THE VENDOR REVIEW CARD · The security answer sheet a buyer's procurement team asks a skill maker for, written from the files.
WAKES WHEN A company asks a skill maker for a security questionnaire · A team reviews skills before rolling them out · Someone asks what a skill sends out, changes or depends on
THE LOOP
Take the skill, zip or library, and any THE PACKET SCAN CARD report.
Run `review` and read the verdict line first.
Answer the buyer's questions in their words: data out, files changed, code run, dependencies, maintainer, licence, version, integrity.
List each gap and what fills it.
Hand the sheet over with the punch so the buyer can check it later.
NEVER
Calls a skill safe or certified
Fills an answer the files don't support
Skips the scan line when no scan was run
IT MAKES review — read skills and write the answer sheets.
THE STANDARD every answer comes from the files; nothing is certified; a missing scan is printed as NOT RUN; every file is hashed; verify by execution; say the limit out loud in the work; nothing hidden; the person decides.
PROOF SELFTEST 16/16 · 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 · 31EA1E7F32E7C838BC067FC8
CITE THIS CARDTHE VENDOR REVIEW CARD, Edition 1. Lund Studio LLC, Westminster, Colorado. https://lundr.tech/?view=vendor-review-card. Punch 31EA1E7F32E7C838BC067FC8. Retrieved 2026-10-13.
What it is.
Writes the security-review answer sheet an enterprise buyer asks for before installing a skill: what it runs, whether it sends data out, writes files, reads credentials or touches personal data, its licence, version, maintainer and integrity punch, all read from the files.
Use when someone is selling skills to a company, answering a vendor security questionnaire, or reviewing a skill before rollout. Do not use to hunt hidden instructions or secrets inside a packet (THE PACKET SCAN CARD does that) or to certify anything as safe.
It carries a machine that shows its working: review — read skills and write the answer sheets — 16 checks in its selftest. It will never calls a skill safe or certified; never fills an answer the files don't support; never skips the scan line when no scan was run.
Eight laws, written into the card.
They are in the card itself, so the AI follows them.
EVERY ANSWER COMES FROM THE FILESEvery answer comes from the files, never from the maker's claims.
NOTHING IS CERTIFIEDNothing is certified. The sheet says what was found and what was not checked.
A MISSING SCAN IS PRINTED AS NOT RUNA missing scan is printed as NOT RUN, never assumed clean.
EVERY FILE IS HASHEDEvery file is hashed; the punch ties the sheet to the exact SKILL.md reviewed.
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-QUESTIONS.md
THE MACHINEvendorreview.py · one commandreview — read skills and write the answer sheets. Every command prints its working and refuses a bad input; 16 checks in its selftest.
What it does once your AI has it.
review Read skills and write the answer sheets
On the record this cut's own 18 `.skill.zip` files — real material (not made up for the test). Every card read: network NO, other programs NO, third-party packages none, writes files YES (each machine writes its report into the folder the person names). Checked by hand against the scripts. - The one gap left on every sheet is the scan: THE PACKET SCAN CARD was not in this workspace, so the sheet says NOT RUN rather than filling it in. The changelog gap the first run found was closed by adding CHANGELOG.md to every packet. 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 calls a skill safe or certified; never fills an answer the files don't support; never skips the scan line when no scan was run.
A static read. It does not run the skill, watch a model use it, test a live service, or replace the buyer's own security review. 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-QUESTIONS.md — the guide in references/, in the card's own voice
scripts/vendorreview.py — the machine: review, standard library only, no network, selftest 16/16
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 16/16 · WITNESSED ON MATERIAL · LIVE ON CLAUDE SONNET 2026-10-13 · 7 OF 7 PASSED · EDITION 1 · PUNCH 31EA1E7F32E7C838BC067FC8
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 1192 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
vendorreview.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.
review
read skills and write the answer sheets
selftest
16 checks that prove the machine; it must print 16/16
THE COMMANDS, IN ORDER, ON THIS CUT'S OWN 18 `.SKILL.ZIP` FILES
$ python3 scripts/vendorreview.py review ZIPS --out out
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 skill folders or zips; optionally THE PACKET SCAN CARD's report. Take the skill, zip or library, and any THE PACKET SCAN CARD report, 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 (16/16), 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. A static read. It does not run the skill, watch a model use it, test a live service, or replace the buyer's own security review.
What will it never do?
It will never calls a skill safe or certified; never fills an answer the files don't support; never skips the scan line when no scan was run.
