What problem does it solve? Coordinating multiple AI coding agents on large tasks is slow and error-prone when done sequentially; this Skill provides proven patterns for splitting work across parallel agent sessions and merging results safely. ## Core Features & Use Cases - Parallel Workflow Patterns: Five ready-made patterns including research-plus-implement, multi-file features, test-and-fix loops, cross-harness execution, and parallel code review. - Multi-Harness Support: Coordinates Claude Code, Codex, OpenCode, Cline, Gemini, and Qwen sessions in separate tmux panes. - Git Worktree Isolation: Guidance for running agents in separate worktrees to avoid file conflicts when panes touch overlapping code. - Use Case: Split a billing feature into three panes—one for database migrations, one for API endpoints, one for UI components—then merge all outputs and integrate in the main session. ## Quick Start Ask the agent to use dmux to split a large task into parallel panes, for example by saying "use dmux to run the schema work, API endpoints, and UI components in parallel agent sessions."