From cursor-agents
Delegates sub-tasks to Cursor agents with sync or async execution. Use for complex file editing, multi-step coding, or research with web access.
How this skill is triggered — by the user, by Claude, or both
Slash command
/cursor-agents:delegateThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
Use the `cursor-agents` MCP tools to break work into sub-tasks and delegate them to Cursor agents.
Use the cursor-agents MCP tools to break work into sub-tasks and delegate them to Cursor agents.
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: "..." }.
Use cursor_task_submit to fire off tasks and continue working:
Submit one or more tasks:
cursor_task_submit(name="Refactor auth module", prompt="...", cwd="...")
cursor_task_submit(name="Write tests for API", prompt="...", cwd="...")
Check status:
cursor_task_status(task_id="<id>")
Fetch result when completed:
cursor_task_result(task_id="<id>")
See all tasks:
cursor_tasks_list()
npx claudepluginhub brainrot-creations/claude-plugins --plugin cursor-agentsDelegates sub-tasks to OpenAI Codex CLI for complex file editing, multi-step coding, or automated code generation. Supports both synchronous and background execution.
Orchestrates parallel AI coding agents in isolated Git worktrees using Agency CLI. Create, list, merge tasks; attach files; manage tmux sessions for simultaneous coding.
Guides Cursor PM ↔ Claude Code two-agent workflow with Plans.md task management and handoff commands. For workflow orientation, not solo implementation or handoff execution.