THE INTRO CARD is free — what an AI skill card is and how to use one Download →Lost Lauren, contact us

THE INSTRUMENTS · Nº 1199 · EDITION 1 · LAUNCHING SOON

LUND CARDS · THE INSTRUMENTSNº 1199 PROPOSED
THE ANNOUNCEMENT CARD — the LSC-1 face
THE CARD AS TEXT · FOR EYES AND FOR MACHINES

THE ANNOUNCEMENT CARD · Writes and checks the messages staff and managers get when an AI assistant arrives.

WAKES WHEN Staff are being told about an AI assistant · A new skill is going out to a team · A manager needs talking points

THE LOOP

  1. Build plan.json.
  2. Run `write`.
  3. Fill every marker with the person.
  4. Run `check`.
  5. Fix FAILs; read WARNs aloud.

NEVER

  • Invents a date, owner or rule
  • Promises the tool is never wrong
  • Leaves out the data rules

IT MAKES write — draft the messages from PLAN.json; check — check finished messages.

THE STANDARD blanks are marked; every message says what; no absolute claims about the tool; every figure has a source or comes out; verify by execution; say the limit out loud in the work; nothing hidden; the person decides.

IN THE BOX CARD.md · CHANGELOG.md · LICENSE-NOTE.md · MANIFEST.md · MY-LEDGER.md · SELFTEST.md · SKILL.md · START-HERE.md · TIN.md · WITNESS.md · card-machine.svg · card.html · card.json · card.svg · doors/HOSTS.md · doors/local/Modelfile · doors/mcp/mcp_card.py · doors/rules/.cursorrules · doors/rules/AGENTS.md · doors/rules/CLAUDE.md · doors/rules/GEMINI.md · doors/rules/copilot-instructions.md · doors/system/CARD.system-8k.txt · doors/system/CARD.system.txt · references/THE-SIX.md · scripts/announce.py · tests/EVALS.md · tests/evals.json.

PROOF SELFTEST 15/15 · witnessed 2026-10-13 on material and live on Claude · 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 · 7085BC2F802FEBD849951359

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

THE ANNOUNCEMENT CARD

Writes and checks the messages staff and managers get when an AI assistant arrives.

WRITE · CHECK

96LEGENDARYWITNESSEDIN CLAUDEIN LUNDRIN 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/announce.py · 2 commands · selftest 15/15
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 (HOSTS.md names each door)
LICENCE
One person, any number of their own AIs and computers · editions replace files · nothing renews · freeze, not loss
PUNCH
7085BC2F802FEBD849951359 · sha-256 of SKILL.md · check any file against it →

CITE THIS CARDTHE ANNOUNCEMENT CARD, Edition 1. Lund Studio LLC, Westminster, Colorado. https://lundr.tech/?view=announcement-card. Punch 7085BC2F802FEBD849951359. Retrieved 2026-10-13.

What it is.

Writes and checks the internal messages for an AI assistant rollout: the launch note, an FAQ, manager talking points and a change notice for each new skill, drafted from the rollout plan with blanks marked rather than invented, then checked for missing who/what/when/help/data rules, long sentences, absolute claims and unsourced figures.

Use when staff are being told about an AI assistant or a new skill. Do not use for outside marketing or press launches, or to plan the rollout itself (THE ROLLOUT CARD).

It carries a machine that shows its working: write — draft the messages from PLAN.json; check — check finished messages — 15 checks in its selftest. It will never invents a date, owner or rule; never promises the tool is never wrong; never leaves out the data rules.

Eight laws, written into the card.

They are in the card itself, so the AI follows them.

BLANKS ARE MARKEDBlanks are marked, never invented.
EVERY MESSAGE SAYS WHATEvery message says what, who, when, help and data rules.
NO ABSOLUTE CLAIMS ABOUT THE TOOLNo absolute claims about the tool.
EVERY FIGURE HAS A SOURCE OR COMES OUTEvery figure has a source or comes out.
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-SIX.md
THE MACHINEannounce.py · two commandswrite — draft the messages from PLAN.json; check — check finished messages. Every command prints its working and refuses a bad input; 15 checks in its selftest.

What it does once your AI has it.

  • write Draft the messages from PLAN.json
  • check Check finished messages
  • On the record a company's launch plan with one skill date missing — fictional records made for the test (every fixture file says FICTIONAL). Drafts left a [FILL] marker for the missing date rather than inventing one; check blocked them (4 FAIL). - On the hand-edited launch note it caught exactly the three planted problems: an absolute claim, a 35-word sentence and an unsourced 40% — each at its line, no false alarms. Live on Claude Sonnet, 2026-10-13: 7 of 7 passed; the card fired on 3 of 3 trigger cases and on none of its hand-off cases.

What it will never do.

It will never invents a date, owner or rule; never promises the tool is never wrong; never leaves out the data rules.

It drafts from the plan and checks for what is missing or risky. It cannot know a company's culture, and the person signs every message. 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-SIX.md — the guide in references/, in the card's own voice
  • scripts/announce.py — the machine: write · check, 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 7085BC2F802FEBD849951359

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 1199 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 · 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.

One email when it is on sale, from the studio; nothing else, ever.

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

announce.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.

writedraft the messages from PLAN.json
checkcheck finished messages
selftest15 checks that prove the machine; it must print 15/15
THE COMMANDS, IN ORDER, ON A COMPANY'S LAUNCH PLAN WITH ONE SKILL DATE MISSING
$ python3 scripts/announce.py write fixture/PLAN.json --out comms
$ python3 scripts/announce.py check comms/CHANGE-NOTICE-order-status-replies.md comms/CHANGE-NOTICE-supplier-contract-summary.md comms/FAQ.md comms/LAUNCH-NOTE.md comms/MANAGER-POINTS.md fixture/edited-LAUNCH-NOTE.md --out check
THE VERDICTS, AS PRINTED
VERDICT: NEEDS FILLING · 5 files · 4 [FILL] marker(s). Add the missing fields to PLAN.json and write again, or fill them by hand. Then run check.
VERDICT: BLOCKED · 4 FAIL, 3 WARN across 6 file(s). Do not send yet.

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?

The rollout plan: dates, owner, help channel, teams, data rules, skills. Build plan.json, 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 3 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 drafts from the plan and checks for what is missing or risky. It cannot know a company's culture, and the person signs every message.

What will it never do?

It will never invents a date, owner or rule; never promises the tool is never wrong; never leaves out the data rules.

← THE INSTRUMENTS · THE FLOOR →

AT YOUR ELBOW, NEVER THE BOSS · NOT LEGAL, MEDICAL, TAX OR FINANCIAL ADVICE · NOT A PAYMENT CARD · © 2026 LUND STUDIO LLC

PAY BYAmerican Express Apple Pay Diners ClubDiscoverGoogle Pay Mastercard PayPalShop Pay Visa
CART · 0