superstack-digestlisted

# superstack-digest The digest is the calibration record paying rent outward. It is assembled from records, never from memory — the conversation is scratch; files are the project (superstack-continuity's rule, applied to reporting). The description's deferrals (a retro tool for retrospectives; a memory/session-history tool for self-recall) bind only if the named tool is really present — check the session's skill listing first and announce the hand-off; when nothing is there, assemble from records right here. ## Assemble 1. **Gather the period's facts from the record:** `git log` across the repos in scope, the claims-log's `Verified:` lines, value-log settlements (`HELD`/`MISSED`), queue movements, open residuals and skipped-gates. Your recall of the period is a hypothesis; the logs are the evidence (R1 on your own memory). **If the record is thin** — early days, files not yet grown — say so: build from `git log` alone and ledger the gap (`Assumed: the period wasn't fully logged — built from git history only`). 2. **Numbers in a digest are data claims.** Sanity-check each before quoting — counts from commands, reconciled against a known total where one exists. A `PROVISIONAL` number never ships to an external reader: round it into honest words or leave it out. ## Write for the named reader 3. **Their language, not the method's.** Shipped work in outcome words, not commit words ("the report now runs in under a minute", not "refactored the aggregation pipeline"). No sessio