M Made Scientific MADE OS · internal · noindex

MADE OS

Four things, in a fixed order. Context grounds everything. Skills are the execution units — one skill, one job, written down. Agents wrap a skill in a trigger, a schedule, an owner and a kill-switch. Tools are what they all run on. A fifth layer, method, is how any of it gets built without becoming a pile of one-offs.

This site is the honest version. It counts what is actually running on bc-made — not what the roadmap says — and it separates two kinds of gap that are usually filed together and should never be.

Live-verified 2026-08-04 by direct sweep of bc-made cron, containers and the os_* registry. 4 red findings — see below.
Read this first — the one distinction this whole site turns on

A gap in something we believe is working is an emergency. A gap in something we know we haven't built is a Tuesday.

Both get called "a gap," and that is how the first kind hides inside the second. So on every page in this site they are drawn differently and they are never mixed in the same list:

StateMeansUrgency
Broken We believe this works. It does not. The registry says live, a doc quotes it as fact, or a dashboard shows it green — and the sweep says otherwise. Now. Someone is relying on it.
Future Known, named, scoped, not built. 32 agents sit here on purpose. Roadmap. Not a problem.

A dead agent flying a live flag is worse than an agent nobody has started, because the second one is honest. Everything red on this site is red for that reason.

Where the OS actually stands

Counted, not claimed

Every number below was re-queried on 2026-08-04 against the Transfer registry (jrfcfayphcmaxsixxupu) and a live SSH sweep of bc-made. Where the registry and the machine disagree, the machine wins and the disagreement is recorded as a red finding.

Agents registered
49
across 9 fleets
Marked live
16
registry status
Live & unverifiable
4
nothing schedules them
Future build
32
9 planned · 23 draft
Active skills
62
4 domain groups
Stack components
33
7 layers
Uncatalogued runtime
22
reported every 30 min
The shape of it

Context grounds skills · skills compose into agents · tools run them · method builds them

The order matters and it is not decorative. A skill written without context produces confident nonsense. An agent built without a skill is a prompt with a cron job attached. And a fleet built without a method becomes 49 unrelated scripts that only one person understands — which is the failure mode this layer exists to prevent.

Context Skills Agents Tools· Method wraps all four
01

Agent Fleet

Every agent, its harness, archetype, trigger and host — grouped by whether it is verifiably running, believed-running-but-isn't, or deliberately not built yet.

16live · 4 contested Open →
02

Skill Library

62 active skills — the execution units. One job each, written down, versioned, and reusable by any agent or any human in a chat window.

62active · 4 domains Open →
03

Tools

The stack the fleet runs on, by layer — frontend, backend, AI, infrastructure, observability, external. What each is for and whether it's healthy.

33components · 7 layers Open →
04

Context

The grounding layer — the databases, the company brain, the wiki, the brand pack. Authored in git, retrieved from Postgres, and the reason answers are specific.

5databases · 1 brain Open →
05

Method

How an agent gets made: pick a shape, pick a harness, write the skill, set the trigger, define the stop condition, register it. The part that makes the fleet compound instead of sprawl.

8harnesses in use Open →
DEEP DIVE

Agent anatomies

Three agents documented end to end at full depth — every stage, every dependency, every guardrail, every honest limit. SCOUT and SSO AGENT are live; BEACON is a pre-build map.

SCOUT · SSO AGENT · BEACON ↗ Open →
The urgent column

Four things we believe are working that are not

These are the only red items on this site. Each one is a case where a system of record says a thing is live and the machine says it is not — which means somebody, at some point, will make a decision on a false premise. Full detail and evidence on the Agent Fleet page.

R-01

FORGE is registered live and has not run in eight weeks

Broken knowledge-platform claude-code-loop
What the sweep found /opt/made-forge exists with a review plan, prompts and a cloned repo. Its last written output is dated 2026-06-11. There is no cron entry under any user, no systemd timer, no container, and no log directory. Nothing on the box will ever start it.

Why it mattersFORGE is the overnight hostile code-reviewer for the reporting-ux app — the thing that is supposed to be catching regressions tab-by-tab while nobody is watching. Believing it runs means believing the app is under continuous review. It is not, and has not been since June.

Last review output2026-06-11
Scheduled bynothing
Registry statuslive
Cheapest resolution: either add the cron and let it run tonight, or set status to paused. Both are honest. Leaving it live is the only wrong answer.

Decision neededSchedule it, or demote it. Not a build task — a five-minute integrity task.

R-02

The nightly resolver is filed under the wrong agent

Broken name collision auto-binder
What the sweep found The fleet reporter binds cron line /opt/made-ralph/nightly.sh to the agent slug RALPH. But RALPH in the registry is a legal-language concept that was never built — its own description says so. The real nightly entity-resolution agent is RESOLVER, which also claims /opt/made-ralph as its repo path.

