A thoughtful wrapper around multiple AI code backends (Codex, Claude, Gemini, OpenCode) that actually handles the orchestration layer most of us end up building anyway. The parallel execution model is the real story here: you can queue up a code explorer task, an architect task, and an implementation task with dependency chains, all in one config block. Agent presets let you bundle backend, model, and prompts into reusable personas like code-explorer or develop. Auto-detects your stack from go.mod or package.json and injects relevant skill files. The worktree isolation flag is a nice touch for keeping experimental changes off your main branch. If you're already scripting multi-step AI workflows or switching between models based on task type, this consolidates that into one tool.
npx skills add https://github.com/cexll/myclaude --skill codeagent