/spec,
/build, /evaluate, /diagnose, /optimize). You can enter at any stage; Helix then suggests the
next one.
After the loop, when an agent has passed its checks, the ship step (
/ship) takes it out: a pull
request, a changelog, CI, and a watch on the agent’s traces after it deploys. Ship is not a sixth
stage. Only you can start it, and it asks before merging. See Ship.
You stay in control
No stage advances on its own. Every change to your code or config is held for your explicit approval before it lands, and nothing runs until you ask — Helix is on-demand, not a background process. The stages are also kept separate on purpose: Evaluate only decides pass or fail and routes any failures to Diagnose, which finds the causes and proposes the fixes. The stage that scores your agent is never the one that changes it, so a passing verdict can’t come from the tool that was supposed to earn it.Enter anywhere
You don’t have to start at Spec. Point Helix at an agent you already have and ask it to evaluate; it will derive criteria from your traces and score the current behaviour. Ask it to diagnose and it will root-cause what the evaluation flagged.Evaluate and Diagnose are part of the
helix binary; there is nothing else to install. See
the lifecycle pages.