the fleet at a glance — every section stamped with its OWN source freshness (honest per-source staleness). VIEW only · static prod snapshot · generated 2026-07-02T07:50:48.799Z
📸 PROD snapshot taken 2026-07-02T07:50:48.799Z — this is a point-in-time capture, not live. Freshness stamps below are as-of the snapshot.
Log grid 40 logs · 🟢6 🟡1 🟠1 🔴1 🟣23 ⚪8
🟢 scanned 40 logs · census live
✓healthy — fresh, serving, within SLO◐degraded — working but partial / SLO at risk✕failing — errors, down, or unreachable❄frozen — heartbeat without progress — fresh log but only ticks, no new edge⚒in-dev — building / not yet registered, no SLO held yet⛔blocked-on-human — waiting on a Jacob unblock (sign-in / OTP / decision)▢retired — quarantined — kept visible but dimmed (honest history)?unclassified — cannot classify honestly — shown without a color, never defaulted green
Mission Control v0.1 — Log Grid + Prod publisher (live)
report.landed5.1h
2025 1040 review checklist
click for full engine ▸
librarian/librarian✓ healthy
40 facts · last edge 2.1h · census live · ENGINE
librarian.tick_failed2.1h
reason=transcriber /api/view returned 502 (supplier unhealthy)
librarian.tick_failed3.5h
reason=transcriber /api/view returned 502 (supplier unhealthy)
librarian.wrote5.1h
T33iI6izAKw
click for full engine ▸
ideas/ideas◐ degraded
40 facts · last edge 7m · census live · PARTIAL
ideas.map7m
ideas=80
ideas.poll7m
ideas=80
ideas.thumbnail7m
Phase-Gated Judging — a finding's severity follows make-it-work / make-it-right / make-it-fast; the judge always OBSERVES everything but only FAILS what the pha
click for full engine ▸
mission-control/decisions⛔ blocked-on-human
9 facts · last edge 4.1h · census live · ENGINE
decision.opened4.1h
Mission Control v1 linking: every card/report/engine/agent row links to its LIVING artifacts — the owning Claude Code conversation (tmux session or resume id),
decision.opened4.1h
Build the model-routing service (monorepo-wide): task-class -> cheapest-capable model with caps + fallback order Fable (conductor/judge/hard-verify) -> Opus spe
decision.opened4.2h
Send Nick the automated-marketing-campaign pitch. A dedicated Claude Code session (tmux: nick-pitch) holds the LIVING draft — attach to refine: tmux attach -t n
click for full engine ▸
acceptance-judge/verdicts✕ failing
21 facts · last edge 16m · census stale · ENGINE
acceptance.ruled16m
caseId=skills-telemetry-visible-2740cb3f
acceptance.judged16m
caseId=skills-telemetry-visible-2740cb3f
acceptance.submitted16m
skills-telemetry-visible-2740cb3f
click for full engine ▸
pipeline-watchdog/watchdog⚒ in-dev
40 facts · last edge 9s
watchdog.breach9s
handoff=transcriber->librarian
watchdog.observed9s
healthy=false
watchdog.breach1m
handoff=transcriber->librarian
click for full engine ▸
cc-activity/activity⚒ in-dev
8 facts · last edge 13s
cc.activity13s
state=ACTIVE
cc.activity28s
state=ACTIVE
cc.activity43s
state=ACTIVE
click for full engine ▸
cc-factory-watch/alerts⚒ in-dev
40 facts · last edge 18s
tick18s
condition=PRODUCING
tick25s
condition=PRODUCING
tick48s
condition=PRODUCING
click for full engine ▸
cc-factory-watch/classified⚒ in-dev
40 facts · last edge 19s
cc.factory19s
state=FACTORY-ACTIVE
cc.factory19s
state=FACTORY-ACTIVE
cc.factory39s
state=FACTORY-ACTIVE
click for full engine ▸
pipeline-health/pipeline-meta⚒ in-dev
40 facts · last edge 52s
pipeline.observed52s
traces=273
pipeline.observed57s
traces=273
pipeline.observed2m
traces=273
click for full engine ▸
pipeline-health/reconcile⚒ in-dev
40 facts · last edge 52s
reconcile.observed52s
healthyCount=5
reconcile.observed2m
healthyCount=5
reconcile.observed3m
healthyCount=5
