planning-optionslisted

<!-- planning:contract --> ## Owns Which approach, and why that one. It generates real alternatives, scores them against the brief's own criteria, and **recommends** — a scored table with no recommendation is abdication. Phases: `CRITERIA → GENERATE → ELIMINATE → COMPARE → DECIDE`. Decided mode: `RECORD → PRESSURE-TEST → DECIDE`. ## Before starting - **Take the criteria from the brief, not from taste.** Options are scored against the `SC-n` and `C-n` that already exist; inventing criteria here is choosing the winner and then justifying it - **Check whether the approach is already decided.** If it is, run decided mode — record the decision, attack it once, move on — and say the three-option minimum is not in force rather than leaving the contract looking violated - **A hard constraint eliminates, it does not score.** An option that violates a `C-n` is out, and scoring it anyway invites it back in on points <!-- deliver:sizing --> - **Declare the tier before anything else**, read off the work and stated at the top of the deliverable. `S` — under a day, reversible: one brief in the response, **no files, no handoff**. `M` — multi-day, single owner: the brief and the plan. `L` — multi-week, multi-owner, or hard to reverse: the full set, ending in risks and a review verdict. **Over-planning an `S` is a failure of the same weight as under-planning an `L`** - **The planning gate stops the run at the phase that owns the condition** — the goal cannot be state