THE IMPACT CARD · Outcome reports where every number traces to its rows, and no family is counted twice.
WAKES WHEN A funder report is due · An annual report needs numbers · Someone asks how many people were really served
THE LOOP
Take the records.
Agree the measures.
Run `report`.
Read the excluded rows together.
Run `check` on the narrative.
NEVER
Invents a number
Counts one family twice
Drops rows without saying
IT MAKES report — compute the measures; check — check every number in a narrative.
THE STANDARD every number traces to its rows; rows and unique people are shown side by side; excluded rows are listed; no figure is rounded up or invented; donor; 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 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 · 52F8719DDF520D0000D14A63
CITE THIS CARDTHE IMPACT CARD, Edition 1. Lund Studio LLC, Westminster, Colorado. https://lundr.tech/?view=impact-card. Punch 52F8719DDF520D0000D14A63. Retrieved 2026-10-13.
What it is.
For nonprofit offices: builds outcome reports from program records where every number traces to the rows it came from, counts are shown as both rows and unique people so no one is counted twice, excluded rows are listed with reasons, and a narrative's figures are checked against the report.
Use for funder reports, annual reports and board updates. Do not use to write the grant proposal itself (THE PROPOSAL CARD) or to invent a figure the records don't hold.
It carries a machine that shows its working: report — compute the measures; check — check every number in a narrative — 15 checks in its selftest. It will never invents a number; never counts one family twice; never drops rows without saying.
Nine laws, written into the card.
They are in the card itself, so the AI follows them.
EVERY NUMBER TRACES TO ITS ROWSEvery number traces to its rows.
ROWS AND UNIQUE PEOPLE ARE SHOWN SIDE BY SIDERows and unique people are shown side by side.
EXCLUDED ROWS ARE LISTEDExcluded rows are listed, never silently dropped.
NO FIGURE IS ROUNDED UP OR INVENTEDNo figure is rounded up or invented.
DONORDonor, volunteer and client records stay on the person's own machine; no file carries one person's contact details into another's.
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-MEASURES.md
THE MACHINEimpact.py · two commandsreport — compute the measures; check — check every number in a narrative. Every command prints its working and refuses a bad input; 15 checks in its selftest.
What it does once your AI has it.
report Compute the measures
check Check every number in a narrative
On the record about 40 program records for a housing nonprofit, with repeat visits and three bad rows — fictional records made for the test (every fixture file says FICTIONAL). Households served 19 from 28 visits (rows and people shown side by side); the three bad rows listed with reasons. - The narrative check matched four numbers to their measures, accepted the one with a [source], and flagged exactly the planted wrong number. 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 number; never counts one family twice; never drops rows without saying.
It counts what the records hold. It cannot tell whether the records are complete or whether a program caused an outcome; the narrative check matches numbers by value, not meaning. 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-MEASURES.md — the guide in references/, in the card's own voice
scripts/impact.py — the machine: report · 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 52F8719DDF520D0000D14A63
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 1206 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
impact.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.
report
compute the measures
check
check every number in a narrative
selftest
15 checks that prove the machine; it must print 15/15
THE COMMANDS, IN ORDER, ON ABOUT 40 PROGRAM RECORDS FOR A HOUSING NONPROFIT, WITH REPEAT VISITS AND THREE BAD ROWS
VERDICT: WARN. 5 measure(s) computed, 0 refused, 3 row(s) left out (see EXCLUDED.md).
VERDICT: FAIL. 1 of 6 number(s) are UNSOURCED.
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?
Program records with an id and a date column, and the measures you report. Take the records, 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 counts what the records hold. It cannot tell whether the records are complete or whether a program caused an outcome; the narrative check matches numbers by value, not meaning.
What will it never do?
It will never invents a number; never counts one family twice; never drops rows without saying.
