autoreview

# Auto Review Use the canonical [autoreview skill](https://github.com/openclaw/agent-skills/tree/main/skills/autoreview). Read the complete installed `~/.agents/skills/autoreview/SKILL.md` and the references it requires before reviewing. If installed at another operator-selected location, use that installation. This repository entrypoint contains no review implementation. If the skill is missing, report it. Installation requires separate authorization: reuse or clone `https://github.com/openclaw/agent-skills` and run `python3 scripts/install-skills autoreview` from that checkout. On Windows, use `python`; `--mode copy` is available when symlinks are unavailable. Prefer the shared `scripts/autoreview` helper with Python from the repository being reviewed, preserving its working directory. Follow the [Windows invocation and result-reading recipe](../../../docs/AGENT_WORKFLOWS.md#run-a-scoped-shared-review) before launch. Always use `--max-priority P3`, select mode/base explicitly, and supply required context. Check fresh final report/status, process outcome, and coverage together; exit zero alone is not a clean P0-P3 assessment. If Codex CLI is unavailable, follow the canonical skill's independent Copilot subagent fallback with the same scope, context, and P0-P3 severity. Report its actual host/model (or unverified identity), coverage, and limitations as a narrative assessment, not helper status or isolation guarantees. Never use fallback to bypass failures or findings. Follow all canonical and repository review requirements. Keep shared fixes and instructions upstream in `openclaw/agent-skills`. Update the shared checkout once for all symlinked consumers; reinstall copy-mode skills after updating their source. Do not add repository-local helpers or test copies.