click for full engine ▸
system-health/health⚒ in-dev
40 facts · last edge 3m
health.snapshot3m
autonomyLadder=L2
health.snapshot8m
autonomyLadder=L2
health.snapshot13m
autonomyLadder=L2
click for full engine ▸
tool-telemetry/tools⚒ in-dev
40 facts · last edge 11m
fact11m
tag=tool.completed
fact11m
tag=tool.called
fact11m
tag=tool.called
click for full engine ▸
.driver/driver⚒ in-dev
22 facts · last edge 43m
edge43m
#68 item-4 feasibility DONE (read-only): merge-main-into-reactive recommended (reactive superset of daytona — one stack, move together); factWrites seal-ificati
tick50m
step-6 green->red edges INVESTIGATED + RESOLVED within tick: mission-control reports/health/deploy red at 06:58:54Z = 54s restart blip during owning session dep
edge1.7h
write-path conformance red-team: SHIP @e62dfdc — all 6 focus areas HOLD (fact-own-at wins; nextSeq=bounded tail-read not O(n); no reader keys on seq/order; mixe
click for full engine ▸
summary-judge/verdicts⚒ in-dev
40 facts · last edge 5.1h
summary-judge.verdict5.1h
T33iI6izAKw
summary-judge.verdict5.1h
QCd2k7WWfkI
summary-judge.verdict6.5h
Gmc4rlKx0pA
click for full engine ▸
sensor/items⚒ in-dev
40 facts · last edge 5.4h
video.appeared5.4h
Mixture of Experts: The AI Trick Eating the World's Memory
video.appeared5.4h
Finally, an Open Standard for the Karpathy LLM Wiki is HERE
Nick's Google Ads Reality Is Locked Behind 3 Access Points He Can't Unify
fact6.6d
tag=ranking.resolved
click for full engine ▸
story-engine/stories▢ retired
40 facts · last edge 7.0d
fact7.0d
No heartbeat: can't tell if an engine is writing without digging through logs
fact7.0d
Agent can't verify its own writes — optimistic updates go unconfirmed
fact7.0d
Every dev session starts blind — no canonical view of which engines are healthy
click for full engine ▸
wiki-hooks/hooks▢ retired
40 facts · last edge 7.1d
sensor.scanned7.1d
sha=f1f2d569eac2739e4a1024f0c12262e9a42a5d19
page:deleted7.1d
wiki/concepts/_TrustDemoTmp.md
sensor.scanned7.1d
sha=7a7639589afff6dea63b2b19a7d0fade9564a8b4
click for full engine ▸
idea-capture/raw-ideas▢ retired
40 facts · last edge 7.1d
fact7.1d
tag=idea.captured
fact7.1d
tag=idea.captured
fact7.1d
tag=idea.captured
click for full engine ▸
github-source/gh-librarian▢ retired
1 facts · last edge 8.0d
gh-librarian.wrote8.0d
repo=automate-friday/automate-friday-platform
click for full engine ▸
github-source/github▢ retired
20 facts · last edge 8.0d
github.observed8.0d
Progressive-trust ramp: opt-in UI (toggle a skill to on_first_use + ratify button)
github.observed8.0d
Tool: System Manifest — the platform's living self-model (primitive grammar + intended topology + build-state)
github.observed8.0d
Tool: Convergence Auditor — diff the real system against the System Manifest, emit a drift report
click for full engine ▸
Tasks 2 live · 0 orphaned
🟢 2 live · 0 orphaned · 12 tmux sessions
tasks-as-living-conversations — each task's owning Claude Code session (tmux), its TASK.md, and any decision card it maps to. A task whose session died shows orphaned, never hidden.
THE DRIVER — charter (agreed with Jacob 2026-07-01 evening)driver
● live — session up 6.1h
attach: tmux attach -t driver
/Users/jh/code/automate-friday/.driver/CHARTER.md
Prod deployment public snapshot on Cloudflare Pages
🟢 prod live + verified · 12m ago
the live URL is a tailnet address for THIS machine; PROD is the published snapshot below (so agents can use it after this session ends). Verified = the deployed URL was fetched and its content hash matched.
a skill sub-agents can find, and we track if they use it. Adoption count IS the eval (incl. the standard-report skill itself).
