メニュー
Delegate a task to Cursor's CLI agent (code review, Q&A, planning) for a second opinion from a non-Claude model
Compress the previous assistant response into a single TL;DR line, then propose exactly three terse next-step labels (≤8 words each, slash commands welcome) the user can take. Use whenever the user types `/tldr`, `/recap`, says "tldr", "tl;dr", "summarize and suggest next steps", "recap that", "what should I do next", "give me the gist", or otherwise asks for a quick summary of what was just said plus suggestions for what to do next. Trigger even when the user phrases it casually ("ok so what now?", "give me the short version + next steps") — this skill exists exactly for those moments where a long answer needs distilling and a clear handoff to action.
Generate text, images, and video from the CLI via the Vercel AI Gateway (one key, hundreds of models).
Fetch and execute a remote skill on-the-fly without installing it permanently. Use when the user wants to try a skill once, run a skill from GitHub, use a remote skill without installing, or mentions "use-skill", "run remote skill", "try this skill", "fetch skill", "one-time skill", or provides a GitHub URL/shorthand pointing to a skill they want to execute. This is the go-to skill whenever someone wants to use a skill they haven't installed locally. Also use when the user mentions skills.sh or wants to search for available skills.
Upload files to catbox.moe for free, anonymous hosting with direct links. Use when the user wants to upload an image, video, or any file to catbox, host a file online, get a direct link to a file, or mentions "catbox", "catbox.moe", "upload to catbox", "host file", or wants a permanent direct URL for a file.
Audit your Claude Code setup for token waste and context bloat. Use when the user says "audit my context", "check my settings", "why is Claude so slow", "token optimization", "context audit", or runs /context-audit. Starts by running /context to see real overhead, then audits MCP servers, CLAUDE.md rules, skills, settings, and file permissions. Returns a health score with specific fixes.
Capture the current session's repeatable process into a reusable SKILL.md skill file. Use when the user wants to create a skill, save a workflow as a skill, turn a process into a reusable skill, or mentions "skillify", "create skill", "make a skill", "save as skill", "capture workflow", "turn this into a skill", "new skill", or wants to automate a repeatable process they just performed.
| name | cursor-agent |
| description | Delegate a task to Cursor's CLI agent (code review, Q&A, planning) for a second opinion from a non-Claude model |
| allowed-tools | ["Bash(cursor-agent:*)","Bash(git diff:*)","Bash(git log:*)","Bash(git status:*)"] |
| when_to_use | Use when the user wants to run cursor-agent (Cursor's CLI). Triggers: 'cursor review', 'ask cursor', 'use cursor', 'review with cursor', 'second opinion from cursor', 'cursor-agent', 'use cursor-agent'. Also use for verifying code/plans/texts/UI with a different model than Claude. |
| argument-hint | [task for cursor-agent, e.g. 'review this branch'] |
| arguments | ["task"] |
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.
$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.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.
Extract from $task and the surrounding conversation:
--model claude-opus-4-7-medium--model claude-4.6-sonnet-medium--model gpt-5.3-codex--model gemini-3.1-pro--model auto--model (cursor uses its default: composer-2-fast)--mode plan--mode (cursor can write)--mode ask (read-only, default)Success criteria: Flags decided, prompt ready.
If the task is a code review:
main (git diff origin/main...HEAD), or uncommitted changes (git diff HEAD)."Review the branch
<name>against main. Usegit diff origin/main...HEADto see the actual changes. Focus on real issues (correctness, edge cases, security); skip nitpicks. Report under ~400 words withfile:linereferences."
For non-review tasks (ask/plan/text/UI), pass the task as-is.
Success criteria: Final prompt string ready for the CLI.
Invoke headless via Bash:
cursor-agent -p --output-format text [--mode <mode>] [--model <model>] "<prompt>"
-p (print/headless).--output-format text unless the task needs structured output.--workspace unless the user explicitly asked for a different dir.--mode ask or --mode plan), no extra permission flags are needed. For headless write mode, do not silently add --force or --yolo; ask the user first.tail -n 200 if you suspect a very long response and want to cap context use. By default, take the full output.Success criteria: cursor-agent returns (exit 0) with a response. If it errors (auth, model not available), surface the error to the user instead of hiding it.
Present to the user in this order:
Keep the summary tight — the goal is to save the user from re-reading, not to replace cursor's output.
Success criteria: User sees both cursor's raw output and a Claude-curated action list.
cursor-agent --list-models shows every available model ID. If the user asks for something exotic (e.g. "thinking tier", "max tier"), check the list first.cursor-agent reads/writes inside the current workspace like any CLI tool — it is not sandboxed by default. Treat its output the same way you'd treat a teammate's PR comment: trust but verify.cursor-agent interactively themselves (no -p).