Reusing the checks a delegate already ran

The idea

After a delegated coding round, the platform reads which checks the delegate ran from its own record of that round. It reuses those results only when the code is unchanged, and runs the checks again otherwise.

The problem
A delegate's log can be forged or stale, but running every check again wastes time.
Why it matters
Genuine runs on the same tree count, and claimed runs do not.
Where it stands
In production as of

Recorded evidence

  • Production · Genuine round passes, old consumer fails

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

  • Native implementation round

    Implementation runs as one sandboxed Claude Code or Codex session, briefed by a compiled file. Its tools go through the gateway hook. The supervisor gets back only the report, the diff and the checks.

  • Native change-proof engine

    One engine finds the change kinds from the diff and the outputs. Each kind needs its own typed proof: a UI recording, a real HTTP exchange, tests, a query, or exact document bytes. Only a person can waive a check, and a waived check shows as not passed.

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.