Why it mattersAn automated binder running every 30 minutes is confidently attributing real production work to an agent that does not exist, while the agent doing the work looks unbound. Any health rollup built on those bindings is wrong, and it is wrong in a direction that makes things look fine.

Agents claiming /opt/made-ralph2
Binder picksthe unbuilt one
Rebinds per day48
Compounding: there are also two resolver schedules — root cron 0 9 * * * running nightly.sh, and claude-user cron 0 7 * * * running run.sh. The wiki documents only the 07:00 one. Nobody wrote down the 09:00 one.

Decision neededRename the concept agent, or give the binder an explicit slug. Then reconcile the two schedules — or confirm both are intended.

R-03

PULSE and MEDIC are the same three cron lines

Broken duplicate identity
What the sweep found Three cron lines run /opt/made-pulse/pulse_monitor.py at */15, :17 hourly and 06:40. The fleet reporter binds all three to PULSE. The wiki says those crons are MEDIC and that PULSE is a separate n8n build still being refined. Both are live in the registry.

Why it mattersOne of these two agents is a phantom, and the live count is inflated by one. Worse, if PULSE-the-n8n-workflow was ever genuinely intended as a distinct thing, nobody can now tell whether it exists, because its name is already answering to somebody else's cron.

Agents bound to one cron set2
Both registry statuseslive

Decision neededPick which one owns /opt/made-pulse. Retire or rename the other.

R-04

The drift detector is not in the registry, and its alarm has been ringing for weeks

Broken /opt/made-fleet unregistered
What the sweep found Two production crons run out of /opt/made-fleetos_fleet_report.py every 30 minutes and os_provision_worker.py every 10. Neither appears in os_agents. The reporter's own output flags them as catalogued: false: it is reporting itself as drift.

Why it mattersEvery run reports drift_count: 22 and has done so continuously. Most of those 22 are client microsites that are legitimately not agents — so the number never moves, and a signal that never moves gets ignored. That is how ORPHAN-SEEDER ran unregistered for months before July. Same failure, still open.

Unregistered production crons2
Persistent drift count22
Bindings upserted per run38
The real bug is the taxonomy, not the count. A microsite container is not an uncatalogued agent. Until the reporter can say "not an agent" as a first-class answer, its drift number is noise and will be treated as noise.

Decision neededRegister the two fleet crons, then add an explicit not-an-agent classification so drift can actually reach zero and mean something.

One more, amber not red: MEDIC's own live-tier probe currently reports probed=13 ok=11 down=2 key_failing=['svc_n8n_made']. The n8n service on bc-made is a failing key target — and n8n is the harness candidate for roughly fourteen of the planned agents. Worth knowing before that roadmap gets committed to.
The not-urgent column

Thirty-two agents deliberately not built

This is the healthy list. Every one of these is named, assigned an archetype, given a candidate harness and a priority, and left alone until it is worth building. Nothing here is a problem — it is a queue, and the point of writing it down is so that "we should build a thing that does X" is answerable with "yes, it's called MOSAIC, it's p2, here's the harness."

9 planned

Next upp1

The specialist ring under DAYBREAK — daybreak, DOSSIER, PERISCOPE, trialwatch, sentinel — plus huntsman (BD), margin and redline (commercial QC), and BIBLIOGRAPHER in testing.

GateDAYBREAK requires 10 consecutive clean business days from a specialist before it promotes. That gate is the method working as designed.

23 draft

Cataloguedp2 · p3

Named and shaped, not scheduled. Includes BEACON — which already has a full pre-build map precisely because doing the discovery before the build is cheaper than after.

Why write them down at allAn unnamed idea gets rebuilt three times. A named draft gets built once.

2 planned tools

Stack

Agent Cost Ledger — per-run cost tracking, currently absent, which is why cost caps are enforced per-agent rather than centrally. Langchain — under evaluation for RAG, not adopted.

NoteThe cost ledger is the one future item with a live consequence: without it, spend is visible per agent but not in aggregate.

Scope, so this page isn't mistaken for something it isn't

This is a mirror, not a control panel

Everything here is read-only and BC-owned. The site reads the Transfer os_* registry and the bc-made machine. It writes nothing, triggers nothing, and never touches Joe's made-ai-os authoring loop — that stays canonical.

The working cockpit is still the reporting-ux app (/made-os, /agents-os, /skills-library, /heartbeat). This site is the narrative layer over the same truth: shareable by URL, readable without a login, and blunt enough to be useful in a planning conversation.

RED line, unchanged: nothing in the OS writes Salesforce, pipeline, price or revenue.