dmux-workflows

Name: dmux-workflows
Availability: InStock
Author: cescrafli

Coordinate parallel AI agent sessions across harnesses using dmux panes.

Updated Mar 26, 2026

Search Tags:#agents #orchestration #tmux #parallel #workflows #dmux #harnesses

Ready to run

npx skills add https://github.com/cescrafli/compyrasion --skill dmux-workflows-cescrafli

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: dmux-workflows
Source: https://github.com/cescrafli/compyrasion/tree/main/skills/dmux-workflows
Command: npx skills add https://github.com/cescrafli/compyrasion --skill dmux-workflows-cescrafli

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Orchestrates parallel AI agent sessions using dmux, a tmux-based pane manager, to streamline multi-harness workflows across Claude Code, Codex, OpenCode, and other systems.

Core Features & Use Cases

Parallel agent panes: Manage multiple agent sessions in parallel with deterministic pane behavior.
Cross-harness orchestration: Coordinate tasks across Claude Code, Codex, OpenCode, and others for faster iteration.
Pattern-driven workflows: Supports patterns like Research + Implement, Multi-File Feature, Test + Fix, and Code Review pipelines.

Quick Start

Start a dmux session and create agent panes for parallel workflows, then merge results back into the main session.

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 a single terminal?▼

You can run parallel AI agent sessions by using dmux to orchestrate multiple tmux panes, allowing you to coordinate tasks across different harnesses like Claude Code and Codex simultaneously for faster iteration.

Can I coordinate tasks across Claude Code and Codex at the same time?▼

Yes, cross-harness orchestration allows you to coordinate tasks across Claude Code, Codex, and OpenCode simultaneously, enabling faster iteration by distributing work across multiple AI systems in parallel panes.

Do I need tmux to manage parallel AI coding workflows?▼

Yes, you need a tmux-enabled terminal and the dmux installation to manage parallel AI coding workflows, as dmux relies on tmux-based pane management to ensure deterministic behavior across agent sessions.

What is the best way to structure multi-file feature development with AI agents?▼

The best way to structure multi-file feature development is by applying pattern-driven workflows like Research + Implement or Multi-File Feature, creating independent panes with clear task boundaries before merging results back into the main session.

How do parallel agent panes handle code review and testing pipelines?▼

Parallel agent panes handle code review and testing through pattern-driven workflows like Test + Fix and Code Review pipelines, managing multiple agent sessions in parallel with deterministic pane behavior to accelerate the review process.

When should I avoid using parallel AI sessions for development tasks?▼

You should avoid using parallel AI sessions when you lack clear task boundaries, as dmux requires independent panes and planned merges to function correctly, making it unsuitable for tightly coupled or interdependent coding tasks.