Figure it out

1. Ground the goal in repository evidence. State the measurable done predicate, scope and rough effort, constraints, baseline, and available verification. Invoke /pstack-how or /pstack-why where needed. Complete when the task can be judged by an artifact or observation rather than activity.
2. Design the smallest sufficient execution playbook: phases, independent units, hypotheses, acceptance gates, rollback or rejection conditions, and reporting. Use /pstack-architect or /pstack-arena for consequential contested boundaries. Complete when every phase ends with checkable evidence and the run fits its grant and budget.
3. Run the loop, using /pstack-swarm for independent work and critics. Test a hypothesis before scaling it, inspect worker outputs, and harden a gamed check rather than accommodating it. Complete each unit only when its actual behavior is proved.
4. Keep the decision trail through /pstack-show-me-your-work. Replan from evidence, preserving scope and approved-interface gates. A productive run still respects its agreed time limit. Complete each checkpoint when progress, remaining work, and decisions are durable.
5. Verify the final artifact and return the predicate result, evidence, alternatives, and exact gaps. Use /pstack-ketchup to explain the user-facing result. Complete when the goal is demonstrated or unfinished work has a concrete handoff; effort alone never establishes completion.