. Supply target, context, and severity; let the reviewer choose the analysis. Verify findings before acting.

Hosted review requests

ClawSweeper's service policy owns automatic review admission, including first reviews of newer maintainer PRs. The rules here govern agent-issued requests. Request @clawsweeper review only when the maintainer asks for it or the owning workflow specifically requires ClawSweeper, after the work and validation are complete. A generic independent-review requirement does not require a hosted bot review. Check for an existing queued or running review before requesting one. Do not automatically request reviews on PR creation, pushes, edits, or progress updates, and do not repeat a pending request. A later head needs a new request only when another review is required and that work is complete.