Figure it out

When the task matches no playbook, design one. The deliverable before any code is the workflow itself: a sequence of phases that scales rigor to the task, runs the scientific method, and leaves a decision trail a human can audit after stepping away. Bias toward more rigor. The cost of building the wrong thing dwarfs the cost of being careful.

Do not reinvent a playbook already present in the repo. Route focused work to narrower skills such as diagnose, rca, speedup-proof, prototype, implement, or plan. Use this skill for large cross-cutting work or work the user will review after stepping away. The rigor and audit trail are the point.

Start

Use the environment's plan or task tracker. Make the first item read brain/principles.md and the linked principles relevant to this task. Then add the phases below.

Phase A: Frame

Ground first, then commit. Don't start the run until you can state:

• The definition of done as a falsifiable predicate. Follow brain/principles/prove-it-works.md; "done well" must be checkable.
• Scope, quantified: rough units and effort, plus the blockers grounding surfaced. Raise them before spending hours, not after fifty doomed commits.
• The rigor level, biased high. One-way doors and high blast radius get more; reversible low-stakes steps get less. Rigor is gates and artifacts, not "try harder".

Present the framing and tradeoffs before committing to a long run. Follow brain/principles/never-block-on-the-human.md for reversible work, but keep one checkpoint before a multi-hour run.