# Plannotator:user Code Review

> Request a code review from the user via plannotator. Use at the end of an implementation task, or when the user asks for a review cycle. Collects structured annotations, then addresses each item.

- Skill: `jamiebrynes7/plannotator-user-code-review` (Agent Skill)
- Install (CLI): `npx skillmds@latest add jamiebrynes7/plannotator-user-code-review`
- Raw SKILL.md: https://api.skillmd.com/api/skills/jamiebrynes7/plannotator-user-code-review/raw
- Safety review: pending
- Works with: Claude Code, Claude.ai, OpenAI Codex
- Category: Productivity
- Author: jamiebrynes7 (https://skillmd.com/u/jamiebrynes7)
- Updated: 2026-09-17
- Page: https://skillmd.com/skills/jamiebrynes7/plannotator-user-code-review

---


Plannotator provides a structured review UI where the user can leave inline
annotations on specific files and lines. Use it to get precise, actionable feedback.

Run the following command to start a review session. Set the Bash tool timeout
to 1800000ms (30 minutes) so the user has enough time to review and annotate.

```
plannotator review
```

Plannotator starts a local HTTP server. If the execution environment
sandboxes localhost socket creation, run the command using its narrowest
available permission-escalation mechanism. Otherwise, run it normally.

If Plannotator reports that its entire port range is exhausted in a
sandboxed environment, treat that as a possible socket-permission failure
rather than immediately changing ports; retry once with permission to bind
a localhost socket.

## Reviewing Feedback

For each annotation from the user:

1. **Summarize** the feedback in one line
2. **Evaluate** whether the suggestion is valid — push back if it would introduce a bug, conflict with project conventions, or reduce code quality
3. **Act** — apply the fix or explain why you disagree

If no changes were requested, acknowledge this and move on.