tstanmay13

An end-of-session learning ritual that converts finished work into durable understanding — by making you recall and reconstruct it before filling any gaps, instead of letting the AI's fluency stand in for your own.

Run a multi-session job as its orchestrator: plan, brief worker sessions, monitor, verify their claims, and loop the human in only for decisions.

A conversational lens that keeps the agent in product-space — describing what the human on the other side of the screen experiences — until you explicitly ask to cross into code-space.

Fable 5's working discipline, distilled — outcome-first reporting, act-don't-ask autonomy, faithful verification. Load at session start on a smaller model.