Cursor Agent

Delegate a task to Cursor's headless CLI agent (cursor-agent). Use this to get a second opinion from a non-Claude model on code reviews, plan critiques, text/copy review, or general Q&A.

Inputs

• $task: The task to hand to cursor-agent. Usually a review or question prompt. If the user adds a model hint (e.g. "with Opus", "using GPT", "pomocí Sonnetu"), extract it and pass via --model.

Goal

Run cursor-agent headless, surface its output to the user, and add a brief Claude TL;DR so the user doesn't have to re-read a wall of text.

Steps

1. Parse the task

Extract from $task and the surrounding conversation:

• Model hint — look for phrasing like:
  • "Opus" / "claude" → --model claude-opus-4-7-medium