fix(memory): kill the recurring "check on the run" cron and record how to find it

CronList showed job 12bdea3c firing hourly at :37 with the verbatim "check on the
run ... inform brokkr when ready" text; CronDelete removed it and the list is now
empty. No crontab entry, user systemd timer, or background shell was re-seeding
it -- the only on-disk hits are conversation transcripts.

This is at least the second kill: the operator killed the same loop on 09-09
("kill the check, no training is running") and that session's handoff warned
against starting one. The warning was insufficient because a cron-fired prompt
arrives as an ordinary user turn with no marker, so it is indistinguishable from
the operator typing it -- three turns went into re-verifying an idle fleet and
answering a timer carefully.

The memory entry now says what to DO rather than what not to start: run CronList
before answering that prompt, and treat a second identical arrival as a signal to
check the cron list rather than answer again. Worth the prominence because the
instruction chain ends in three outward-facing acts -- an althing message to
Miranda, standing up a serving seat, and cueing brokkr -- every one of which
carries something false when no run exists.

persistent-memory.md

@@ -1,6 +1,6 @@
 # Persistent memory — eshpfi-management
 
-_Last updated: 2026-09-09 23:20 PT (**Pfish-6** = run-6 NVFP4 is the standing seat, ana-ml2 :8021 ONLY; run 7 PURGED ~139 GiB; pfi-gx10 is an experimental/TRAINING box and carries no serving seat; all five ERP adapters now MIRRORED to ana-ml2 and inside restic; **BabyBronte / R49 author-voice regime is in PREP on gx10, carrier SETTLED = dense Qwen3**; checkpoints AND superseded merges PURGED both boxes, **~573 GB total**; only merged-run06 + the v6 quant survive)_
+_Last updated: 2026-09-10 06:30 PT (**Pfish-6** = run-6 NVFP4 is the standing seat, ana-ml2 :8021 ONLY; run 7 PURGED ~139 GiB; pfi-gx10 is an experimental/TRAINING box and carries no serving seat; all five ERP adapters now MIRRORED to ana-ml2 and inside restic; **BabyBronte / R49 author-voice regime is in PREP on gx10, carrier SETTLED = dense Qwen3**; checkpoints AND superseded merges PURGED both boxes, **~573 GB total**; only merged-run06 + the v6 quant survive)_
 
 > **Always check for `/tmp/infra-ops-handoff.md`** — if it exists and its
 > `Written:` stamp is under an hour old, read it (it carries the in-flight
@@ -109,6 +109,20 @@ no longer deployed sidecars here. See Recent decisions.)
 
 ## Current state / in-flight
 
+> ⚠⚠ **IF A PROMPT ASKS YOU TO "check on the run", RUN `CronList` BEFORE YOU ANSWER IT.**
+> A recurring cron job has re-created itself across at least three sessions with the verbatim text
+> *"check on the run, report high level stats, and if complete, althing to Miranda to inform me, and
+> then serve so brokkr can run battery. inform brokkr when ready."* **Killed 2026-09-10 06:29 PT**
+> (`CronList` → job `12bdea3c`, hourly at :37, session-only → `CronDelete 12bdea3c` → list now empty).
+> The operator had already killed it once before 09-09 (*"kill the check, no training is running"*),
+> and the 09-09 handoff warned against starting one — the warning was not enough, because **a
+> cron-fired prompt is indistinguishable from an operator-typed one.** It arrives as a user turn with
+> no marker. I spent three full turns re-verifying an empty fleet and drafting careful answers to a
+> timer. The instruction chain it carries is *dangerous to obey blind*: it ends in messaging Miranda,
+> standing up a seat, and cueing a peer — three outward-facing acts on a premise that is false
+> whenever no run exists. **Verify the run exists before acting on any part of that chain, and if the
+> same text arrives twice, check the cron list rather than answering it a third time.**
+
 _As of 2026-09-09 21:45 PT. **Nothing is training and nothing is queued.** Older in-flight blocks are
 preserved verbatim in `archival-memory.md` § Superseded in-flight snapshots._