THE HOME GROUND · THE TRAILHEAD · Nº 1217 · EDITION 1 · LAUNCHING SOON

LUND CARDS · THE HOME GROUNDNº 1217

THE CARD AS TEXT · FOR EYES AND FOR MACHINES

THE FIRST RACE · A first race picked by arithmetic on your own numbers: cutoff margins, build weeks, no promises.

WAKES WHEN A newer runner has a race list and wants to know which fit. · Someone asks whether they can make a race's cutoff. · A runner wants every number behind a verdict explained.

THE LOOP

Read the race list and the runner's numbers
Project the finish against each cutoff
Check build weeks by the ladder rule
Say FITS, TIGHT or NOT YET, and why

NEVER

Never promises a finish
Never fits a race with no cutoff on record
Never gives medical clearance

IT MAKES fit — every race: weeks, ladder, projected finish, cutoff margin, verdict (FITS first by date); 0.1 and 15 are defaults you can change; explain — every number for one race and the file and field it came from; export — the fit table as CSV (or JSON).

THE LAW A fit is arithmetic on the runner's own numbers, printed with every number it used. The card says when a race is tight, when it is not yet, and when a cutoff is not on record.

IN THE BOX SKILL.md · CARD.md · ▣ scripts/firstrace.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 · C7EB8C1C85D8909CE6DC5199

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

THE FIRST RACE

A first race picked by arithmetic on your own numbers: cutoff margins, build weeks, no promises.

FIT · EXPLAIN · 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/firstrace.py · 3 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: C7EB8C1C85D8909CE6DC5199 · sha-256 of SKILL.md · check any file against it →

CITE THIS CARDTHE FIRST RACE, Edition 1. Lund Studio LLC, Westminster, Colorado. https://lundr.tech/?view=first-race-card. Punch C7EB8C1C85D8909CE6DC5199. Retrieved 2026-10-13.

What it is.

Use when a newer runner picks a first race from a race list against their own pace, longest run and weeks available. Not a training plan, a promise to finish or medical advice.

It carries a machine that shows its working: fit — every race: weeks, ladder, projected finish, cutoff margin, verdict (FITS first by date); 0.1 and 15 are defaults you can change; explain — every number for one race and the file and field it came from; export — the fit table as CSV (or JSON) — 14 checks in its selftest. It never promises a finish; never fits a race with no cutoff on record; never gives medical clearance.

The law, written into the card.

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

THE LAWA fit is arithmetic on the runner's own numbers, printed with every number it used. The card says when a race is tight, when it is not yet, and when a cutoff is not on record.

The method.

Read the race list (date, distance, climb, cutoff) and the runner's own numbers (longest recent run, comfortable pace, weeks available).
Project a finish from distance and pace, with a stated allowance for climbing.
Set the projection against the cutoff and print the margin. Under the tight line it prints TIGHT.
Check the weeks needed to build from the longest recent run by the ladder rule, printed with the verdict.
Explain any race on request: every number and where it came from.

What you bring.

A race list with dates, distances, climbs and cutoffs.
Your longest recent run, your comfortable pace and the weeks you have.

Planned as a separate seat, not in this box and not yet on sale: a ranked list of the races the studio covers.

What it does once your AI has it.

fit Every race: weeks, ladder, projected finish, cutoff margin, verdict (FITS first by date); 0.1 and 15 are defaults you can change
explain Every number for one race and the file and field it came from
export The fit table as CSV (or JSON)

What it will never do.

It never promises a finish; never fits a race with no cutoff on record; never gives medical clearance.

Where it hands off: A build to get there → THE RUNNER; The course details → THE COURSE BOOK; Health questions → a clinician.

It is not training 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/firstrace.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 — any studio edition (planned, not yet on sale: a ranked list of the races the studio covers). Also not in the box: any data you must bring, and advice of any kind (not training 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 C7EB8C1C85D8909CE6DC5199

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 1217 — 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

firstrace.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.

`fit`	every race: weeks, ladder, projected finish, cutoff margin, verdict (FITS first by date); 0.1 and 15 are defaults you can change
`explain`	every number for one race and the file and field it came from
`export`	the fit table as CSV (or JSON)
`selftest`	14 checks that prove the machine; it must print selftest 14/14

THE SELFTEST, AS PRINTED

ok  1  ladder: 8 km to 10 km is a 25% increase, 2 weeks needed
ok  2  ladder: a race more than double the longest run is NOT YET
ok  3  projected finish = 10 x 6.0 x (1 + 100/1000 x 0.1) = 60.6 min, margin 2.3% → TIGHT
ok  4  a race with room on both build and cutoff is FITS (margin 33.3%)
ok  5  no cutoff on the list → NO CUTOFF ON RECORD, never FITS
ok  6  no gain on the list → NO GAIN ON RECORD and no projection invented
ok  7  a race already run → PAST
ok  8  sort: FITS first by date (Early Fit before Late Fit), then TIGHT
ok  9  fit prints the not-a-promise / not-medical-advice line and the ladder rule
ok  10  5 km to 10 km is a 100% increase, 8 weeks needed; 3 weeks available → NOT YET
ok  11  explain names the file and field behind each number
ok  12  explain on an unknown race is bad input (exit 2)
ok  13  export is deterministic (same bytes twice)
ok  14  runner.json missing the pace is bad input (exit 2), nothing guessed
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?

A race list with dates, distances, climbs and cutoffs. Your longest recent run, your comfortable pace and the weeks you have. 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 training or medical advice.

What will it never do?

It never promises a finish; never fits a race with no cutoff on record; never gives medical clearance.

← THE HOME GROUND · THE FLOOR →