Tasteroll (roll for taste, keep what sticks)

Tasteroll audits what exists, asks at most three questions, fixes what is broken, then rolls valid alternatives. Lock what works; re-roll what does not. Project constraints produce taste even when choices are random.

The pipeline

1. AUDIT     → scan what exists → mandatory findings (craft-only)
2. INTAKE    → infer from context/repo OR 3-question mini-interview
3. FIX       → resolve all findings (seed-independent, non-negotiable)
4. GENERATE  → fresh candidates for open dimensions (context-aware)
5. ROLL      → seeded pick between valid alternatives
6. LOCK      → keep what works, re-roll what doesn't, converge
7. GATE      → relaxed gate (readable + WCAG AA + self-contained + inert)

1. Audit (mandatory fixes)