Name: cursor-agent-supervisor
Author: ypares

Imported from ypares/agent-skills (cursor-agent-supervisor/SKILL.md). Install upstream with npx skills add ypares/agent-skills --skill cursor-agent-supervisor. Copyright stays with the author.

Agent Supervisor

You can start subagents (e.g. to work on a specific JJ revision) with:

# Create a conversation with a sub-agent:
cursor-agent --print --model <model-name> create-chat  # Prints a conversation uuid

# Give a task to the sub-agent: (command will finish when sub-agent is done)
cursor-agent --print --resume <conversation-uuid> "...description of the subagent's task..."

Model Selection

cursor-agent --print --model unknown-model will print an error that will list available models. Unless you know which model is best for the task, just use sonnet-4.5 by default.

Invocation

Important: Sub-agent tasks can take several minutes. Always use a longer timeout:

# In your Shell tool call, set timeout to 10 minutes
timeout: 600000

The --print flag makes the sub-agent run on its own, and reply only once it is done.

Setting Things up for the Sub-agent

Prepare things up so the agent can focus on its task (eg. if using JJ, don't ask them to run jj commands unless really necessary. Notably run jj edit yourself first to get into the revision where the work should be done). Ideally, the sub-agent should only have to read your instructions, hack on code, run build/tests, hack on code, etc. until your instructions are implemented, and then reply with a final answer. YOU are in charge of bookkeeping, not them. YOU have the big picture, they don't.

Giving Good Instructions

Give the subagent the instructions they will need to complete the task, but do not overwhelm them.

Do:

Provide a clear, specific goal
List key files to read/modify
Specify what "done" looks like
Include relevant patterns to follow or reference implementations
Tell them which skills to load if needed

Don't:

Dump or link to entire skills when they only need a subset
Include irrelevant context
Leave success criteria ambiguous

Task Description Template

Work on [specific task] in [repo/directory].

**Setup:**
- Skills to load or files to read IN FULL
- Summarized instructions from skills or files, tailored to the task

**Goal:**
[Clear description of what to implement/fix]

**Key files:**
- path/to/main/file.ts - [why it matters]
- path/to/reference.ts - [pattern to follow]

**Requirements:**
- [Specific requirement 1]
- [Specific requirement 2]

**Done when:**
- [Testable criterion 1]
- [Testable criterion 2]
- [e.g., "pnpm -F @pkg lint passes"]

After Sub-agent Completes

Always verify the sub-agent's work:

Check what changed: check the commit/revision diff, and adequation with the task
Review the actual code if the changes are non-trivial
Run verification commands (tests, type-check, lint)
Update task status based on results (if using jj-todo-workflow)

When Things Go Wrong

If the sub-agent:

Fails or errors out: Read the output, fix any blocking issues, retry with more context
Produces incomplete work: Continue the work yourself or spawn another sub-agent with clarified instructions
Goes off track: Review what happened, potentially revert changes, retry with tighter constraints
Gets stuck on tooling: May need to provide explicit commands or paths

Install cursor-agent-supervisor and it becomes one more candidate the router can pick - when it fits.

A listing is a routing target with a manifest: what it does, which domains it covers, what it costs and who publishes it. Once installed it sits beside your own models and tools, is scored like any other candidate for each request, and shows up in the trace when it wins. Ratings come from workspaces that installed it, one per account.

{ "ocm": "1", "id": "ypares-agent-skills-cursor-agent-supervisor", "kind": "skill", "name": "cursor-agent-supervisor", "description": "Offloading tasks with a well-defined scope to sub-agents, for instance to use a sub-agent to implement a set of specs. Use this skill whenever a task should not need a broad knowledge of the whole project", "publisher": "ypares", "version": "1.0.0", "capabilities": { "domains": [ "general" ], "tags": [ "skill-md", "skills-sh" ], "languages": [ "en" ] }, "quality_prior": 0.6, "examples": [ "Offloading tasks with a well-defined scope to sub-agents, for instance to use a sub-agent to implement a set of specs. Use this skill whenever a task should not need a broad knowledge of the whole project" ], "primary": false, "metadata": { "source": { "provider": "skills.sh", "repository": "https://github.com/ypares/agent-skills", "path": "cursor-agent-supervisor/SKILL.md", "ref": "HEAD", "url": "https://github.com/ypares/agent-skills/blob/HEAD/cursor-agent-supervisor/SKILL.md", "key": "ypares/agent-skills/cursor-agent-supervisor/SKILL.md" } }, "instructions": "# Agent Supervisor\n\nYou can start subagents (e.g. to work on a specific JJ revision) with:\n\n```bash\n# Create a conversation with a sub-agent:\ncursor-agent --print --model <model-name> create-chat # Prints a conversation uuid\n\n# Give a task to the sub-agent: (command will finish when sub-agent is done)\ncursor-agent --print --resume <conversation-uuid> \"...description of the subagent's task...\"\n```\n\n## Model Selection\n\n`cursor-agent --print --model unknown-model` will print an error that will list available models.\nUnless you know which model is best for the task, just use `sonnet-4.5` by defau", "cost": { "context_tokens": 805 } }

cursor-agent-supervisor

About

Agent Supervisor

Model Selection

Invocation

Setting Things up for the Sub-agent

Giving Good Instructions

Task Description Template

After Sub-agent Completes

When Things Go Wrong

Install cursor-agent-supervisor and it becomes one more candidate the router can pick - when it fits.

Use it

Manifest

Reviews