Skip to content

Cursor

meshpoint connect cursor

writes entries into ~/.cursor/hooks.json (file format {"version":1,"hooks":{...}}) for sessionStart, beforeSubmitPrompt, afterAgentResponse, stop, preCompact and sessionEnd, each running meshpoint tap cursor, and the skill at ~/.cursor/skills/meshpoint/SKILL.md. With --project <repo> both land in <repo>/.cursor/. Cursor reloads hooks.json on save. Existing hooks are kept; --remove deletes only Meshpoint’s entries and the skill.

  • Recall and presence arrive as additional_context at session start.
  • Prompts and replies come from the beforeSubmitPrompt and afterAgentResponse payloads.
  • A due checkpoint is delivered as a followup_message from the stop hook, which Cursor submits as the next user message. Cursor caps auto follow-ups at five per conversation.
  • preCompact and sessionEnd send the spool.

Cursor must be allowed to run meshpoint items put and meshpoint items retract in its shell approval settings, or the checkpoint command waits for a click.

Ported from Cursor’s published hook documentation; not yet run end to end against the platform. Unconfirmed:

  • the transcript file format (touched paths and the nudge counter depend on it),
  • whether afterAgentResponse fires once per turn,
  • whether the agent picks the skill up from the follow-up message on its own.

Cursor also loads .claude/settings.json hooks. A repository connected for both Claude Code and Cursor at project scope would run two taps; connect at user scope.

If you run Cursor with Meshpoint, tell us what you see; a meshpoint doctor output and the spool file after one session are enough to close these.