Stage exit checklists and loop limits

The idea

Each stage has an exit checklist. Code judges the clear items and System One the unclear ones. Repeated holds go to a person, and a loop guard stops the run when the same result repeats.

The problem
A stage could end with work missing, or a worker could loop forever.
Why it matters
A stage ends only when its items are met, and loops stop early.
Where it stands
In production as of

A step-by-step replay of this idea is not published yet. The library adds one when a recorded run shows it.

  • Nine-stage lifecycle; the builder never judges itself

    Each item records which stages apply (context, architecture, design, spec, tests, build, standards, verification, delivery), why, who decided and which gate enforces each. A verdict from the builder's own context counts as Unverified.

  • Code checks for code that AI workers operate

    A check without a model holds worker code to module size, header, import cycles, colocated tests, index entries and typed exports. It runs at act exit, in verification and in the platform verifier.

  • Gate ledger

    A registry names each gate and the failure it prevents. From records, it counts how often the gate caught that failure and how often a person overruled it.

Turn the numbers into shipped work.

Crewshal runs these choices for you: a persistent AI worker with memory and rules, on your Claude and Codex subscriptions.