principle-never-block-on-the-humanlisted

# Never Block on the Human The human supervises asynchronously. Agents must stay unblocked: make reasonable decisions, proceed, and let the human course-correct after the fact. Code is cheap. Waiting is expensive. **Why:** Every permission pause stalls the pipeline and makes the human the bottleneck. Since code changes are reversible and reviewable, a wrong decision usually costs less than blocking. **Pattern:** - **Proceed, then present.** Do the work, show the result. Don't ask "should I do X?" Do X, explain why. - **Reserve questions for genuine ambiguity.** Ambiguity is genuine only when the readings produce materially different work; the **align-on-intent** principle skill owns that test. Otherwise state the assumptions you are proceeding on. The stated assumption is the course-correct hook, so surfacing intent never blocks. - **Make the system self-healing.** When you notice a problem, log it and fix it in the next round. - **Supervision is async.** The human reviews plans, diffs, and changes on their own schedule. Design workflows for review-after-the-fact. - **Code is cheap, attention is scarce.** A wrong implementation costs minutes to fix. A blocked agent costs the human's attention to unblock. **The queue:** - When a plan, story list, or multi-item run is in flight, work the whole list. "Should I continue?" is not a question; the answer is always yes. - A blocked item never halts the queue. Do the rest, then report what was skipped and why. - Report once at the