cd into the repo, run predev, and the agent works on your files where they live.
1
Launch in your repo
/reverse whenever you’re ready.2
Reverse-engineer the codebase with /reverse
/arch shows the resulting architecture graph right in the terminal, and the agent plans future work against it instead of rediscovering your codebase every session.3
Sprint on new features
4
Review with git
The agent edits files directly in your working tree, so your normal workflow is the review process:Stage, commit, and push on your own terms. Parallel sessions (
/fork, /sprint) work in isolated git worktrees so they never collide with your checkout or with each other; their work lands back in your main workspace when they finish.Everything stays in sync with the web workspace. The reverse-engineered architecture, Kanban board, and roadmap for this repo are all there when you open the same project at pre.dev.
Tips
- One directory, one project. Relaunching
predevin the same folder resumes the same project — history, sessions, and settings included. Usepredev --newif you want a clean slate for the same directory. - Re-run
/reverseafter big changes. If the codebase shifts significantly (a large merge, a refactor done outside pre.dev), reverse-engineer again so the architecture graph matches reality.
Next steps
Command reference
Every slash command, grouped by what it does.
CLI overview
Install, first run, and when to use the CLI vs the web.

