THE HOME GROUND · THE TRAILHEAD · Nº 1216 · EDITION 1 · LAUNCHING SOON

LUND CARDS · THE HOME GROUNDNº 1216

THE CARD AS TEXT · FOR EYES AND FOR MACHINES

THE GROUP RUN · Pace groups from what runners say, pacers who volunteered, and a count that matches at the end.

WAKES WHEN A club has RSVPs and needs pace groups. · The start sheet for a group run needs printing. · The finish count does not match the start.

THE LOOP

Read RSVPs and stated paces
Split into groups inside the pace band
Name volunteer pacers or say PACER NEEDED
Count everyone home and account for gaps

NEVER

Never puts a runner in a faster group
Never invents a pacer
Never closes a run with someone unaccounted

IT MAKES groups — pace groups no wider than the band in min/km (0.5 is a default; set your own); roll — roll call: MATCH or MISSING n; refuses to close a mismatch without --accounted; sheet — printable start sheet: groups, regroups, headcount boxes; export — the groups as CSV (or JSON); contacts are never exported.

THE LAW Everyone who starts is counted home. Groups follow each runner's own stated pace, pacers are people who said yes, and a run is not closed until the counts match or every gap is accounted for.

IN THE BOX SKILL.md · CARD.md · ▣ scripts/grouprun.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 13/13 · 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 · EF41D25EE4AA092B049708C1

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

THE GROUP RUN

Pace groups from what runners say, pacers who volunteered, and a count that matches at the end.

GROUPS · ROLL · 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/grouprun.py · 4 commands · selftest 13/13
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: EF41D25EE4AA092B049708C1 · sha-256 of SKILL.md · check any file against it →

CITE THIS CARDTHE GROUP RUN, Edition 1. Lund Studio LLC, Westminster, Colorado. https://lundr.tech/?view=group-run-card. Punch EF41D25EE4AA092B049708C1. Retrieved 2026-10-13.

What it is.

Use when organising a group run: splitting runners into pace groups, naming pacers, printing the start sheet, counting everyone back. Not for training plans or medical care.

It carries a machine that shows its working: groups — pace groups no wider than the band in min/km (0.5 is a default; set your own); roll — roll call: MATCH or MISSING n; refuses to close a mismatch without --accounted; sheet — printable start sheet: groups, regroups, headcount boxes; export — the groups as CSV (or JSON); contacts are never exported — 13 checks in its selftest. It never puts a runner in a faster group; never invents a pacer; never closes a run with someone unaccounted.

The law, written into the card.

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

THE LAWEveryone who starts is counted home. Groups follow each runner's own stated pace, pacers are people who said yes, and a run is not closed until the counts match or every gap is accounted for.

The method.

Read the RSVPs: each runner's stated pace and distance.
Sort by pace and split into groups no wider than the band. Each group runs at its slowest stated pace.
Name a pacer only from runners who volunteered; otherwise print PACER NEEDED.
Print the start sheet with groups, regroup points and headcount boxes. Emergency contacts, if given, appear on the sheet only and never in any export.
Count start and finish. A mismatch keeps the run open until every missing person is accounted for in writing.

What you bring.

RSVPs with each runner's stated pace and distance.
Who has volunteered to pace.
Emergency contacts, if you keep them. They are printed on the sheet only.

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

What it does once your AI has it.

groups Pace groups no wider than the band in min/km (0.5 is a default; set your own)
roll Roll call: MATCH or MISSING n; refuses to close a mismatch without --accounted
sheet Printable start sheet: groups, regroups, headcount boxes
export The groups as CSV (or JSON); contacts are never exported

What it will never do.

It never puts a runner in a faster group; never invents a pacer; never closes a run with someone unaccounted.

Where it hands off: Routes and stops → THE ROUTE VAULT; Weather calls → THE WEATHER CALL; An injury or emergency → emergency services first.

It is not safety 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/grouprun.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 or medical advice).

PROOF · SELFTEST 13/13 · WITNESSED IN CLAUDE 2026-10-13 ON FICTIONAL FIXTURES · THE TEST PROMPTS IN FRESH CHATS OWED · EDITION 1 · PUNCH EF41D25EE4AA092B049708C1

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 1216 — 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

grouprun.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.

`groups`	pace groups no wider than the band in min/km (0.5 is a default; set your own)
`roll`	roll call: MATCH or MISSING n; refuses to close a mismatch without --accounted
`sheet`	printable start sheet: groups, regroups, headcount boxes
`export`	the groups as CSV (or JSON); contacts are never exported
`selftest`	13 checks that prove the machine; it must print selftest 13/13

THE SELFTEST, AS PRINTED

ok  1  groups: five paced runners cut into two groups no wider than 0.5 min/km
ok  2  no runner is placed in a group faster than their stated pace
ok  3  pacer named only from pacer=yes; a group without one prints PACER NEEDED
ok  4  no pacer column: every group PACER NEEDED, none invented
ok  5  a runner with no pace is left UNGROUPED — NO PACE GIVEN (# comment line skipped)
ok  6  roll: equal counts print MATCH and close
ok  7  roll: mismatch prints MISSING 2 and is refused (exit 1) without --accounted, nothing logged
ok  8  roll: mismatch closes only with --accounted, and the note is logged
ok  9  sheet: regroups in order, headcount boxes, contacts shown, missing contact said plainly
ok  10  sheet without a route prints NO REGROUPS ON RECORD
ok  11  export never carries contacts (and refuses a --contacts flag)
ok  12  export is deterministic (same bytes twice)
ok  13  a pace that is not a number is bad input (exit 2)
selftest 13/13

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?

RSVPs with each runner's stated pace and distance. Who has volunteered to pace. Emergency contacts, if you keep them. They are printed on the sheet only. 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 (13/13), 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 or medical advice.

What will it never do?

It never puts a runner in a faster group; never invents a pacer; never closes a run with someone unaccounted.

← THE HOME GROUND · THE FLOOR →