What problem does it solve? Coordinating multiple AI coding agents on large tasks is slow and error-prone when done sequentially in a single session. This Skill provides patterns for running parallel agent sessions in tmux panes, so independent workstreams like research, implementation, testing, and review can proceed simultaneously. ## Core Features & Use Cases - Parallel Agent Orchestration: Launch and manage multiple agent panes (Claude Code, Codex, OpenCode, Gemini, and more) with dmux's create-and-merge workflow. - Five Workflow Patterns: Ready-made patterns for research-plus-implementation, multi-file features, test-and-fix loops, cross-harness delegation, and parallel code review pipelines. - Git Worktree Isolation: Guidance for isolating file changes per agent using git worktrees, plus an ECC helper script that automates branch-backed worktrees, per-worker task files, and tmux pane launching. - Use Case: Split a billing feature into three panes—one for database migrations, one for API endpoints, one for UI components—then merge the results and integrate in the main pane. ## Quick Start Ask the agent to split the current task into parallel dmux panes, for example by saying "use dmux to run the auth implementation and the test writing in parallel panes and merge the results."
