decision-mappinglisted

# Decision Mapping — chart the way before planning it A loose idea has arrived: too big for one agent session, and wrapped in fog. The way from here to the **destination** is not visible yet. This skill charts that way as a **decision map** — a single committed markdown file — then works its **decision tickets** one at a time until the route is clear. The destination varies per effort, and naming it is the first act of charting: a spec to hand off, a decision to lock before planning starts, or a change made in place. The map is domain-agnostic. **Plan, don't do.** Each ticket resolves a decision; the map is done when nothing is left to decide before someone goes and builds. The pull to just do the work is the signal you have reached the edge of the map and it is time to hand off — to `writing-plans`, `superplan`, or `blueprint`. An effort can override this in its `## Notes`; absent that, produce decisions, not deliverables. **Refer by name.** Tickets have names — their headings. In everything a human reads, use the name, never a bare number. A wall of `#3, #4, #7` is illegible; names read at a glance. The numbers exist so blocking edges can point at something stable, and they ride inside the name, never instead of it. ## Where the map lives One markdown file per effort, **committed** alongside the work it plans: | Effort | Path | |---|---| | Harness | `.claude/docs/plans/<YYYY-MM-DD>-<effort>-map.md` | | Project | `<project>/docs/plans/<YYYY-MM-DD>-<effort>-map.md` |