About plannotator-annotate
A Plannotator skill for annotating documents in a browser session, with a gate mode for reviewing and approving plans, specs, or documents.
Key features
- 01Annotate documents in Plannotator
- 02Use gate mode for approval
- 03Return annotations as JSON
- 04Handle notes accompanying approval
Use cases
- 01Give feedback on a document
- 02Approve or gate a generated plan
- 03Review a specification before proceeding
Install
Copy the command and run it in a terminal.
npx skills add https:/ / github.com/ backnotprop/ plannotator --skill plannotator-annotateAfter installing, type/plannotator-annotatein Claude Code to confirm it loaded.
Bundled filesagents/openai.yaml
Details
From the project READMEPlannotator Annotate
Use this skill when the user wants to annotate a document in Plannotator instead of reviewing it inline in chat.
Run for ordinary annotation/feedback:
plannotator annotate <path-or-url>
Run when the user asks to review, approve, accept, or gate a generated plan/spec/document:
plannotator annotate <path-or-url> --gate --json
Plain annotate has no Approve button; it only supports feedback or closing the session. Never promise an approval action unless --gate is present. --json only changes the output format and does not enable approval by itself.
Behavior:
- Launch the command with Bash.
- Wait for the browser review to finish.
- If annotations are returned, address them directly.
- If the session closes without feedback (the output is empty, or a JSON object with
"decision": "dismissed"), acknowledge it in one sentence and stop. Do not begin any work: closing the session is not approval. - In a
--gatesession, an approval may still carry notes — a"decision": "approved"result with a"feedback"field (without--json, an "Approved with Notes" message). Read those notes and carry them into subsequent work, but do not revise the document over them: they are guidance, not a change request. - If the command reports that the arguments could not be resolved to a file, URL, or folder, work out which target the user means and re-run the command yourself with that concrete path or URL.
Do not ask the user to paste a shell command into the chat. Run the command yourself.