Skip to content
Back to skills

Delegate

ASecurity

Delegate a sub-task to a Cursor agent. Use when a task is better handled by a Cursor agent (e.g. complex file editing, multi-step coding tasks, research with web access).

  • 23 stars
  • 0 votes
  • 0 copies
  • 0 views
  • Added October 17, 2026
ai-agentsgoapi

Works with

  • cursor
  • api
  • mcp

Security analysis

A100/100

Scanned October 17, 2026

npx -y skills add Brainrot-Creations/plugins --skill delegate --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Delegate?

Add the live security badge to your README. It updates with every re-scan.

Security grade badge for Delegate
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/brainrot-creations-delegate-df42db51/badge)](https://www.skillsdirectory.com/skills/brainrot-creations-delegate-df42db51)

More formats (shields.io, HTML) on the badges page. Keep it an A: scan every change in CI with Pro.

Download with Pro
SKILL.md
---
name: delegate
description: Delegate a sub-task to a Cursor agent. Use when a task is better handled by a Cursor agent (e.g. complex file editing, multi-step coding tasks, research with web access).
---

Use the `cursor-agents` MCP tools to break work into sub-tasks and delegate them to Cursor agents.

## Synchronous delegation (need result now)

Use `cursor_run` when you need the output before continuing:

```
cursor_run(
  prompt="<full task description with all context the agent needs>",
  cwd="/path/to/project"   # optional, defaults to current directory
)
```

Returns `{ text: "<agent output>", stop_reason: "..." }`.

## Background delegation (parallel work)

Use `cursor_task_submit` to fire off tasks and continue working:

1. Submit one or more tasks:
   ```
   cursor_task_submit(name="Refactor auth module", prompt="...", cwd="...")
   cursor_task_submit(name="Write tests for API", prompt="...", cwd="...")
   ```

2. Check status:
   ```
   cursor_task_status(task_id="<id>")
   ```

3. Fetch result when completed:
   ```
   cursor_task_result(task_id="<id>")
   ```

4. See all tasks:
   ```
   cursor_tasks_list()
   ```

## Writing good prompts for Cursor agents

- Include full context — the agent has no knowledge of what you've done so far
- Specify the working directory if the task involves files
- Be explicit about what "done" looks like (files to edit, tests to pass, output expected)
- If the task spans multiple files, list the key ones

Attribution

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments

Loading comments…

Newsletter

Get the weekly list of safe new skills, and the ones we pulled.