THE HOME GROUND · THE MARKET ROW · Nº 1224 · EDITION 1 · LAUNCHING SOON

LUND CARDS · THE HOME GROUNDNº 1224

THE CARD AS TEXT · FOR EYES AND FOR MACHINES

THE EXPO BOOTH · One booth counted by the hour: traffic, stops, sales, sell-through, and what it really netted.

WAKES WHEN A maker is counting a booth's traffic and sales. · After the event, someone wants the real net. · Two booths need comparing.

THE LOOP

Tally each hour: passers, stops, sales
Report stop rate, conversion, sell-through
Net after fee, travel and goods
Break even, and compare booths

NEVER

Never counts an uncounted hour as zero
Never shows a net without its costs
Never invents traffic

IT MAKES tally-add — append one counted row (refuses an hour the booth was not open); report — traffic per hour, stop rate, conversion, revenue, cost of goods, net, best and worst hours, sell-through per SKU, units left; breakeven — units needed at the average margin to cover fee + travel + other_costs; compare — two booths side by side (each uses its own tally and stock files); export — the report's numbers as JSON.

THE LAW A booth is judged on what was counted. Hours nobody counted say NOT COUNTED, and the net is shown with every cost that made it.

IN THE BOX SKILL.md · CARD.md · ▣ scripts/booth.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 16/16 · 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 · 17E79F5871188694F5A3B785

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

THE EXPO BOOTH

One booth counted by the hour: traffic, stops, sales, sell-through, and what it really netted.

TALLY-ADD · REPORT · BREAKEVEN · COMPARE · 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/booth.py · 5 commands · selftest 16/16
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: 17E79F5871188694F5A3B785 · sha-256 of SKILL.md · check any file against it →

CITE THIS CARDTHE EXPO BOOTH, Edition 1. Lund Studio LLC, Westminster, Colorado. https://lundr.tech/?view=expo-booth-card. Punch 17E79F5871188694F5A3B785. Retrieved 2026-10-13.

What it is.

Use when a maker runs a booth at an expo or market and counts traffic, stops and sales by hour to see what it netted. Not for choosing events or for tax advice.

It carries a machine that shows its working: tally-add — append one counted row (refuses an hour the booth was not open); report — traffic per hour, stop rate, conversion, revenue, cost of goods, net, best and worst hours, sell-through per SKU, units left; breakeven — units needed at the average margin to cover fee + travel + other_costs; compare — two booths side by side (each uses its own tally and stock files); export — the report's numbers as JSON — 16 checks in its selftest. It never counts an uncounted hour as zero; never shows a net without its costs; never invents traffic.

The law, written into the card.

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

THE LAWA booth is judged on what was counted. Hours nobody counted say NOT COUNTED, and the net is shown with every cost that made it.

The method.

Set the booth up: fee, travel, other costs and opening hours.
Tally each hour: people passing, people stopping, sales and revenue by SKU.
Report the stop rate, conversion, revenue, cost of goods, net after fixed costs, best and worst hours, and sell-through by SKU.
Work out the break-even in units at the average margin.
Compare two booths side by side.

What you bring.

Your booth fee, travel and costs.
Your hourly tally: passers, stops, sales.
The stock you brought, its unit cost and price.

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

What it does once your AI has it.

tally-add Append one counted row (refuses an hour the booth was not open)
report Traffic per hour, stop rate, conversion, revenue, cost of goods, net, best and worst hours, sell-through per SKU, units left
breakeven Units needed at the average margin to cover fee + travel + other_costs
compare Two booths side by side (each uses its own tally and stock files)
export The report's numbers as JSON

What it will never do.

It never counts an uncounted hour as zero; never shows a net without its costs; never invents traffic.

Where it hands off: Taxes on booth sales → a tax professional; The product drop → THE MAKER'S DROP; Product codes → THE VESSEL KEY.

It is not tax or financial 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/booth.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 tax or financial advice).

PROOF · SELFTEST 16/16 · WITNESSED IN CLAUDE 2026-10-13 ON FICTIONAL FIXTURES · THE TEST PROMPTS IN FRESH CHATS OWED · EDITION 1 · PUNCH 17E79F5871188694F5A3B785

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 1224 — 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

booth.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.

`tally-add`	append one counted row (refuses an hour the booth was not open)
`report`	traffic per hour, stop rate, conversion, revenue, cost of goods, net, best and worst hours, sell-through per SKU, units left
`breakeven`	units needed at the average margin to cover fee + travel + other_costs
`compare`	two booths side by side (each uses its own tally and stock files)
`export`	the report's numbers as JSON
`selftest`	16 checks that prove the machine; it must print selftest 16/16

THE SELFTEST, AS PRINTED

ok  1  report sums passers 150, stops 30, sales 4, revenue 75.00
ok  2  an open hour with no counts (a blank row) prints NOT COUNTED, never 0
ok  3  stop rate 20.0% and conversion 13.3% printed with what they came from
ok  4  cost of goods 25.00 and net -70.00 = revenue - cogs - fixed
ok  5  sell-through per SKU and units left (A 3 of 10, 7 left; B 1 of 4, 3 left)
ok  6  best hour day 1 09:00, worst counted day 1 10:00; a row outside open hours is named
ok  7  breakeven: avg margin 12.86 over 14 units, 10 units needed, rule printed
ok  8  breakeven refuses when there is no positive margin
ok  9  net NOT COMPUTED when costs are missing or revenue blank; fixed costs UNKNOWN
ok  10  compare prints both booths side by side
ok  11  tally-add refuses an hour the booth was not open
ok  12  tally-add rejects a negative count with exit 2
ok  13  tally-add appends a row that report then counts (passers 190)
ok  14  SOLD MORE THAN BROUGHT is flagged, not hidden
ok  15  export gives the same bytes twice
ok  16  a sale with no sku makes cost of goods UNKNOWN and is named, not given a SKU
selftest 16/16

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 booth fee, travel and costs. Your hourly tally: passers, stops, sales. The stock you brought, its unit cost and price. 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 (16/16), 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 tax or financial advice.

What will it never do?

It never counts an uncounted hour as zero; never shows a net without its costs; never invents traffic.

← THE HOME GROUND · THE FLOOR →