tailscale-report14 total
today 0 · 7d 0 · last used 19.0d ago
make-engine9 total
today 0 · 7d 9 · last used 2.1d ago
automate-friday-wiki:wiki-publish3 total
today 0 · 7d 3 · last used 15.5h ago
chrome-devtools-axi3 total
today 0 · 7d 3 · last used 2.6d ago
spec-driven3 total
today 0 · 7d 0 · last used 21.5d ago
tts-on3 total
today 0 · 7d 0 · last used 13.4d ago
update-config3 total
today 0 · 7d 0 · last used 19.5d ago
tribunal-review-admin2 total
today 0 · 7d 0 · last used 21.5d ago
wiki-publish2 total
today 0 · 7d 2 · last used 16.1h ago
architecture-review1 total
today 0 · 7d 1 · last used 4.1d ago
auto-red-team1 total
today 0 · 7d 0 · last used 19.5d ago
calibrate-judge1 total
today 0 · 7d 1 · last used 3.4d ago
career-ops1 total
today 0 · 7d 1 · last used 2.6d ago
claude-in-chrome1 total
today 0 · 7d 1 · last used 2.6d ago
competitive-analysis-for-builders1 total
today 0 · 7d 0 · last used 39.9d ago
design-md-picker1 total
today 0 · 7d 0 · last used 27.2d ago
dev1 total
today 0 · 7d 1 · last used 2.7d ago
driving-tmux-claude-sessions1 total
today 0 · 7d 0 · last used 7.3d ago
effect-development1 total
today 0 · 7d 0 · last used 19.5d ago
engine1 total
today 0 · 7d 1 · last used 4.2d ago
harvest-conversation-type1 total
today 0 · 7d 0 · last used 9.6d ago
image-exploration1 total
today 0 · 7d 0 · last used 27.1d ago
loop1 total
today 1 · 7d 1 · last used 6.1h ago
request-approval1 total
today 0 · 7d 0 · last used 11.1d ago
transcribe-video1 total
today 0 · 7d 0 · last used 27.3d ago
validate1 total
today 0 · 7d 1 · last used 4.6d ago
vercel:deploy1 total
today 0 · 7d 0 · last used 22.0d ago
Decisions 9 open · your call
🟢 own log · 9 open
mc links v1
GO?
What
Mission Control v1 linking: every card/report/engine/agent row links to its LIVING artifacts — the owning Claude Code conversation (tmux session or resume id), its TASK.md, the engine dashboard, and the wiki page. Tasks-as-conversations become a first-class column (the desk).
Build the model-routing service (monorepo-wide): task-class -> cheapest-capable model with caps + fallback order Fable (conductor/judge/hard-verify) -> Opus specialized CC plan (workhorse) -> Codex (cross-vendor red-team + bulk) -> Gemini (multimodal/judge diversity) -> OpenRouter (spot). Per-task $ telemetry lands on the board.
Send Nick the automated-marketing-campaign pitch. A dedicated Claude Code session (tmux: nick-pitch) holds the LIVING draft — attach to refine: tmux attach -t nick-pitch. Draft + rehearsal-vs-respond-as-nick registered as a report when ready.
A standard FREEZE DOOR: `control.freeze` / `control.resume` as FACTS an engine's supervisor honors (per the thermostat-real doctrine — disable/tune/halt are facts on the log, never out-of-band state), added to the engine template so every engine inherits a uniform way to be paused from the cockpit without a bespoke kill for each one. Mission control stays a VIEW; it would only render freeze STATE, never reach in to flip it.
Why now
Jacob asked for a way to freeze an engine from the grid. The honest way is a doctrine-conformant fact door in the template, not a one-off script — building it once in engines/_template makes freeze a first-class, auditable capability across the whole fleet.
Approve building the freeze door into engines/_template (control.freeze/control.resume facts + supervisor honor) and retrofitting the pipeline engines (youtube-watcher / transcriber / librarian)?
Mission Control is published to prod at af-mission-control.pages.dev — but the deploy token can't edit Cloudflare Access, so the URL is unlisted-but-PUBLIC until you gate it. It shows internal business state (threads, decisions, engine health).
Why now
It went to prod tonight so agents can use it after this session; the ~2-minute Access gate is the one thing only you can do (dashboard-only, the token can't).
Source
prod publisher / Cloudflare
Gate af-mission-control.pages.dev with Cloudflare Access (your email), and optionally add mission.automatefriday.com?
Open the Codex fan-out (10x compute) once mission control v1 is the intake surface. The business map's empty slots become the hole-list; the report intake becomes the register — so a wide fan-out has solid holes to contribute to instead of scattering.
Why now
The 10x compute exists but has had no solid hole to contribute to; mission control v1 (business map + report intake) is what turns that compute into filled slots and registered reports.
