agent-teams

Coordinates multi-agent teams with shared task lists and file-based mailboxes.

99|16|Updated Feb 7, 2026
One-click install
npx skills add https://github.com/tmustier/pi-agent-teams --skill agent-teams-tmustier
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: agent-teams
Source: https://github.com/tmustier/pi-agent-teams/tree/main/skills/agent-teams
Command: npx skills add https://github.com/tmustier/pi-agent-teams --skill agent-teams-tmustier

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Coordinate multi-agent teamwork by spawning and coordinating teammate agents that work in parallel on shared task lists, using file-based mailboxes for messages and lifecycle management.

Core Features & Use Cases

  • Spawns and coordinates teammate agents that poll for tasks, execute them, and report back to the leader.
  • Shared task lists with statuses, owners, and dependencies to ensure correct sequencing and progress.
  • Mailbox-based communication with separate namespaces for team messages and task-specific notifications.
  • Configurable UI styles and support for custom team styles, plus lifecycle controls (start, shutdown, kill).
  • Supports long-running teams with per-session contexts and workplan governance for planning and coordination.

Quick Start

Spawn a team of teammates and begin coordinating tasks across your Pi sessions.

Frequently Asked Questions about agent-teams

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

FAQPage Schema
How do I coordinate multi-agent teamwork with shared task lists?

Multi-agent teamwork is coordinated by spawning teammate agents that poll for tasks, execute them, and report back to a leader. Shared task lists track statuses, owners, and dependencies to ensure correct sequencing and progress across parallel Pi sessions.

How does mailbox-based communication work for LLM agents?

Mailbox-based communication uses separate namespaces for team messages and task-specific notifications. Teammate agents poll these file-based mailboxes to receive instructions and report execution results back to the leader agent.

Can I spawn teammate agents that work in parallel on the same task list?

Yes, you can spawn teammate agents that work in parallel on shared task lists. The leader-teammate model supports task delegation, while task statuses and dependencies ensure correct sequencing and prevent conflicts during parallel execution.

What is the best way to manage the lifecycle of teammate agents across Pi sessions?

Managing the lifecycle of teammate agents involves using start, shutdown, and kill controls. These lifecycle commands support long-running teams with per-session contexts and workplan governance for continuous planning and coordination.

Do I need to configure UI styles for my agent teams?

Configuring UI styles is optional but supported. You can apply custom team styles to coordinate multi-agent teams, ensuring the interface presentation matches your preferred workplan governance and task-management visualization.