THE DEAL ROOM · THE ORIGINATION · Nº 1297 · EDITION 1 ·Liquid error (snippets/rm-deal-sourcer-card line 27): comparison of String with 0 failed
LUND CARDS · THE DEAL ROOMNº 1297
THE CARD AS TEXT · FOR EYES AND FOR MACHINES
THE DEAL SOURCER CARD · the screening seat — scores a list of companies against an investment thesis
WAKES WHEN a fund needs to screen many companies against a thesis to find targets · a person asks 'deal sourcing', 'which of these fit our thesis', 'screen this list' · a pipeline of candidates needs ranking by fit
THE LOOP
thesis · the investment criteria as scored filters: size, growth, margin, sector, moat
score · each company against each filter, from its own data
rank · the list by weighted fit, best first
why · each target carries the reason it scored where it did
NEVER
Recommends an investment — it scores fit against a thesis; a person decides what to pursue
Gives investment advice or tells anyone to buy, sell, invest in, or price a deal
Promises, guarantees, or projects a certain return — outputs are assumptions, not outcomes
Presents an invented number as real — unknown inputs are marked [FILL] for the person's own data
IT MAKES run — scores a companies CSV against weighted thesis filters, ranks, explains each score; selftest — 11 checks that prove the machine.
THE LAW A card builds and checks the deal artifact — the model, the memo, the analysis. It never gives investment advice, never promises or projects a guaranteed return, never presents an invented number as real, never drafts a real securities offer, and never replaces the judgment, relationships, and diligence a deal needs. The person and their licensed advisors own every number and every decision.
PROOF SELFTEST 11/11 · 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 · 26A35D252B68DA024CBBFA50
CITE THIS CARDTHE DEAL SOURCER CARD, Edition 1. Lund Studio LLC, Westminster, Colorado. https://lundr.tech/?view=deal-sourcer-card. Punch 26A35D252B68DA024CBBFA50. Retrieved 2026-10-20.
What it is.
Scores a list of companies against an investment thesis. Use when a fund needs to screen many companies against a thesis to find targets. Not for deal advice or promised returns. For diligence on a chosen target → THE COMMERCIAL DILIGENCE CARD.
It carries a machine that shows its working: run — scores a companies CSV against weighted thesis filters, ranks, explains each score; selftest — 11 checks that prove the machine — 11 checks in its selftest, run in the open below. It never recommends an investment — it scores fit against a thesis; a person decides what to pursue; never gives investment advice or tells anyone to buy, sell, invest in, or price a deal; never promises, guarantees, or projects a certain return — outputs are assumptions, not outcomes; never presents an invented number as real — unknown inputs are marked [FILL] for the person's own data.
The house law, written into the card.
It is in the card itself, so the AI follows it.
THE HOUSE LAW · THE DEAL ROOMA card builds and checks the deal artifact — the model, the memo, the analysis. It never gives investment advice, never promises or projects a guaranteed return, never presents an invented number as real, never drafts a real securities offer, and never replaces the judgment, relationships, and diligence a deal needs. The person and their licensed advisors own every number and every decision.
THE LIMIT, ON THE TINIt scores the companies and data you supply against filters you set; it does not find companies or verify their data. Sourcing is only as good as the list and the thesis.
The method.
Thesis. The investment criteria as scored filters: size, growth, margin, sector, moat.
Score. Each company against each filter, from its own data.
Rank. The list by weighted fit, best first.
Why. Each target carries the reason it scored where it did.
What it does once your AI has it.
run Scores a companies CSV against weighted thesis filters, ranks, explains each score
selftest 11 checks on the studio’s own example inputs; it must print selftest 11/11
What it will never do.
It never recommends an investment — it scores fit against a thesis; a person decides what to pursue; never gives investment advice or tells anyone to buy, sell, invest in, or price a deal; never promises, guarantees, or projects a certain return — outputs are assumptions, not outcomes; never presents an invented number as real — unknown inputs are marked [FILL] for the person's own data.
Where it hands off: Diligence on a chosen target → THE COMMERCIAL DILIGENCE CARD. Valuing it → THE VALUATION CARD (THE EXCHANGE).
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/sourcer.py — the machine, Python standard library only, offline; selftest 11/11
RUN.md — the dated run: the selftest as it printed when the card was cut, with the date and the host
references/THE-METHOD.md — the method in plain words, in the card’s own voice
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 11/11 · 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 26A35D252B68DA024CBBFA50
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 1297 —Liquid error (snippets/rm-deal-sourcer-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. Not investment advice, not an appraisal and not an offer to sell securities. 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
sourcer.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.
run
scores a companies CSV against weighted thesis filters, ranks, explains each score · run COMPANIES.csv THESIS.txt
selftest
11 checks that prove the machine; it must print selftest 11/11
selftest · AS PRINTED
$ python3 scripts/sourcer.py selftest
wrote DEAL-SOURCING.md — 3 scored, 1 not scored
REFUSED: no companies — expected company,revenue,growth,margin,sector
REFUSED: need a thesis file (key=value filters and weights)
wrote DEAL-SOURCING.md — 3 scored, 1 not scored
wrote DEAL-SOURCING.md — 3 scored, 1 not scored
selftest 11/11
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: the investment criteria as scored filters: size, growth, margin, sector, moat. 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 (11/11), 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 scores the companies and data you supply against filters you set; it does not find companies or verify their data. Sourcing is only as good as the list and the thesis.
What will it never do?
It never recommends an investment — it scores fit against a thesis; a person decides what to pursue; never gives investment advice or tells anyone to buy, sell, invest in, or price a deal; never promises, guarantees, or projects a certain return — outputs are assumptions, not outcomes; never presents an invented number as real — unknown inputs are marked [FILL] for the person's own data.
