THE HOME GROUND · THE MARKET ROW · Nº 1223 · EDITION 1 · LAUNCHING SOON

LUND CARDS · THE HOME GROUNDNº 1223

THE CARD AS TEXT · FOR EYES AND FOR MACHINES

THE VESSEL KEY · Codes printed on your goods that open the right card page: checked, issued once, label words only.

WAKES WHEN A maker issues codes for a batch of products. · A scanned code needs checking. · A customer asks how to use the product a code is printed on.

THE LOOP

Issue codes for a batch, each one once
Check a code: VALID, BAD CHECK, UNKNOWN
Print the code sheet for the printer
Quote the maker's label and add nothing

NEVER

Never issues a serial twice
Never adds advice beyond the maker's label
Never accepts a code that fails its check

IT MAKES issue — add N new codes to codes.csv; each url is base-url + /k/ + code; verify — print VALID, BAD CHECK, UNKNOWN BATCH or NOT ISSUED; label — print the maker's own label lines for SKU, word for word; sheet — print a text sheet of that batch's codes and urls; export — write every code as JSON (stdout unless --out).

THE LAW A code is issued once and checked every time. When a customer asks how to use the product, the card reads the maker's own label and adds nothing to it.

IN THE BOX SKILL.md · CARD.md · ▣ scripts/vesselkey.py (machine) · ▣ scripts/evals.py (test runner) · tests/EVALS.json (8 tests) · references/ (schema + fictional demo) · START-HERE.md · system/ doors · MY-LEDGER.md · LICENSE-NOTE.md · card.svg · card.json · card.html · AUDIT.md · MANIFEST.md · WITNESS.md · SELFTEST.md.

PROOF SELFTEST 14/14 · witnessed in Claude 2026-10-13 on fictional fixtures · the test prompts in fresh chats owed · Edition 1.

THE SEAL 96 of 100 · LEGENDARY · WITNESSED · Trigger 5 · Machinery 5 · Law 5 · Portability 5 · Proof 4

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. LICENSE-NOTE.md rides in the packet and is the licence.

THE PUNCH · SHA-256 OF SKILL.MD · B9714BF60758E617610603A7

THE FACE, FULL SIZE → · THE MACHINE FACE → · card.json →

THE VESSEL KEY

Codes printed on your goods that open the right card page: checked, issued once, label words only.

ISSUE · VERIFY · LABEL · SHEET · EXPORT

LEGENDARYWITNESSEDIN CLAUDE IN LUNDR IN CHATGPT

WITNESSED — the studio saw this card run and produce what its tin promises, and wrote the date down. What the marks mean →

THE SPEC SHEET · READ BEFORE YOU BUY · THE STANDARD EVERY CARD MEETS →

SEAL: 96 of 100 · LEGENDARY · WITNESSED
EDITION: E1 · witnessed 2026-10-13
MACHINE: scripts/vesselkey.py · 5 commands · selftest 14/14
RUNS: On your own computer. Standard library only, offline; no account, no key, no telemetry.
HOSTS: Claude · Claude Code · ChatGPT · Gemini · any AI that reads a file (START-HERE.md and system/ name each door)
LICENCE: One person, any number of their own AIs and computers · editions replace files · nothing renews · freeze, not loss
PUNCH: B9714BF60758E617610603A7 · sha-256 of SKILL.md · check any file against it →

CITE THIS CARDTHE VESSEL KEY, Edition 1. Lund Studio LLC, Westminster, Colorado. https://lundr.tech/?view=vessel-key-card. Punch B9714BF60758E617610603A7. Retrieved 2026-10-13.

What it is.

Use when a maker prints codes on physical products that open a card or page: issuing serials, checking a scanned code, printing code sheets. Not for nutrition or dosing advice.

It carries a machine that shows its working: issue — add N new codes to codes.csv; each url is base-url + /k/ + code; verify — print VALID, BAD CHECK, UNKNOWN BATCH or NOT ISSUED; label — print the maker's own label lines for SKU, word for word; sheet — print a text sheet of that batch's codes and urls; export — write every code as JSON (stdout unless --out) — 14 checks in its selftest. It never issues a serial twice; never adds advice beyond the maker's label; never accepts a code that fails its check.

The law, written into the card.

It is in the card itself, so the AI follows it.

THE LAWA code is issued once and checked every time. When a customer asks how to use the product, the card reads the maker's own label and adds nothing to it.

The method.

Issue codes for a SKU and batch: serial numbers in order, each with a check character, each with the page address it opens.
Refuse to issue a serial that already exists.
Check any scanned code: VALID, BAD CHECK (a mistyped or forged code), UNKNOWN BATCH or NOT ISSUED.
Print the code sheet for the printer.
For how-to questions, quote the maker's label word for word, starting 'From the maker's label:'.

What you bring.

Your SKUs and batch numbers.
Your label text, word for word.
The base address of your card pages.

Nothing of the studio's is needed; the data is yours.

