dmux-workflows

Orchestrate parallel AI agent sessions across Claude Code, Codex, and OpenCode with dmux.

1|Updated Mar 8, 2026
One-click install
npx skills add https://github.com/vinitgirdhar/GRID_ --skill dmux-workflows-vinitgirdhar
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: dmux-workflows
Source: https://github.com/vinitgirdhar/GRID_/tree/main/.agent/.agents/skills/dmux-workflows
Command: npx skills add https://github.com/vinitgirdhar/GRID_ --skill dmux-workflows-vinitgirdhar

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Orchestrate parallel AI agent sessions using dmux, a tmux-based pane manager for agent harnesses.

Core Features & Use Cases

  • Parallel orchestration: manage multiple agent panes in a single dmux session to run research, implementation, and testing in parallel.
  • Cross-harness coordination: coordinate tasks across Claude Code, Codex, OpenCode, and other tools for faster multi-agent workflows.
  • Best practices: use independent panes and git worktrees to avoid conflicts and improve throughput.

Quick Start

Start a dmux session and create parallel agent panes for your workload.

Frequently Asked Questions about dmux-workflows

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

FAQPage Schema
How do I run parallel AI agent sessions in tmux?

You can run parallel AI agent sessions in tmux by using dmux to manage multiple agent panes within a single session, allowing simultaneous research, implementation, and testing across different harnesses.

What is cross-harness coordination for AI agents?

Cross-harness coordination is the process of managing simultaneous tasks across Claude Code, Codex, and OpenCode, using dmux to coordinate multi-agent workflows and improve overall throughput.

Can I coordinate Claude Code and Codex in the same tmux session?

Yes, you can coordinate Claude Code and Codex in the same tmux session by using dmux to create independent panes for each harness, enabling parallel task execution and cross-harness coordination.

How do I avoid conflicts when running multiple AI agents in parallel?

To avoid conflicts when running multiple AI agents in parallel, use independent dmux panes and git worktrees to isolate each agent's working directory, preventing file overlaps and improving throughput.

What is the best way to merge tmux panes for AI agents?

The best way to merge tmux panes for AI agents is using dmux pane merging capabilities, which consolidates independent agent sessions back into a coordinated view for cross-harness workflows.