checklist-bound-executionlisted

# Checklist-Bound Execution A harness for fanning checklist / plan items out to spawned agents WITHOUT drift. Use it any time two or more agents execute items from a shared plan and "did the agent actually do its exact job?" matters. ## Why this exists (read first) Spawned agents (Workflow agents, Task subagents) start with a FRESH, isolated context. They do not see the conversation, the plan, or your intent unless it is handed to them. When the assignment is vague — or worse, fails to arrive (the Workflow `args` global is unreliable and has come through as `undefined`) — the agent reconstructs the task from whatever it can read and IMPROVISES. That is the root cause of drift, not "lack of discipline." Enforcement is therefore NOT a single instruction. It is four mechanisms together: 1. **Determinism of assignment** — each agent receives its item VERBATIM, embedded in its prompt. 2. **Structured proof** — each agent must return a schema-validated completion record (validated at the tool layer, so it cannot hand-wave; the runtime retries on mismatch). 3. **Independent verification** — a separate, read-only agent re-checks each item against its acceptance criteria, adversarially, and can FAIL it. 4. **Loop-back** — a failed item is sent back to a worker to fix, then re-verified, up to a bound. A skill alone is advisory. This skill works because it pairs the procedure (here) with the Workflow script's deterministic control flow + structured-output schemas + a verifie