intake

# intake The front-door of the msg planning pipeline. Ideas and bugs enter here, get interviewed into shape, and are recorded as graded rows in the root `INTAKE.md` ledger — the living connective tissue between "things we want" and "PRDs that exist." `plan-pm` reads those rows and drafts the PRD autonomously. ``` intake (capture + interview + grade → INTAKE.md rows) → plan-pm (picks a row, drafts the PRD solo, stamps in-progress + prd mapping) → … → post-merge --production (stamps the row completed) ``` ## Usage **Capture mode** — protocol: [`refs/protocol-intake.md`](refs/protocol-intake.md) - `/intake` — capture one or more ideas/bugs into `INTAKE.md`. Pass the idea(s) as input, or be prompted. - `/intake <idea text>` — capture the described idea directly. Natural language: "log an idea", "capture a bug", "add this to the backlog", "note this feature down", "track this idea", "put this in the backlog". **Update mode** — protocol: [`refs/protocol-update.md`](refs/protocol-update.md) - `/intake --update` — list every un-shipped row (`backlog` + `in-progress`) in full, then edit the one you pick. - `/intake --update <free text>` — edit directly, e.g. `/intake --update #4 — goal should be "cut time-to-first-search"`. Unclear input still gets a follow-up question; the one-shot form buys speed, not a bypass. Natural language: "update that idea", "change the goal on #4", "edit the backlog row about search", "fix the idea I logged". Update mode edits **`idea` / `goal`...