THE INSTRUMENTS · THE CRAFT GATES · Nº 1337 · EDITION 1 ·Liquid error (snippets/rm-every-rep-card line 27): comparison of String with 0 failed
LUND CARDS · THE INSTRUMENTSNº 1337
THE CARD AS TEXT · FOR EYES AND FOR MACHINES
THE EVERY REP CARD · the coverage seat — every representative case tried before anything ships
WAKES WHEN a deliverable is about to ship and it must work on every case, not just the one you looked at · a person says 'did you check every slide/width/page', 'test it all', 'try every rep' · a deck, a theme, a document or a dataset needs a coverage gate before hand-off
THE LOOP
plan · list every representative case: every slide, every width, every page, every row, every browser
check · go through them one by one; record pass or fail and the evidence for each
hold · the gate refuses to pass while any rep is unchecked, failing, or has no evidence
ship · only when every rep is checked, passed, and evidenced
NEVER
Passes a deliverable with an unchecked rep — 'I looked at one and it was fine' is not a pass
Counts a check without evidence — a claim with no proof is not a check
Lets a single failing case be waved through because the rest were fine
IT MAKES plan — writes the rep plan, gates the work, refuses to pass until every rep is proven; gate — writes the rep plan, gates the work, refuses to pass until every rep is proven; selftest — 22 checks that prove the machine.
THE LAW Nothing ships until it is proven. A craft gate checks the work against every representative case and every reading rule, records the evidence, and refuses to pass what it has not proven. The maker holds the standard; the gate holds the line.
PROOF SELFTEST 22/22 · witnessed in Claude 2026-10-20 on the studio’s own example inputs · the dated run in the box (RUN.md) · Edition 1.
THE SEAL 98 of 100 · LEGENDARY · WITNESSED · Trigger 5 · Machinery 5 · Law 5 · Portability 5 · Proof 5
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 · 00F8BA792F366AEC6F1357EA
CITE THIS CARDTHE EVERY REP CARD, Edition 1. Lund Studio LLC, Westminster, Colorado. https://lundr.tech/?view=every-rep-card. Punch 00F8BA792F366AEC6F1357EA. Retrieved 2026-10-20.
What it is.
Every representative case tried before anything ships. Use when a deliverable is about to ship and it must work on every case, not just the one you looked at. Not for making or fixing the work itself. Pairs with THE OPTIMAL READING CARD.
It carries a machine that shows its working: plan — writes the rep plan, gates the work, refuses to pass until every rep is proven; gate — writes the rep plan, gates the work, refuses to pass until every rep is proven; selftest — 22 checks that prove the machine — 22 checks in its selftest, run in the open below. It never passes a deliverable with an unchecked rep — 'I looked at one and it was fine' is not a pass; never counts a check without evidence — a claim with no proof is not a check; never lets a single failing case be waved through because the rest were fine.
The law, written into the card.
It is in the card itself, so the AI follows it.
THE HOUSE LAW · THE CRAFT GATESNothing ships until it is proven. A craft gate checks the work against every representative case and every reading rule, records the evidence, and refuses to pass what it has not proven. The maker holds the standard; the gate holds the line.
THE LIMIT, ON THE TINIt enforces that every rep was checked and evidenced; it does not do the checking for you — you (or a render tool) produce the evidence, and the gate holds the line.
The method.
Plan. List every representative case: every slide, every width, every page, every row, every browser.
Check. Go through them one by one; record pass or fail and the evidence for each.
Hold. The gate refuses to pass while any rep is unchecked, failing, or has no evidence.
Ship. Only when every rep is checked, passed, and evidenced.
What it does once your AI has it.
plan Writes the rep plan, gates the work, refuses to pass until every rep is proven
gate Writes the rep plan, gates the work, refuses to pass until every rep is proven
selftest 22 checks on the studio’s own example inputs; it must print selftest 22/22
What it will never do.
It never passes a deliverable with an unchecked rep — 'I looked at one and it was fine' is not a pass; never counts a check without evidence — a claim with no proof is not a check; never lets a single failing case be waved through because the rest were fine.
Where it hands off: Whether each surface reads well → THE OPTIMAL READING CARD. Re-measuring each claim before it is called done → THE DOUBLE CHECK CARD. A security sweep → THE WATCH.
