team

Manage long-lived provider LLM teammates within Claude Code workflows.

201|27|Updated May 30, 2026
One-click install
npx skills add https://github.com/ethanhq/cc-fleet --skill team-ethanhq
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: team
Source: https://github.com/ethanhq/cc-fleet/tree/main/skills/team
Command: npx skills add https://github.com/ethanhq/cc-fleet --skill team-ethanhq

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) components.

What problem does it solve?

This Skill addresses the challenge of managing long-term collaboration with third-party LLM providers, enabling seamless integration into Claude Code's agent teams.

Core Features & Use Cases

  • Long-Lived Collaboration: Spawn LLM teammates that persist across turns, facilitating multi-turn discussions and sustained parallel work.
  • Provider Integration: Work with any Anthropic- or OpenAI-compatible model, including your Codex subscription, without a Claude subscription.
  • Use Case: For a sustained parallel build/work scenario, spawn multiple teammates to work on different files simultaneously, or when you need a collaborator for a multi-turn task.

Quick Start

Use the 'team' skill to spawn a long-lived LLM teammate for a sustained task. Example: /team spawn --as worker-1 --model strong

Frequently Asked Questions about team

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I orchestrate long-lived LLM teammates for sustained parallel work in Claude Code?

You can orchestrate long-lived LLM teammates by using the team skill to spawn provider LLM instances that persist across turns, facilitating multi-turn discussions and sustained parallel work within Claude Code workflows. Use the spawn command to assign tasks and collect results.

Can I use OpenAI-compatible models as teammates without a Claude subscription?

Yes, you can integrate any Anthropic- or OpenAI-compatible model, including your Codex subscription, as a long-lived teammate without requiring a Claude subscription. The skill requires Claude Code for orchestration but uses provider-specific LLM APIs for backend execution.

What is the best way to manage task assignment and resource cleanup for provider LLM teammates?

The best way to manage task assignment and resource cleanup is using the team skill's lifecycle management, which handles spawning long-lived provider LLM teammates, collecting their results, and executing resource cleanup automatically within Claude Code workflows.

How do I spawn multiple LLM teammates to work on different files simultaneously?

To spawn multiple LLM teammates for simultaneous file work, use the spawn command with distinct identifiers like `--as worker-1` and specify the model strength. This enables sustained parallel build scenarios where teammates work on different files concurrently.

What are the limitations of using long-lived provider LLM teammates for multi-turn collaboration?

Limitations include the requirement for Claude Code to orchestrate the provider LLM APIs and the need for provider-specific APIs for backend execution. Resource cleanup must be managed properly to avoid lingering instances after sustained multi-turn collaboration ends.