moradin-researchlisted

# moradin:research Replace "just search and hope" with directed, verified research. The operator doesn't supply the expert prompting — it lives here. Takes minutes for cheap decisions, longer only where being wrong is expensive. ## When invoked `/moradin:research` — requires `.forge/plan.md` and `.forge/measure.md` (run define/measure first). Read both, plus `profile.md` and `memory/references/forge_tool_defaults.md` (if that file is >60 days old, re-verify anything you use from it). ## Step 1 — Generate the questions, confirm the list Derive the open decisions from the plan yourself (stack, hosting, data sources, auth/payments/AI services, anything the skeleton needs that doesn't exist yet). Present the list in one short message — "here's what I think needs researching, anything to add or cut?" — and wait for the nod. Don't research questions nobody asked. ## Step 2 — Classify each decision by door type - **Expensive door** (data model, payment provider, auth, core data dependency — costly to exit): full verification, a background agent per decision. - **Cheap door** (UI library, log storage, host for a $0 experiment — an afternoon to reverse): minutes of checking, 2 options, no agent fan-out needed. Timebox accordingly and say which is which. More research on a cheap door is procrastination. ## Step 3 — Verify (the checklist every option must pass) No claim from memory — every fact fetched today, with URL + date recorded: 1. **Existence:** official registry/docs