What problem does it solve? Coordinating multiple AI agent sessions manually is chaotic and error-prone. This Skill provides structured patterns for running parallel agent workflows with dmux, a tmux pane manager, so you can divide complex tasks across Claude Code, Codex, OpenCode, and other harnesses without losing track of results. ## 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. - Git Worktree Integration: Isolate file changes per agent pane using git worktrees to prevent merge conflicts when panes touch overlapping files. - Merge and Troubleshooting Guidance: Best practices for merging pane output, managing token usage, and resolving common tmux or pane issues. - Use Case: You need to ship a billing feature fast. Spawn three dmux panes—one for database migrations, one for API endpoints, one for UI components—then merge the results and integrate in the main session. ## Quick Start Ask the agent to split your current task into parallel dmux panes, for example by saying "use dmux to run the auth implementation and the test writing in parallel panes".
