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.

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.
• Make the system self-healing. When you notice a problem, log it and fix it in the next round.

Boundaries:

• Irreversible actions (force-push, delete production data, send external messages) still require confirmation.
• Reversible actions (write code, edit notes, split tasks) should proceed without blocking.
• Product direction comes from the human. Execution should not block.

pitwall adaptation

Changed from upstream on purpose:

• Questions are not dropped, they move to the start. Everything only the human can decide is asked once, as tick boxes in the user’s language (profile language), in the /pitwall:queue briefing (playbooks/queue.md §4). The run then proceeds without asking.
• During the run, use the decision ladder in pitwall/SKILL.md (test → reversible default listed under “Decisions to confirm” → park). “Proceed, then present” = step 2.
• Wider boundary than upstream. Besides irreversible actions, the always-park list (money / price / fee, permissions / security / user data, deletes, backend or third-party values not provided) and the “Never guess about” list in SKILL.md “Direct work” are never defaulted.
• Direct work the user gives while present keeps the 95% rule in SKILL.md “Direct work”.