THE VOLUNTEER CARD · Fills volunteer shifts fairly, keeps screened roles screened, and shows every gap with its reason.
WAKES WHEN Build days, events or programs need volunteers · Someone asks why a shift is unfilled · Volunteer hours need totalling
THE LOOP
Take the roster and the shifts.
Run `schedule`.
Read GAPS.md and decide whom to ask.
Send each person their own reminder.
Run `hours` after the event.
NEVER
Puts an unscreened person on a screened role
Shares one volunteer's contact with another
Runs a background check
IT MAKES schedule — fill shifts and write reminders; hours — total logged hours.
THE STANDARD screened roles go only to people marked yes; fewest hours so far is asked first; every gap carries its reason; donor; verify by execution; say the limit out loud in the work; nothing hidden; the person decides.
PROOF SELFTEST 15/15 · witnessed 2026-10-13 on material and live on Claude · Edition 1.
THE SEAL 92 of 100 · LEGENDARY · WITNESSED · Trigger 4 · 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 · 18831635D44F1FC9CC15FEE9
CITE THIS CARDTHE VOLUNTEER CARD, Edition 1. Lund Studio LLC, Westminster, Colorado. https://lundr.tech/?view=volunteer-card. Punch 18831635D44F1FC9CC15FEE9. Retrieved 2026-10-13.
What it is.
For nonprofit offices: fills volunteer shifts from a roster and a shift list, fairly and within each person's days, skills and weekly hours, never putting an unscreened person on a role that needs screening; shows every unfilled slot with its reason, writes each volunteer a reminder with only their own shifts, and totals logged hours.
Use when scheduling build days, events or programs. Do not use for paid staff payroll or for running background checks.
It carries a machine that shows its working: schedule — fill shifts and write reminders; hours — total logged hours — 15 checks in its selftest. It will never puts an unscreened person on a screened role; never shares one volunteer's contact with another; never runs a background check.
Eight laws, written into the card.
They are in the card itself, so the AI follows them.
SCREENED ROLES GO ONLY TO PEOPLE MARKED YESScreened roles go only to people marked yes.
FEWEST HOURS SO FAR IS ASKED FIRSTFewest hours so far is asked first.
EVERY GAP CARRIES ITS REASONEvery gap carries its reason.
DONORDonor, volunteer and client records stay on the person's own machine; no file carries one person's contact details into another's.
VERIFY BY EXECUTIONVerify by execution, not by reasoning: run the machine and read what it prints before saying a thing is done.
SAY THE LIMIT OUT LOUD IN THE WORKSay the limit out loud in the work: every result names what it did not check.
NOTHING HIDDENNothing hidden: two readers, the person and the AI, see the same words.
THE PERSON DECIDESThe person decides.
What rides in the card.
In the card’s own voice, with a machine that shows its working.
THE GUIDEreferences/THE-FAIR-FILL.md
THE MACHINEvolunteer.py · two commandsschedule — fill shifts and write reminders; hours — total logged hours. Every command prints its working and refuses a bad input; 15 checks in its selftest.
What it does once your AI has it.
schedule Fill shifts and write reminders
hours Total logged hours
On the record 14 volunteers and a two-day build weekend of 22 slots — fictional records made for the test (every fixture file says FICTIONAL). No one marked 'no' or 'maybe' was placed in the kids' corner; each reminder holds only its own person's shifts. - 21 of 22 slots filled — the most possible, counted by hand. The hours log's 14-hour day and future date were flagged. Live on Claude Sonnet, 2026-10-13: 7 of 7 passed; the card fired on 2 of 3 trigger cases and on none of its hand-off cases.
What it will never do.
It will never puts an unscreened person on a screened role; never shares one volunteer's contact with another; never runs a background check.
It schedules from what the roster says. It cannot know who is reliable, who is injured, or whether a screening is still current. It is an AI reading a text file: it can be wrong, so check what matters against your own records and the source.
What’s in the buy.
CARD.md — the whole card: its boot, laws, loop, when it says no, its seals, ledger, term and score · SKILL.md — the door your AI reads first · START-HERE.md — the first five minutes, for you
THE-FAIR-FILL.md — the guide in references/, in the card's own voice
scripts/volunteer.py — the machine: schedule · hours, standard library only, no network, selftest 15/15
WITNESS.md — the runs on real material and live on Claude, with what was not run · SELFTEST.md — the machine's own test, as run at the cut · MANIFEST.md, every file hashed · CHANGELOG.md
tests/evals.json + EVALS.md — the cases it must take, hand off and refuse
MY-LEDGER.md — the card's memory, on your own machine · TIN.md, the nine lines on the tin · LICENSE-NOTE.md
card.svg + card-machine.svg + card.json · card.html, the card as one offline file · doors/ — the rules files for Cursor, Codex, Gemini, Copilot and Claude Code, the system text for any other AI, a local-model file and an MCP door
PROOF · SELFTEST 15/15 · WITNESSED ON MATERIAL · LIVE ON CLAUDE SONNET 2026-10-13 · 7 OF 7 PASSED · EDITION 1 · PUNCH 18831635D44F1FC9CC15FEE9
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 1205 PROPOSED — 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. 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 WITNESS.MD
volunteer.py, every command showing its working.
A small Python program, standard library only. Your AI runs it; you can too. The blocks below are pasted from the card’s own WITNESS.md, as printed.
schedule
fill shifts and write reminders
hours
total logged hours
selftest
15 checks that prove the machine; it must print 15/15
THE COMMANDS, IN ORDER, ON 14 VOLUNTEERS AND A TWO-DAY BUILD WEEKEND OF 22 SLOTS
VERDICT: GAPS. 1 of 22 slot(s) unfilled. 2 input problem(s) to read.
VERDICT: FAIL. 2 flag(s), 0 row(s) unreadable.
THE RUNS ARE PASTED FROM THE CARD’S OWN WITNESS.MD AS PRINTED. FIXTURES MARKED FICTIONAL ARE THE STUDIO’S OWN EXAMPLES, INVENTED FOR THE RECORD; NO PRIVATE PERSON IS NAMED.
QUESTIONS AT THE TABLE
Asked before the wire.
What does it need from me?
A volunteer roster and a shift list. Take the roster and the shifts, and it goes from 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 self-test (15/15), a run on real or invented material with every command and verdict pasted into WITNESS.md as printed, and live runs on Claude Sonnet: 7 of 7 passed; the card fired on 2 of 3 trigger cases and on none of its hand-off cases.; 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 schedules from what the roster says. It cannot know who is reliable, who is injured, or whether a screening is still current.
What will it never do?
It will never puts an unscreened person on a screened role; never shares one volunteer's contact with another; never runs a background check.
