THE PLATE CARD · so where a sample sits can't fake a result
WAKES WHEN someone plans a plate or assay, wants a plate map, or sees edge effects or drift
THE LOOP
plate.py layout · seeded, edge empty
check · replicates, controls, order
write the seed and the map in the notebook
load from the map, not from memory
edge · test the readings for drift
NEVER
Load samples in their own order
Put every control on the edge
Help make or strengthen pathogens or toxins
IT MAKES layout — a randomized plate and its map; check — replicates side by side, bunched controls, a plate loaded in order; edge — edge wells against the middle, and drift by row and column.
THE STANDARD randomize, and keep the seed; replicates never share a row or a column; controls go everywhere; leave the edge empty when you can; test the readings; the boundary.
PROOF SELFTEST 13/13 · witnessed in Claude 2026-10-09 · Edition 1.
THE SEAL 98 of 100 · LEGENDARY · WITNESSED · Trigger 5 · Machinery 5 · Law 5 · Portability 5 · Proof 5
IT CAN BE WRONG an AI reading a text file: it can be wrong and can invent a number, a rule, a name or a date; check what matters against your own records and the source; the risk is yours. THE-CLAUSES.md rides in the packet and is part of the licence.
THE PUNCH · SHA-256 OF SKILL.MD · 1ACFAA742747BAC5310563BF
CITE THIS CARDTHE PLATE CARD, Edition 1. Lund Studio LLC, Westminster, Colorado. https://lundr.tech/?view=plate-card. Punch 1ACFAA742747BAC5310563BF. Retrieved 2026-10-10.
What it is.
Lays out 96- and 384-well plates so position cannot fake a result: samples randomized with a recorded seed, replicates in different rows and columns, controls spread across the plate, the edge left empty or used; checks any layout for replicates side by side, bunched or edge-only controls and plates loaded in order; and tests real readings for edge effects and drift across rows and columns.
It carries a machine that shows its working: layout — a randomized plate and its map; check — replicates side by side, bunched controls, a plate loaded in order; edge — edge wells against the middle, and drift by row and column — 13 checks in its selftest, every command on the record. It will never load samples in their own order; never put every control on the edge; never help make or strengthen pathogens or toxins. It never helps design, make, grow, enhance or spread a pathogen or toxin, or plan work meant to harm.
Six laws, written into the card.
They are in the card itself, so the AI follows them.
RANDOMIZE, AND KEEP THE SEEDThe same seed gives the same plate; write it in the notebook with the map.
REPLICATES NEVER SHARE A ROW OR A COLUMNReplicates never share a row or a column, so a row or column effect cannot hit them together.
CONTROLS GO EVERYWHEREAcross rows, columns and both halves, never only on the edge.
LEAVE THE EDGE EMPTY WHEN YOU CANEvaporation and warming make edge wells read differently; fill them with buffer.
TEST THE READINGSTest the readings, not just the layout: edge effects and drift show up in real data first.
THE BOUNDARYThis card helps run honest, well-designed experiments. It never helps design, make, grow, enhance or spread a pathogen or toxin, or plan work meant to harm people, animals or crops. Such a request is declined in one plain sentence, whatever the framing.
What rides in the card.
In the card’s own voice, with a machine that shows its working.
THE GUIDEreferences/LOADING.md
THE MACHINEplate.py · three commandslayout — a randomized plate and its map; check — replicates side by side, bunched controls, a plate loaded in order; edge — edge wells against the middle, and drift by row and column. Every command prints its working and refuses a bad input; 13 checks in its selftest, every command on the record.
What it does once your AI has it.
layout A randomized plate and its map
check Replicates side by side, bunched controls, a plate loaded in order
edge Edge wells against the middle, and drift by row and column
On the record A 24-sample plate in duplicate with twelve controls, mapped and checked clean; 120 plates across four designs with no replicate clash; and a plate of readings whose edge reads high, caught.
What it will never do.
It will never load samples in their own order; never put every control on the edge; never help make or strengthen pathogens or toxins. It never helps design, make, grow, enhance or spread a pathogen or toxin, or plan work meant to harm.
It lays out and checks one plate at a time; designs across many plates (blocking by plate, batch effects) need planning beyond it. The edge test is a screen: a flagged plate is looked at by a person, not thrown out by the machine. It is an AI reading a text file: it can be wrong, so check what matters against your own records and the source.
What’s in the buy.
