affaan-m avatar

Dmux Workflows

This is a patterns guide for running multiple AI coding agents in parallel using dmux, a tmux-based pane manager. You create separate panes with `n`, each running its own agent session (Claude Code, Codex, whatever), then merge results back with `m`. The skill covers five solid patterns: research plus implementation in parallel, splitting multi-file features, test-and-fix loops, cross-harness work, and parallel code reviews. It also documents an ECC helper script that automates git worktree creation per agent so they don't step on each other's file changes. Useful when you have a chunky task that splits cleanly into independent pieces, though you'll burn tokens faster since each pane is a full session.

skills.sh installs
5.4K
GitHub stars
300.3K
last updated
Aug 21, 2026

Install

$ npx -y skills add affaan-m/ecc --skill dmux-workflows --agent claude-code

Installs into .claude/skills of the current project.

Files

dmux Workflows

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

When to Activate

  • Running multiple agent sessions in parallel
  • Coordinating work across Claude Code, Codex, and other harnesses
  • Complex tasks that benefit from divide-and-conquer parallelism
  • User says "run in parallel", "split this work", "use dmux", or "multi-agent"

What is dmux

dmux is a tmux-based orchestration tool that manages AI agent panes:

  • Press n to create a new pane with a prompt
  • Press m to merge pane output back to the main session
  • Supports: Claude Code, Codex, OpenCode, Cline, Gemini, Qwen

Install: Install dmux from its repository after reviewing the package. See github.com/standardagents/dmux

Quick Start

# Start dmux session
dmux

# Create agent panes (press 'n' in dmux, then type prompt)
# Pane 1: "Implement the auth middleware in src/auth/"
# Pane 2: "Write tests for the user service"
# Pane 3: "Update API documentation"

# Each pane runs its own agent session
# Press 'm' to merge results back

Workflow Patterns

Pattern 1: Research + Implement

Sponsors

Details

Repository
github.com/affaan-m/ecc
Categories
AI & Agent Building, Automation & Workflows, CLI & Terminal
First seen
Jul 14, 2026

More from affaan-m/ecc

All 263
1affaan-m avatargan-style-harnessaffaan-m/eccGAN-inspired Generator-Evaluator agent harness for building high-quality applications autonomously. Based on Anthropic's March 2026 harness design paper.5.4Kskills.sh installs
2affaan-m avatarralphinho-rfc-pipelineaffaan-m/eccRFC-driven multi-agent DAG execution pattern with quality gates, merge queues, and work unit orchestration.5.4Kskills.sh installs
3firebase avatarfirebase-local-env-setupfirebase/agent-skillsBare minimum INITIAL setup for getting started with Firebase (Node.js, CLI installation, first-time login). Use ONLY for first-time setup. For updating, trouble5.1Kskills.sh installs
4czlonkowski avatarn8n-code-pythonczlonkowski/n8n-skillsWrite Python code in n8n Code nodes. Use when writing Python in n8n, using _input/_json/_node syntax, working with standard library, or need to understand Pytho5.1Kskills.sh installs
5github avatarpremium-frontend-uigithub/awesome-copilotA comprehensive guide for GitHub Copilot to craft immersive, high-performance web experiences with advanced motion, typography, and architectural craftsmanship.5Kskills.sh installs
6forcedotcom avatarexperience-ui-bundle-agentforce-client-generateforcedotcom/sf-skillsUse this skill when the user asks to add, embed, integrate, configure, style, or remove an agent, chatbot, chat widget, conversation client, or AI assistant in 5Kskills.sh installs