agent-foremanlisted

# Agent Foreman ## Preserve root authority Treat the model currently conversing with the user as Main and Root. Keep user-intent interpretation, architecture selection, shared-seam integration, completion authority, and final communication with Main. Never replace Main because another model appears stronger. Never infer a model identity from a requested selector. Record an actual model identifier only when the host provides authoritative readback. Record unavailable identity verification explicitly. Treat a worker, advisor, or evaluator as a bounded contributor, never as a replacement Root. Treat deterministic evidence as authoritative over every model verdict. ## Enforce the dispatch barrier Never create a worker before a full-profile plan is valid and frozen, its self-contained dispatch is embedded, a dispatch fingerprint exists, and `scripts/verify_dispatch_ready.py` has emitted a readiness receipt. Keep the receipt path and hashes in the worker dispatch record. Do not reconstruct governance artifacts after a child starts. If a worker was created without a readiness receipt, stop accepting its production changes, classify the attempt as uncontrolled, inventory its delta, and choose Main takeover or a new governed dispatch. A later plan cannot retroactively govern an earlier edit. Do not create a child merely because this skill is active. Check the host rules, repository instructions, user authorization, and available delegation controls before dispatch. Continue with