Jev and Claude Code refactor pulls 31 yes-or-no checks out of model calls
A five-step playbook covers auditing a transcript, writing a schema, moving one decision first and handing low-confidence cases back to Opus, claiming 348ms per check and 93.3% of broken rules caught.
CLAUDE OPUS 5.5 + FABLE 5.1 + JEV ENGINEERING = THE CHEAPEST CODING LOOP YOU CAN RUN one real multi-file refactor in Claude Code hid 31 checks inside it did it pass, is it the right file, merge, retry or flag a person the core idea: 25-40% of model calls in any agent loop with a review step are checks Claude writes the code. Jev makes the calls who owns which job: > read a diff, write a review - Claude > does this pass, is this the right file - Jev > write the fix - Claude > merge, retry or flag a person - Jev > enforce the exact rule - your own code the numbers: > 348 ms per check > 93.3% of broken rules caught > TypeSafe's best case: 200x faster, 400x cheaper the playbook: 1. audit one real transcript and mark every yes-or-no moment 2. write the schema down: questions, answers, confidence lines 3. move one decision first, keep the rest of the loop as is 4. below the threshold, hand it back to Opus 5.5 or Fable 5.1 5. npx skills add typesafe-ai/skills --skill typesafe-ai the key insight: Jev can't hallucinate text because it never writes any but a bad schema lets it pick the wrong option with clean confidence so set the threshold per decision and spot-check the sure ones the engineer who cuts the review bill and keeps the code quality is the one who gets the raise
This post quotes another post: x.com/polydao/status/2103689373774483815