What it does once your AI has it.

issue Add N new codes to codes.csv; each url is base-url + /k/ + code
verify Print VALID, BAD CHECK, UNKNOWN BATCH or NOT ISSUED
label Print the maker's own label lines for SKU, word for word
sheet Print a text sheet of that batch's codes and urls
export Write every code as JSON (stdout unless --out)

What it will never do.

It never issues a serial twice; never adds advice beyond the maker's label; never accepts a code that fails its check.

Where it hands off: Hydration or nutrition questions → a qualified professional; The drop itself → THE MAKER'S DROP; Booth sales → THE EXPO BOOTH.

It is not nutrition or medical advice. It is an AI reading a text file: it can be wrong, so check what matters against your own records and the source. The holder brings their own AI; no endorsement by Anthropic or any other AI company is claimed.

What’s in the buy.

SKILL.md — the card your AI reads: when it wakes, the loop, the never-lines, the hand-offs.
CARD.md — the whole card in ten sections: face, law, method, machine, what you bring, never, tests, seal, term.
scripts/vesselkey.py — the machine, Python standard library only; `selftest` proves it on its own fixtures.
tests/EVALS.json and scripts/evals.py — 8 test prompts and the offline runner that scores your AI's answers.
references/ — the data schema and FICTIONAL demo files, invented to show the machine, not real.
MY-LEDGER.md — your own record of what you asked and what you decided.
START-HERE.md, system/short-prompt.md, system/rules.md — the doors, for any AI with or without skills.
card.svg, card.json, card.html, AUDIT.md, MANIFEST.md, WITNESS.md, SELFTEST.md — the faces and the proof.
NOT IN THE BOX — nothing of the studio's is needed; the data is yours. Also not in the box: any data you must bring, and advice of any kind (not nutrition or medical advice).

PROOF · SELFTEST 14/14 · WITNESSED IN CLAUDE 2026-10-13 ON FICTIONAL FIXTURES · THE TEST PROMPTS IN FRESH CHATS OWED · EDITION 1 · PUNCH B9714BF60758E617610603A7

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 1223 — 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 · NOTHING RENEWS ITSELF

OFFLINE · ONE LICENCE · PUNCH-CHECKABLE · THE STANDARD

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 CARD’S OWN SELFTEST.MD

vesselkey.py, every command showing its working.

A small Python program, standard library only. Your AI runs it; you can too. The block below is pasted from the card’s own SELFTEST.md, as printed when it was run from inside the packet.

`issue`	add N new codes to codes.csv; each url is base-url + /k/ + code
`verify`	print VALID, BAD CHECK, UNKNOWN BATCH or NOT ISSUED
`label`	print the maker's own label lines for SKU, word for word
`sheet`	print a text sheet of that batch's codes and urls
`export`	write every code as JSON (stdout unless --out)
`selftest`	14 checks that prove the machine; it must print selftest 14/14

THE SELFTEST, AS PRINTED

ok  1  Luhn mod 36 round trip: every made check character verifies (24 codes)
ok  2  docstring's worked example holds: check of A1 is O and A1O verifies
ok  3  every single mistyped character is caught
ok  4  issue writes 3 codes, each url = base-url + /k/ + code
ok  5  issue refuses a serial already issued and keeps the '#' note
ok  6  verify prints VALID with the url for an issued code
ok  7  verify prints BAD CHECK for an altered check character
ok  8  verify prints UNKNOWN BATCH for a batch not on file
ok  9  verify prints NOT ISSUED for a good code never issued
ok  10  verify rejects a malformed code with exit 2
ok  11  label prints 'From the maker's label:' and the maker's lines, adding nothing
ok  12  label refuses a SKU with no label on file (NO LABEL ON FILE)
ok  13  sheet lists the batch's 3 codes in serial order
ok  14  export gives the same bytes twice and holds 3 codes
selftest 14/14

THE RUN IS PASTED FROM THE CARD’S OWN SELFTEST.MD AS PRINTED. ITS FIXTURES ARE FICTIONAL, INVENTED FOR THE TEST; NO PRIVATE PERSON IS NAMED.

QUESTIONS AT THE TABLE

Asked before the wire.

What does it need from me?

Your SKUs and batch numbers. Your label text, word for word. The base address of your card pages. If something it needs is missing, it says what is missing and stops there.

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 machine's selftest (14/14), run from inside the packet in Claude on 2026-10-13 on fictional fixtures and pasted into SELFTEST.md as printed; the twelve-check audit (AUDIT.md). Owed, and said so in WITNESS.md: The 8 test prompts asked in fresh chats with the card installed. Until they are run and scored, the tests are owed. Any run on real data. Every demo file is fictional. 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 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. LICENSE-NOTE.md rides in the packet and is the licence. It is not nutrition or medical advice.

What will it never do?

It never issues a serial twice; never adds advice beyond the maker's label; never accepts a code that fails its check.

← THE HOME GROUND · THE FLOOR →