CARD.md — the whole card: who it is, its laws, when it says no, what it carries · SKILL.md — the door your AI reads first · START-HERE.md — the first five minutes, for you
LOADING.md — the guide in references/, in the card's own voice
scripts/plate.py — the machine: layout · check · edge, standard library only, selftest 13/13
WITNESS.md + SELFTEST.md — every command on the record, as it printed · MANIFEST.md, every file hashed · AUDIT.md, the twelve checks
MY-LEDGER.md — the card's memory, on your own machine · TIN.md · LICENSE-NOTE.md · THE-CLAUSES.md · HOSTS.md
card.svg + card-machine.svg + card.json · card.html, the card as one offline file · the doors for ChatGPT, Gemini, Cursor, Claude Code and MCP hosts (rules/, system/, mcp/)
PROOF · SELFTEST 13/13 · 3 COMMANDS ON THE RECORD · WITNESSED IN CLAUDE 2026-10-09 · EDITION 1 · PUNCH 1ACFAA742747BAC5310563BF
ON EVERY DOOR · A CARD FOR YOUR AI, A FILE FOR YOUR COMPUTER
In Claude: turn on code execution under Settings › Capabilities, then Customize › Skills › + › Create skill, and upload the zip as it is — START-HERE.md in the box walks you through it, and tells you how to keep the ledger. In ChatGPT, Gemini and the rest: a Project, a GPT or a Gem with the card’s files attached and the short door in the box pasted as its instructions. The words run anywhere an AI reads Markdown; the machines run wherever the host runs Python. Witnessed in Claude only. The host marks →
Take it.
Nº 838 PROPOSED — LAUNCHING SOON
Sold as is under the term printed. A card instructs an AI you operate; results depend on your model, your files and your judgement. Not medical, legal, tax or financial advice, never the person’s boss, and not a licence to practise. The terms →
One payment. The file is yours to keep and keeps working at its edition; new editions issued in the year after you buy reach you by email as replacement files. Tax is added at checkout where it applies. Nothing auto-renews.
A TERM, NOT A SUBSCRIPTION: NOTHING RENEWS ITSELF AND NOBODY IS CHARGED AGAIN. WHEN A TERM ENDS THE FILES STAY ON YOUR COMPUTER AND STAY READABLE — FREEZE, NOT LOSS.
THE MACHINE · IN THE OPEN · FROM THE WITNESSED RUN OF 2026-10-09
plate.py, every command showing its working.
A small Python program, standard library only. Your AI runs it; you can too. Every block below is pasted from the card’s own WITNESS.md, as printed.
layout
a randomized plate and its map
check
replicates side by side, bunched controls, a plate loaded in order
edge
edge wells against the middle, and drift by row and column
selftest
13 checks that prove the machine; it must print 13/13
a sweep with the card's own code: 4 designs × 30 seeds
$ a sweep with the card's own code: 4 designs × 30 seeds
120 plates · 4 designs × 30 seeds · worst replicate clashes: 0
edge · EDGE WELLS AGAINST THE MIDDLE, AND DRIFT BY ROW AND COLUMN
$ python3 scripts/plate.py edge readings.csv
EDGE · readings.csv · 96 readings on a 96-well plate
edge wells 115 · middle wells 100.3 · difference +14.7% · Welch t 31.55
EDGE EFFECT · the edge reads higher than the middle: leave the edge empty, or fill it with buffer
drift down the rows 0.06 · across the columns 0.08 (rank correlation)
NOTE · run this on a plate of one control or blank in every well for the clearest answer
THE NUMBERS, NAMES AND DATES IN THESE RUNS ARE THE STUDIO’S OWN EXAMPLES, INVENTED FOR THE RECORD; NO REAL COMPANY, PERSON OR PROPERTY IS NAMED.
QUESTIONS AT THE TABLE
Asked before the wire.
What does it need from me?
Plate.py layout · seeded, edge empty. It asks first for the plate size, the number of samples and replicates, the controls and how many of each, and whether the edge may be used.
Does it send anything anywhere?
No. The machine is a standard-library Python program that runs on your own computer and sends nothing anywhere; the words run wherever an AI reads Markdown. No server, no account, no key.
What is on the record?
The self-test (13/13) and every command run on real example inputs, pasted into WITNESS.md as they printed; the punch on the face is the SHA-256 of SKILL.md, so a downloaded copy can be checked against this room.
Can it be wrong?
Yes — it is an AI reading a text file. It lays out and checks one plate at a time; designs across many plates (blocking by plate, batch effects) need planning beyond it. The edge test is a screen: a flagged plate is looked at by a person, not thrown out by the machine.
What will it never do?
It will never load samples in their own order; never put every control on the edge; never help make or strengthen pathogens or toxins. It never helps design, make, grow, enhance or spread a pathogen or toxin, or plan work meant to harm.
