stampede

Orchestrate multiple AI agents across tmux panes with filesystem IPC.

2|2|Updated Mar 6, 2026
One-click install
npx skills add https://github.com/DUBSOpenHub/copilot-skills --skill stampede
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: stampede
Source: https://github.com/DUBSOpenHub/copilot-skills/tree/main/stampede
Command: npx skills add https://github.com/DUBSOpenHub/copilot-skills --skill stampede

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

This Skill automates complex, multi-agent workflows by decomposing tasks, dispatching them to independent AI agents in separate terminal panes, and synthesizing their results, all while ensuring fault tolerance and conflict detection.

Core Features & Use Cases

  • Multi-Agent Orchestration: Manages a fleet of AI agents for parallel task execution.
  • Cross-Terminal Coordination: Utilizes tmux panes and filesystem IPC for seamless communication.
  • Fault Tolerance: Implements dead agent recovery and atomic operations.
  • Conflict Detection: Identifies and reports on overlapping file modifications.
  • Use Case: Imagine you need to refactor a large codebase. Stampede can split the codebase into manageable chunks, assign each chunk to a different AI agent for refactoring, monitor their progress, and merge the changes back together, flagging any conflicts.

Quick Start

Use stampede to launch 8 agents on your current repository to add tests, fix errors, and update documentation.

Frequently Asked Questions about stampede

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

FAQPage Schema
How do I coordinate multiple AI agents for parallel code refactoring?

Multi-agent orchestration coordinates independent AI agents across separate tmux panes via filesystem IPC, dispatching parallel work units for complex task decomposition. It manages atomic operations, dead agent recovery, and conflict-aware synthesis to merge refactored code.

Can I run parallel AI agents in tmux for workflow automation?

Running parallel AI agents in tmux uses filesystem IPC for cross-terminal coordination and workflow automation. The system supports task splitting, dead agent recovery, and conflict-aware synthesis to manage complex multi-agent execution.

What happens if an AI agent crashes during multi-agent task execution?

Dead agent recovery handles AI agent crashes during multi-agent task execution by ensuring fault tolerance through atomic operations. This preserves completed parallel work units and maintains workflow stability across terminal panes.

How does conflict detection work when multiple agents modify the same codebase?

Conflict detection identifies and reports overlapping file modifications when multiple agents modify the same codebase simultaneously. It uses conflict-aware synthesis and shadow scoring during auto-merging to flag overlapping edits in parallel work units.

Do I need any specific dependencies to orchestrate AI agents across terminals?

No specific dependencies are required to orchestrate AI agents across terminals beyond tmux panes and filesystem IPC. The system operates independently using scripts and references for task decomposition and parallel execution.