shippers. / oracle
seen before it's asked

oracle.

an operating console, not a status report. every agent visible, every number sourced, you only show up where it matters.

01 · the agents, in orbit

every agent heartbeats or gets pulled. live nodes pulse and carry traffic to the core. a flat line isn't resting, it's not finished.

oracle operator core customsbeating · 6/6 agentsverify: supabase heartbeats, live · checked 14/09/2026 18:07 outreachsending · activeverify: last send 14/09/2026 09:40 - no Mon-Fri sendwindow missed since sentinelwatching · cleanverify: last run 14/09/2026 18:00, ok=true avaanswering · last call 2h agoverify: +442045727044 -> agent, 10+ calls, last 30sdone success · webhook portal.strydeos.com up ·elevenlabs, live · checked 14/09/2026 18:08 caller fleetgate failed · trademind 88%, 1 P0ava 100% of gate 95% (13x1, 13 calls, 0 P0,backfilled from the 4 Sep 2026 overnight ledger) 11dago · trademind 88% of gate 95% (34 scenarios, 1 P0,backfilled from commit c09a224, the 25 Aug run) 21d…
02 · the instruments

computed, never declared. silence on any one is the failure.

/ instrument 01

ci

4/4 green

/ instrument 02

fixed

100%

03 · the doctrine, moving

watch the job travel. it holds at amber, the operator clears it, it moves on. everything between gates is the fleet's problem.

intent dispatch gate · scope build gate · pre-deploy ship sign-off paid the operator appears three times. that's the whole job.
04 · what needs you

not fleet state, the queue of things only you can call. empty is the goal, not the default.

an inbox instruction reads you when it needs a human call, not a guess. a finding reads high or critical when sentinel could not heal it alone. quiet equals not finished.

05 · the actions

what oracle actually did, not fleet state.

2h agourgent alert sent - 6 live prod errors (STRYDEOS-DASHBOARD-36, STRYDEOS-DASHBOARD-37 +4 more)sent
4h agoweekly digest sent (102 runs rolled up)sent
1d ago"test reply" — test reply, cleared in the 13 sep tt auditdone
1d ago"Re: test reply" — test reply, cleared in the 13 sep tt auditdone
1d agourgent alert sent - 3 live prod errors (STRYDEOS-DASHBOARD-3A, STRYDEOS-DASHBOARD-3B, STRYDEOS-DASHBOARD-3G)sent
1d agourgent alert sent - 2 live prod errors (STRYDEOS-DASHBOARD-3A, STRYDEOS-DASHBOARD-3B)sent
2d agourgent alert sent - checks failing on StrydeOutreach; 2 live prod errors (STRYDEOS-DASHBOARD-3A, STRYDEOS-DASHBOARD-3B)sent
2d agourgent alert sent - 1 live prod error (STRYDEOS-DASHBOARD-3B)sent
40d ago"Yo" — Engine live sending is ON, last set by shippers-restore-false-positive-2026-07-07.done
06 · the watch

every reading below is timestamped at source. silence is the failure state, so an instrument that cannot prove when it last spoke is not trusted, it is flagged.

ci
4/4 green
live
4/4 repos green on latest run
fixed
100%
live
293 of 293 findings resolved (all-time)
outreach
sending · active
live
last send 14/09/2026 09:40 - no Mon-Fri send window missed since
2/2 instruments live · 5/5 orbit nodes livechecked 14/09/2026 18:08
07 · what the fleet has learned

every fleet keeps a ledger of the mistakes it has already paid for. a quiet ledger is not a clean fleet, it is usually a fleet that stopped writing things down.

42 rules held across 3 ledgers · 1 gone quieta rule is only held if the mistake is not repeated