Source
codex fan-out / mission control v1
Once mission control v1 is the intake — go/no-go on the Codex fan-out, and how wide?
The Tier-1 onboarding-bench front-door reliability test was blocked on op reauth — now unblocked. An overnight run resumes frontier work; its GQM is already defined (pass/fail aha, pave-list as deliverable, observe-not-score).
Why now
The blocker is cleared and the GQM is already shown/agreed — the only thing missing is the word go.
Source
onboarding-bench
Dispatch the onboarding-bench overnight run tonight?
Interactive op (1Password) works now, but headless agents (driver loop, cron, overnight runs) can't use the desktop biometric session — they need the existing service-account token in their env once.
Why now
It unblocks agents self-serving keys, healthchecks.io self-provisioning, and RentRedi rung 2 — several threads are waiting on this one pointer.
Source
vault / headless agents
Where does the op service-account token live (a 1P item name), or is it OK to store it in the login keychain for agents?
The cc-control repo has a merge conflict on branch janitor-backup-2026-07-01 that an agent cannot safely resolve — it needs Jacob's hand to decide which side wins.
Why now
It is blocking a clean commit of cc-control work; the janitor pass flagged it as the one surface it could not reconcile itself.
Source
janitor pass / cc-control
Resolve the cc-control merge conflict on janitor-backup-2026-07-01 yourself, or tell the agent which side to take?
Business map 10 registered · 2 unregistered · 7 holes to fill
🟢 registry census fresh · updated 9s ago
every business function is a slot — registered = a live engine in the census, unregistered = a real engine with no published card, PLACEHOLDER = a hole to fill (the fan-out's hole-list).
slot
engine
what fills this
Fleet mission control
mission-controllive · ENGINE
see the whole business at a glance + decide
Engine registry / discovery
registrylive · ENGINE
census + health of every engine
Content pipeline · watch
youtube-watcherlive · PARTIAL
watch sources for new material (frontier engine #1)
Content pipeline · transcribe
transcriberlive · ENGINE
turn media into text
Content pipeline · file to wiki
librarianlive · ENGINE
fold knowledge into the wiki
Wiki maintenance
wiki-sweeplive · ENGINE
keep the knowledge base clean + self-managing
Idea capture
ideaslive · PARTIAL
capture sparks into the flow
Conversation → knowledge
conversation-refinerystale · ENGINE
refine conversations into durable facts
Idea routing
idea-librarianstale · ENGINE
route ideas to the right home
Sub-agent telemetry
tool-telemetryunregistered
which agents/tools fire across the fleet
Personal finance
rentredi-expensesstale · ENGINE
trusted monthly expense book
Thread driver / conductor
.driver loopunregistered · not-yet-an-engine
drive open threads to done so Jacob stops driving
VPS / infra health
PLACEHOLDER
unattended box health w/ recovery ladder (frontier engine #2, HumbleBrands)
Nick CRM (barbershop + swim school)
PLACEHOLDER
reconcile + grow Nick's bottom line (frontier engine #3)
Social sensing (X bookmarks → ideas)
PLACEHOLDER
triage Jacob's bookmarks into the idea flow
Content pipeline · draft + ratify + post
PLACEHOLDER
reply in operator voice, one-tap human ratify (content-pipeline-shipping)
Taxes / CPA
PLACEHOLDER
keep the books tax-ready; 1040 + quarterlies
HumbleBrands client-health
PLACEHOLDER
$1k/mo support client — agent health monitor
Narra (audiobooks in your voice)
PLACEHOLDER
demand-validated product; concierge → engine
Reports 5 registered · latest first
🟢 own log · 5 registered
reports get built anywhere — they REGISTER here. File one from any session: node engines/mission-control/report.mjs "title" "path-or-url" --thread X --depth L2
Acceptance judge maiden verdictsL3 cross-checked
2026-07-02T06:38:37.275Z · from acceptance-judge build · thread acceptance-judge
aphase-rul · session 9c85df13 · last tool 11m ago · 58 calls
recently finished
writer-rebase-feasibilitylikely delivered
awriter-re · finished 43m ago · 17 calls
acceptance-judgelikely delivered
aacceptanc · finished 1.2h ago · 67 calls
write-path-redteamlikely delivered
awrite-pat · finished 1.7h ago · 28 calls
general-purposelikely delivered
a281d7a6c4 · finished 1.8h ago · 40 calls
