Using RigOne
Install it, build a workflow, run it against a project and read what happened.
Start the step-by-step tutorialStart here
- Getting started Install RigOne, check that the download is genuine and open it for the first time.
- Tutorial: your first run, step by step This tutorial takes you from an empty RigOne to a finished run and a goal handed to Auto.
- Concepts RigOne uses a small, fixed vocabulary.
- The window and the sidebar The RigOne window has three columns.
Sidebar: run the work
Sidebar: build the rig
Sidebar: what agents know
- Knowledge Knowledge (⌘5) holds what agents take into their prompts.
- Context Context (⌘6) holds named sets of material an agent works from.
- Skills Skills shows the skills the open project gives its agents, read from .claude/skills and .agents/skills.
- Lab Lab (⌘7) lets you measure an agent, a skill or a workflow on cases from your own code.
Settings and your phone
Trust and data
- Checks and second opinions When a step finishes, RigOne runs the checks itself; it does not ask the agent whether it worked.
- Where the changes go Each step works in its own copy of your code, so agents cannot trip over each other.
- Safety model RigOne treats orchestration failures as product failures, not terminal noise.
- Files on disk A project's .rig-one/ folder is plain files and safe to commit.