orchestrate

Manage multiple Claude code agents across git worktrees and tmux sessions.

Updated Apr 28, 2026
One-click install
npx skills add https://github.com/aoxendine3/sovra-core-lighthouse --skill orchestrate-aoxendine3
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: orchestrate
Source: https://github.com/aoxendine3/sovra-core-lighthouse/tree/main/AutoGPT/.claude/skills/orchestrate
Command: npx skills add https://github.com/aoxendine3/sovra-core-lighthouse --skill orchestrate-aoxendine3

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) and references (resource) and assets (resource) components.

What problem does it solve?

This Skill streamlines the management of multiple AI agents by overseeing their creation, monitoring, and recycling, thus reducing manual intervention.

Core Features & Use Cases

  • Fleet Supervision: Enables natural language commands to manage numerous Claude agents operating in tmux sessions.
  • Worktree & Branch Management: Discovers spare git worktrees, spawns agents on specified tasks, and recycles worktrees efficiently.
  • Use Case: Automate the process of coordinating a fleet of code agents working in parallel, with status checks and safe aborts as needed.

Quick Start

Ask the system to start supervising agents for a list of tasks and monitor their progress without manual script execution.

Frequently Asked Questions about orchestrate

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

FAQPage Schema
How do I manage multiple Claude code agents running in parallel?

To manage multiple Claude code agents running in parallel, you can use natural language commands to supervise a fleet of agents operating across separate tmux sessions, handling their spawning, monitoring, and recycling automatically.

What is the best way to coordinate AI agents using git worktrees?

Coordinating AI agents using git worktrees involves discovering spare worktrees, spawning agents on specified tasks within those branches, and recycling the worktrees efficiently once tasks are complete to ensure safe parallel execution.

Can I automate agent lifecycle handling and status updates in tmux?

Yes, you can automate agent lifecycle handling and status updates in tmux by issuing natural language commands to start supervising agents, monitor their progress, and safely abort or recycle them without manual script execution.

How do I recover a code agent from a failed task in a parallel workflow?

To recover a code agent from a failed task in a parallel workflow, the orchestration system ensures safe operation and easy recovery by allowing safe aborts and recycling of git worktrees and tmux sessions as needed.

Do I need tmux and git worktrees to run parallel agent tasks?

Yes, tmux and git worktrees are required to run parallel agent tasks, as the system relies on discovering spare worktrees to spawn agents and managing their isolated execution environments across separate tmux sessions.