dmux-workflows

Name: dmux-workflows
Availability: InStock
Author: sakamoto-family-smile

Coordinate parallel AI agent sessions across multiple harnesses with dmux.

Updated Apr 13, 2026

Search Tags:#multi-agent #orchestration #tmux #parallel #workflows #harness #dmux

Ready to run

npx skills add https://github.com/sakamoto-family-smile/agent_monorepo --skill dmux-workflows-sakamoto-family-smile

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: dmux-workflows
Source: https://github.com/sakamoto-family-smile/agent_monorepo/tree/main/.claude/skills/ecc/dmux-workflows
Command: npx skills add https://github.com/sakamoto-family-smile/agent_monorepo --skill dmux-workflows-sakamoto-family-smile

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Orchestrates parallel AI agent sessions across Claude Code, Codex, OpenCode, and other harnesses using dmux, a tmux pane manager, to reduce idle time and improve cross-harness productivity.

Core Features & Use Cases

Pattern 1: Research + Implement — Split research and implementation into parallel tracks to accelerate learning and delivery.
Pattern 2: Multi-File Feature — Parallelize work across independent files (docs, code, tests) with coordinated integration.
Pattern 3: Test + Fix Loop — Run tests in one pane and implement fixes in another to shorten feedback cycles.
Pattern 4: Cross-Harness — Use different tools for different tasks to optimize throughput (Claude Code, Codex, Claude Code Task tool, etc.).
Pattern 5: Code Review Pipeline — Parallelize security, performance, and test-review perspectives and merge results into a single report.
ECC Helper — External helper for git worktrees and tmux orchestration to plan and execute multi-pane sessions.

Quick Start

Start a dmux session and create parallel agent panes to run your tasks.

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 agents in tmux to speed up coding workflows?▼

You can run parallel AI agents in tmux by using a pane manager to orchestrate multiple sessions concurrently. This reduces idle time by splitting research, implementation, and testing into coordinated tracks across different harnesses like Claude Code and Codex.

Can I use Claude Code and Codex together in the same multi-agent workflow?▼

Yes, you can use Claude Code and Codex together in a multi-agent workflow. Cross-harness coordination lets you assign different tools to different panes, optimizing throughput by matching specific AI harnesses to specialized tasks like research or implementation.

What is the best way to parallelize a test and fix loop with multiple AI agents?▼

The best way to parallelize a test and fix loop is to run tests in one tmux pane and implement fixes in another. This shortens feedback cycles by allowing concurrent execution, letting one agent validate while another immediately applies the required code corrections.

How do you coordinate multiple AI agents to review code for security and performance?▼

You coordinate multiple AI agents for code review by parallelizing different review perspectives across panes. Agents analyze security, performance, and tests simultaneously, merging their individual results into a single comprehensive report for faster pipeline execution.

Does multi-agent orchestration require a specific environment to manage panes?▼

Multi-agent orchestration requires a tmux environment to manage panes. An external helper handles git worktrees and tmux orchestration to plan and execute multi-pane sessions, ensuring parallel AI agents operate without overlapping workspace conflicts.

When should I use parallel agent sessions instead of a single AI coding assistant?▼

You should use parallel agent sessions instead of a single assistant when tasks can be split into independent tracks, such as multi-file features or research and implementation. Parallel workflows reduce idle time and accelerate delivery compared to sequential processing.