startlisted

# Starting the next block of work **Project facts come from `.claude/WSS.WORKFLOW.json`** — `WSS.record.*`, `WSS.commands.*`, `WSS.gate`, `WSS.agents.*`, `WSS.lanes.*`, `WSS.hazards.*`. Read it first. Without a manifest, fall back to conventional names, skip what you cannot resolve, and say so in one line rather than guessing. **Under lane mode, some of these keys resolve to a lane-scoped file instead, and the batch is bounded by that lane's `scope` globs** — both are [`references/WSS.LANES.md`](references/WSS.LANES.md)'s, read where lane mode is on, before step 3 reads any record; a non-lane run needs neither and says nothing about it. Three records hold the pending work and they answer different questions: | Record | Answers | Precedence | |---|---|---| | `WSS.record.openDecisions` | What can't responsibly start until a choice is made | **First, always** | | `WSS.record.todo` | What could start today, with the detail to do it | Second | | `WSS.record.roadmap` — this lane's, where a selector resolves one | What goal is being worked toward, and what order its blocks go in | Only when the first two are dry | Under lanes there is a step before all three: **the transfer queue is drained in Phase 0**, so what a sibling lane filed is already sitting in the records above by the time this table applies. It is never read as a fourth source here. Decisions come first because an open decision is not a task that can wait — it is a choice that **gets made anyway**, silently, by whoe