general-purposelikely delivered
a4b608750e · finished 2.1h ago · 90 calls
Engines 7/11 live · sacred pipeline highlighted
🟢 registry census fresh · updated 9s ago
sacred pipeline
youtube-watcherlive · PARTIAL
→
transcriberlive · ENGINE
→
librarianlive · ENGINE
rest of the fleet
acceptance-judgestale · ENGINE
conversation-refinerystale · ENGINE
idea-librarianstale · ENGINE
ideaslive · PARTIAL
mission-controllive · ENGINE
registrylive · ENGINE
rentredi-expensesstale · ENGINE
wiki-sweeplive · ENGINE
Driver tmux session alive
🟢 driver alive · last advance 43m ago
edge 2026-07-02T07:08:18Z
#68 item-4 feasibility DONE (read-only): merge-main-into-reactive recommended (reactive superset of daytona — one stack, move together); factWrites seal-ification already on main conflict-free; real work = outbox.ts 7 semantic hunks + reroute 9 raw db.insert(facts) writers (lint rule = completeness gate) + hand-verify mcpMutation clean-merge trap; ~half-day; open check = which branches deploy to shared dev (factlog-substrate possible 3rd unchained source). Plan staged in outbox addendum 2; execution needs Jacob go + worktree-owner coordination
tick 2026-07-02T07:00:42Z
step-6 green->red edges INVESTIGATED + RESOLVED within tick: mission-control reports/health/deploy red at 06:58:54Z = 54s restart blip during owning session deploy cycle (red->green 06:59:48Z, registry live, run.mjs alive, deploy.succeeded fresh); acceptance-judge born-red = new engine under active dev vs /tmp fixture server (their surface, dev churn, not distress). Sacred pipeline all green. Advance: dispatched READ-ONLY #68 item-4 feasibility (writer-worktree rebase topology/conflicts/seal-ification/deploy-risk in platform repo)
edge 2026-07-02T06:11:01Z
write-path conformance red-team: SHIP @e62dfdc — all 6 focus areas HOLD (fact-own-at wins; nextSeq=bounded tail-read not O(n); no reader keys on seq/order; mixed legacy+seq lines tolerated permanently; safe to merge WITHOUT restarting live rate-server :3005; exam cwd-independent; checker+kit untouched — green is genuine; pre-existing failures byte-identical on base). Latent non-blocking: seq starts at 1 mid-file on migrated legacy logs — never a primary key. ALL FOUR overnight branches now verified SHIP; trunk line updated
edge 2026-07-02T06:05:05Z
privileged-write conformance fix BUILT: fix/privileged-write-conformance @e62dfdc (4 raw appendFileSync sites -> kit journal door; shapes preserved with consumers checked; RED 4 violations -> GREEN 32/32 + conformance PASS 270 files; exemption case argued and correctly rejected — check has no exemption machinery; librarian core untouched, validated on scratch :3991). Red-team dispatched (shape spread-order, legacy seq semantics, mixed-format concurrency, exam path fragility, checker-not-weakened) · NEW pre-existing finding #2: layout+tick-purity FAIL on mission-control/log/deploy.jsonl (50% restated levels, tick-spam) on base ref — mission-control session still actively editing (10 uncommitted); NOT dispatching onto their surface; queue for their retrofit or a thread once they commit
tick 2026-07-02T05:56:26Z
dispatched privileged-write conformance fix (fix/privileged-write-conformance off feat/log-projection-convention): route librarian/calibration rate-server, wiki-auto-intake, conversation-dispatcher fact appends through the kit door; sacred constraint = librarian calibration sidecar only, no service restarts; exemption-over-refactor allowed for deliberate exam writers
edge 2026-07-02T05:46:46Z
#33 increments 1+5 COMPLETE: feat/hook-intervention-layer = 95648f5 + 2b95f3a (drift->unknown attribution + drift counter incl. pin-blind near-miss case; 4KB/100-line constraints cap with truncation marker — red evidence: unbounded version injected 15,125 bytes from a 14KB file; hook-stream 12/12, injector 20/20, all gates green; one builder stall = zsh =word expansion abort, recovered clean). Branch merge-ready, stacks on feat/log-projection-convention · NEW FINDING (pre-existing, not this branch): _kit journal.test.ts CONFORMANCE red on clean HEAD — privileged-write-path violations by librarian/calibration/rate-server.mjs, wiki-auto-intake/conformance.mjs, conversation-dispatcher (fact-log append-sprawl class); needs an owner/thread