dmux-workflows

Orchestrate parallel AI agent sessions across dmux panes.

1|1|Updated Mar 31, 2026
One-click install
npx skills add https://github.com/zardusai-cyber/zardus_setup --skill dmux-workflows-zardusai-cyber
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: dmux-workflows
Source: https://github.com/zardusai-cyber/zardus_setup/tree/main/ecc/skills/dmux-workflows
Command: npx skills add https://github.com/zardusai-cyber/zardus_setup --skill dmux-workflows-zardusai-cyber

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Coordinating multiple AI agent sessions across dmux to enable parallel exploration and faster progress in complex, multi-harness workflows.

Core Features & Use Cases

  • Parallel agent panes for Claude Code, Codex, OpenCode, and other harnesses.
  • Pattern-based workflows for research + implementation, test + fix, and cross-harness orchestration.
  • Clear pane creation and merging instructions to consolidate results.

Quick Start

Start a dmux session and create panes for each agent task.

Frequently Asked Questions about dmux-workflows

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

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

You can coordinate parallel AI agent sessions using dmux, a tmux pane manager designed for agent harnesses. It provides pattern-based workflows for research, implementation, and testing across multiple panes.

Can I run Claude Code and Codex agents in parallel using tmux pane management?

Yes, dmux supports parallel agent panes for Claude Code, Codex, OpenCode, and other harnesses. You can create independent panes for each agent task and orchestrate cross-harness workflows.

What is the best way to consolidate outputs from multiple AI agents running in parallel?

The best way to consolidate outputs from parallel AI agents is through dmux's pane creation and merging instructions, which guide you in combining results from independent agent tracks into a single consolidated output.

How do I set up a research and implementation workflow with parallel AI agents?

Set up a research and implementation workflow by starting a dmux session and creating separate tmux panes for each agent task. dmux provides clear patterns for splitting research and implementation tracks.

Do I need tmux to orchestrate parallel AI workflows with dmux?

Yes, tmux is required because dmux is built as a tmux pane manager specifically for agent harnesses. It relies on tmux to handle pane creation, interaction, and workflow orchestration.

What are the limitations of using tmux panes for parallel agent orchestration?

dmux focuses on lightweight parallelism orchestration and simple workflow patterns. It is designed for pane-based interaction and clear guidance on pane creation and merging, which may limit complex cross-harness coordination needs.