prepare-digest-deltalisted

# Prepare the Repo Digest delta (apply-at-merge) You just implemented and evidenced a ticket. You already know exactly what changed — so you are the cheapest place to write down how the **Repo Digest** should move and which **feature** this ticket ships. This skill records that as a single, structured **evidence row**. It is INERT: nothing is applied now. The factory's merge step reads this row **post-review** and applies it deterministically (no new agent call). If the ticket is rejected, it never merges, so this prepared delta never pollutes the digest. This is the **prepare** half of prepare-at-delivery / apply-at-merge. Recording the delta here — instead of running a fresh `claude -p` on every merge — is the whole cost win. Keep it cheap: you are summarising a diff you already have, not re-deriving it. ## Steps 1. **Decide what the digest should say now.** For each Repo Digest section your change makes stale (architecture, key flows, conventions, surface area, gotchas, …), write the SHORT updated prose for that section — only sections you actually changed. If the change is small and touches no section's narrative, you may record zero sections (the merge will still stamp freshness). 2. **Name the feature this ticket ships.** One feature note: its `name`, a one-line `summary`, and — if you know it — the `scopeNode` and `provenance` (e.g. the epic ref). This is what the merge advances/adds to `shipped`. 3. **Record ONE evidence row** via the Dispatch MC