THE PLAIN WORDS CARD · Finds what makes a document hard to read and suggests plainer words, without rewriting it.
WAKES WHEN A policy, letter or help page is hard to read · Someone asks for plainer words · A public document needs a reading grade
THE LOOP
Take the files and the target.
Run `check`.
Run `suggest`.
Agree which sentences to change.
Show each change.
NEVER
Rewrites the whole file unasked
Calls an estimate exact
Drops a term the reader needs
IT MAKES check — measure files and write PLAIN.md and plain.json; suggest — print simpler words to swap in.
THE STANDARD it suggests; grades are estimates and said to be; needed terms stay and get explained; every finding has its line; 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 96 of 100 · LEGENDARY · WITNESSED · Trigger 4 · 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 · 734E1A7F43AAE19A4A521957
CITE THIS CARDTHE PLAIN WORDS CARD, Edition 1. Lund Studio LLC, Westminster, Colorado. https://lundr.tech/?view=plain-words-card. Punch 734E1A7F43AAE19A4A521957. Retrieved 2026-10-13.
What it is.
Finds what makes a document hard to read and suggests plainer words: reading grade, long sentences, passive voice, acronyms used before they are explained, jargon, and the longest words, each with its line, plus a list of swaps (utilize to use, in order to to, prior to to before). It never rewrites the file.
Use on policies, letters, reports, help pages and announcements. Do not use for colour contrast or screen-reader checks (THE ACCESSIBILITY CARD) or for spelling and grammar.
It carries a machine that shows its working: check — measure files and write PLAIN.md and plain.json; suggest — print simpler words to swap in — 15 checks in its selftest. It will never rewrites the whole file unasked; never calls an estimate exact; never drops a term the reader needs.
Eight laws, written into the card.
They are in the card itself, so the AI follows them.
IT SUGGESTSIt suggests; the writer decides.
GRADES ARE ESTIMATES AND SAID TO BEGrades are estimates and said to be.
NEEDED TERMS STAY AND GET EXPLAINEDNeeded terms stay and get explained.
EVERY FINDING HAS ITS LINEEvery finding has its line.
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-SWAPS.md
THE MACHINEplainwords.py · two commandscheck — measure files and write PLAIN.md and plain.json; suggest — print simpler words to swap in. Every command prints its working and refuses a bad input; 15 checks in its selftest.
What it does once your AI has it.
check Measure files and write PLAIN.md and plain.json
suggest Print simpler words to swap in
On the record this cut's own 18 SKILL.md files — real material (not made up for the test). 5 of 18 read at grade 8 or under; the other 13 are written for a model, not the public, and the report shows where each runs long. It suggested and changed nothing (file hashes unchanged). 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 rewrites the whole file unasked; never calls an estimate exact; never drops a term the reader needs.
Formulas and word lists, in English. It cannot tell whether a sentence is true or kind, and a low grade does not make a document clear on its own. 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-SWAPS.md — the guide in references/, in the card's own voice
scripts/plainwords.py — the machine: check · suggest, 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 734E1A7F43AAE19A4A521957
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 1209 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
plainwords.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.
check
measure files and write PLAIN.md and plain.json
suggest
print simpler words to swap in
selftest
15 checks that prove the machine; it must print 15/15
THE COMMANDS, IN ORDER, ON THIS CUT'S OWN 18 SKILL.MD FILES
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 documents (.md, .txt or .html) and a target grade. Take the files and the target, 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. Formulas and word lists, in English. It cannot tell whether a sentence is true or kind, and a low grade does not make a document clear on its own.
What will it never do?
It will never rewrites the whole file unasked; never calls an estimate exact; never drops a term the reader needs.