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. Names of other companies and standards are used only to say what the card works with.
What’s in the buy.
SKILL.md — the door your AI reads first: when it wakes, when it does not, the loop, the never-lines, the house law
CARD.md — the whole card in ten sections, §0 to §9 · TIN.md — what is on the tin, in nine lines
scripts/everyrep.py — the machine, Python standard library only, offline; selftest 22/22
RUN.md — the dated run: the selftest as it printed when the card was cut, with the date and the host
references/THE-ARMADA.md — the default width armada and why coverage beats spot-checking
references/THE-METHOD.md — the method in plain words, in the card’s own voice
references/THE-REP-SETS.md — the standard rep sets (slides, widths, pages, rows, browsers, states)
START-HERE.md and system/short-prompt.md — the doors, for any AI with or without skills
MY-LEDGER.md — the card’s memory, on your own machine · LICENSE-NOTE.md — the licence
PROOF · SELFTEST 22/22 · AUDIT 12/12 · WITNESSED IN CLAUDE 2026-10-20 ON THE STUDIO’S OWN EXAMPLE INPUTS · THE TEST PROMPTS IN FRESH CHATS OWED · EDITION 1 · PUNCH 00F8BA792F366AEC6F1357EA
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 1337 —Liquid error (snippets/rm-every-rep-card line 116): comparison of String with 0 failed
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.
AFTER YOU PAY · SIGN IN WITH THE EMAIL YOU PAID WITH · THE CARD OPENS ON MY CARDS → · CHECKED AGAINST ITS FINGERPRINT · NOTHING TO WAIT FOR
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 STUDIO’S RUN OF 2026-10-20
everyrep.py, showing its working.
A small Python program, standard library only. Your AI runs it; you can too. The block below is the machine’s selftest as it printed when the studio ran it from inside the packet, in Claude, on 2026-10-20.
plan
writes the rep plan, gates the work, refuses to pass until every rep is proven · plan KIND [reps...]
gate
writes the rep plan, gates the work, refuses to pass until every rep is proven · gate REP-PLAN.csv
selftest
22 checks that prove the machine; it must print selftest 22/22
selftest · AS PRINTED
$ python3 scripts/everyrep.py selftest
wrote REP-PLAN.csv — 12 reps of kind 'slides', all unchecked
wrote REP-GATE.md — HOLD (12 unchecked, 0 failed, 0 without evidence)
wrote REP-GATE.md — HOLD (0 unchecked, 1 failed, 0 without evidence)
wrote REP-GATE.md — HOLD (0 unchecked, 0 failed, 1 without evidence)
wrote REP-GATE.md — PASS (0 unchecked, 0 failed, 0 without evidence)
wrote REP-PLAN.csv — 7 reps of kind 'widths', all unchecked
REFUSED: unknown rep kind 'toaster' — known: slides, widths, pages, rows, browsers, states, devices
REFUSED: the rep plan is empty — there is nothing proven, so nothing passes
selftest 22/22
THE SELFTEST RUNS ON THE STUDIO’S OWN EXAMPLE INPUTS, INVENTED FOR THE TEST; NO REAL COMPANY, PERSON OR ACCOUNT IS NAMED.
QUESTIONS AT THE TABLE
Asked before the wire.
What does it need from me?
Your own files and figures, on your own disk. It starts by asking for them: list every representative case: every slide, every width, every page, every row, every browser. If something it needs is missing, it marks it and says so — it never fills a gap with a guess.
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 (22/22), run from inside the packet in Claude on 2026-10-20 on the studio's own example inputs and printed below as it ran; the twelve-check audit (AUDIT.md, 12/12); MANIFEST.md with every file hashed. RUN.md in the box is that run, dated. Still to come, as the next receipt: the card's test prompts asked in fresh chats with the card installed. 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. It enforces that every rep was checked and evidenced; it does not do the checking for you — you (or a render tool) produce the evidence, and the gate holds the line.
What will it never do?
It never passes a deliverable with an unchecked rep — 'I looked at one and it was fine' is not a pass; never counts a check without evidence — a claim with no proof is not a check; never lets a single failing case be waved through because the rest were fine.
