skills.rest
Femad-6
Femad-6COMMUNITY
Explore all skills by this author →
WebsiteGitHub

dmux-workflows

Orchestrates parallel AI agent sessions across tmux panes using dmux.

Updated Mar 25, 2026
Search Tags:#claude code#multi-agent#orchestration#tmux#git worktree#dmux#parallel workflows
One-click install
npx skills add https://github.com/Femad-6/my-skills --skill dmux-workflows-femad-6
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: dmux-workflows
Source: https://github.com/Femad-6/my-skills/tree/main/.github/skills/dmux-workflows
Command: npx skills add https://github.com/Femad-6/my-skills --skill dmux-workflows-femad-6

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? Coordinating multiple AI agent sessions manually is error-prone and slow; this Skill provides patterns for running parallel agent workflows across Claude Code, Codex, OpenCode, and other harnesses using dmux, a tmux pane manager. ## Core Features & Use Cases - Parallel Agent Orchestration: Create and manage multiple agent panes in a single tmux session, then merge results back to the main session. - Workflow Patterns: Includes five ready-made patterns covering research-plus-implementation, multi-file features, test-and-fix loops, cross-harness work, and parallel code review. - Git Worktree Isolation: Use separate worktrees per pane to avoid file conflicts, with an ECC helper script that automates worktree creation, task files, and tmux pane launching. - Use Case: Split a large feature into independent tracks—one pane builds database migrations, another builds API endpoints, a third builds UI components—then merge all outputs for integration. ## Quick Start Ask the agent to split the current task into parallel dmux panes, for example by saying "run these three independent tasks in parallel with dmux and merge the results."

Frequently Asked Questions about dmux-workflows

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

FAQPage Schema
How do I run multiple AI agents in parallel with tmux?▼

Use dmux, a tmux pane manager for AI agents. Start a dmux session, press 'n' to create a new pane with a prompt for each agent task, and press 'm' to merge pane output back into the main session.

What tasks should I parallelize across agent panes?▼

Parallelize only independent tasks with clear boundaries, such as separate files or concerns. Good examples include research plus implementation, multi-file features, and parallel security, performance, and test-coverage reviews.

Which AI coding tools does dmux support?▼

dmux supports Claude Code, Codex, OpenCode, Cline, Gemini, and Qwen. Each pane runs its own full agent session, so you can mix harnesses for cross-harness workflows.

How do I avoid merge conflicts with parallel agents?▼

Use git worktrees to isolate file changes per pane. Create a branch-backed worktree per worker, run each agent in its own worktree, then merge the branches when the work is done.

What are the limitations of running parallel agent panes?▼

Each pane is a full agent session consuming API tokens, so keep total panes under five or six. Tasks that depend on each other's output should not be parallelized, and tmux must be installed first.

Related Skills

Explore More Software Engineering Skills→
mirzadhammirzadham

dmux-workflows

Orchestrates parallel AI agent sessions across tmux panes using dmux.

Community
Intermediate
TyrizxTyrizx

merge

Merge a topic branch into the base branch and resolve conflicts in the main worktree.

Official
Intermediate
JhabbigJhabbig

multi-reviewer-patterns

Coordinates parallel code reviews and consolidates overlapping findings into a prioritized report.

Community
Advanced
VetCodersVetCoders
1

vc-delegate

Delegate bounded tasks to Claude subagents via the Task tool.

Official
Intermediate