THE HOME GROUND · THE TRAILHEAD · Nº 1218 · EDITION 1 · LAUNCHING SOON

LUND CARDS · THE HOME GROUNDNº 1218

THE CARD AS TEXT · FOR EYES AND FOR MACHINES

THE WEATHER CALL · Race-day go, modify, delay or cancel against the director's own thresholds, with the call logged.

WAKES WHEN A director has readings and needs them set against the event's thresholds. · Lightning, heat, wind or air quality is near the event's lines. · The decision needs logging with who made it and when.

THE LOOP

Load the director's thresholds
Take the latest readings and their sources
Each measure: GO, MODIFY, DELAY or CANCEL
Log the call with who decided and when

NEVER

Never sets a threshold for the director
Never makes the call
Never uses a stale reading as current

IT MAKES call — each measure vs your threshold, the readings used and their sources; readings older than --max-age minutes (default 30, set your own) print STALE; log — append the director's decision; refused without --by; history — every logged decision in time order; export — every reading with its call against your thresholds, as CSV (or JSON).

THE LAW The director decides. The card holds the director's own thresholds, sets the latest readings against them, says which line each one crosses, and writes the call into a log with a name and a time.

IN THE BOX SKILL.md · CARD.md · ▣ scripts/weathercall.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 17/17 · 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 · 849DB42E16DA91B86A66730B

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

THE WEATHER CALL

Race-day go, modify, delay or cancel against the director's own thresholds, with the call logged.

CALL · LOG · HISTORY · 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/weathercall.py · 4 commands · selftest 17/17
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: 849DB42E16DA91B86A66730B · sha-256 of SKILL.md · check any file against it →

CITE THIS CARDTHE WEATHER CALL, Edition 1. Lund Studio LLC, Westminster, Colorado. https://lundr.tech/?view=weather-call-card. Punch 849DB42E16DA91B86A66730B. Retrieved 2026-10-13.

What it is.

Use when an event director checks readings against their own weather thresholds and logs the call. Not a forecast and not a safety standard; the director decides.

It carries a machine that shows its working: call — each measure vs your threshold, the readings used and their sources; readings older than --max-age minutes (default 30, set your own) print STALE; log — append the director's decision; refused without --by; history — every logged decision in time order; export — every reading with its call against your thresholds, as CSV (or JSON) — 17 checks in its selftest. It never sets a threshold for the director; never makes the call; never uses a stale reading as current.

The law, written into the card.

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

THE LAWThe director decides. The card holds the director's own thresholds, sets the latest readings against them, says which line each one crosses, and writes the call into a log with a name and a time.

The method.

Load the director's thresholds for lightning, heat, wind, air quality and wind chill. A measure with no threshold prints NO THRESHOLD SET.
Take the latest reading at or before the decision time, with its source. A reading older than the limit prints STALE.
Set each measure against its lines. The strongest line wins: CANCEL over DELAY over MODIFY over GO.
Write the decision into the log with the director's name, the time and a note. No name, no entry.

What you bring.

Your thresholds, set with your medical lead and governing body.
Readings from the sources you trust, with times.

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

What it does once your AI has it.

call Each measure vs your threshold, the readings used and their sources; readings older than --max-age minutes (default 30, set your own) print STALE
log Append the director's decision; refused without --by
history Every logged decision in time order
export Every reading with its call against your thresholds, as CSV (or JSON)

What it will never do.

It never sets a threshold for the director; never makes the call; never uses a stale reading as current.

Where it hands off: The forecast itself → the national weather service; Medical response → the event's medical lead; Event logistics → THE RACE DIRECTOR.

It is not safety 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/weathercall.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 safety advice).

PROOF · SELFTEST 17/17 · WITNESSED IN CLAUDE 2026-10-13 ON FICTIONAL FIXTURES · THE TEST PROMPTS IN FRESH CHATS OWED · EDITION 1 · PUNCH 849DB42E16DA91B86A66730B

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 1218 — 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

weathercall.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.

`call`	each measure vs your threshold, the readings used and their sources; readings older than --max-age minutes (default 30, set your own) print STALE
`log`	append the director's decision; refused without --by
`history`	every logged decision in time order
`export`	every reading with its call against your thresholds, as CSV (or JSON)
`selftest`	17 checks that prove the machine; it must print selftest 17/17

THE SELFTEST, AS PRINTED

ok  1  calm readings are GO on every measure with a threshold
ok  2  AQI with no threshold prints NO THRESHOLD SET and is not checked
ok  3  strike 10 km away, 12 min ago, inside 16 km / 30 min → DELAY; heat 29 → MODIFY; worst DELAY
ok  4  CANCEL beats DELAY (lightning DELAY, strike 06:18; heat 34 from a second source at 06:45 is over the 33 cancel line)
ok  5  call prints the header, the readings used and their sources
ok  6  before any reading: NO READING on every measure and NO CALL (exit 1)
ok  7  a reading 60 min old is marked STALE and exits 1
ok  8  close strike (7 km, newest reading) older than the wait (40 min ≥ 30) → GO, and the wait rule says so
ok  9  close strike at 07:00, far reading at 07:05, call at 07:05 → DELAY naming the 07:00 reading and strike time
ok  10  close strike exactly at the wait boundary: 29 min after → DELAY, 30 min after → GO
ok  11  close reading with no last_strike_min_ago: strike taken at the reading time → DELAY
ok  12  export looks back for lightning: the far 07:05 row still carries DELAY from the 07:00 strike
ok  13  wind chill -12 is at or below the -10 modify line → MODIFY
ok  14  log without --by is refused (exit 1) and writes nothing
ok  15  log appends with the name; history lists decisions in time order
ok  16  a decision outside GO/MODIFY/DELAY/CANCEL is bad input (exit 2)
ok  17  export is deterministic and carries a call per reading
selftest 17/17

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 thresholds, set with your medical lead and governing body. Readings from the sources you trust, with times. 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 (17/17), 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 safety advice.

What will it never do?

It never sets a threshold for the director; never makes the call; never uses a stale reading as current.

← THE HOME GROUND · THE FLOOR →