THE PIPELINE CARD · a pipeline the forecast can stand on
WAKES WHEN someone runs a pipeline review or a forecast, or asks what will close and what is stuck
THE LOOP
pipeline.py hygiene · stale, past due
fix the record or close the deal lost
stage odds from closed deals, each quarter
forecast · weighted, by stage, by owner
aging · the deals stuck past their stage
NEVER
Borrow another company's stage odds
Let a rep set the odds on their own deals
Forecast a deal with no amount or no next step
IT MAKES new — the sheet (example rows) and stages.json beside it; hygiene — stale, past due, no next step, no amount; forecast — weighted forecast and coverage, by stage and owner; aging — days in stage against the median; outliers named.
THE STANDARD a pipeline is a record of promises; hygiene is whether it is true; the odds are yours; the forecast is arithmetic, and said so; a deal twice as long in a stage as the median is not in that stage; coverage is a rule of thumb; one currency at a time.
PROOF SELFTEST 13/13 · witnessed in Claude 2026-10-09 · 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. THE-CLAUSES.md rides in the packet and is part of the licence.
THE PUNCH · SHA-256 OF SKILL.MD · 2FE56EB3154FCDE2F0AFA93B
CITE THIS CARDTHE PIPELINE CARD, Edition 1. Lund Studio LLC, Westminster, Colorado. https://lundr.tech/?view=pipeline-card. Punch 2FE56EB3154FCDE2F0AFA93B. Retrieved 2026-10-10.
What it is.
Keeps a sales pipeline honest and turns it into a forecast the team can stand on: names every stale deal, past-due close date, missing next step and missing amount; weights the open pipeline by the team's own stage odds from its closed deals, by stage and by owner; shows coverage against the quota; and finds deals that have sat in a stage far longer than the rest.
It carries a machine that shows its working: new — the sheet (example rows) and stages.json beside it; hygiene — stale, past due, no next step, no amount; forecast — weighted forecast and coverage, by stage and owner; aging — days in stage against the median; outliers named — 13 checks in its selftest, every command on the record. It will never borrow another company's stage odds; never let a rep set the odds on their own deals; never forecast a deal with no amount or no next step.
Six laws, written into the card.
They are in the card itself, so the AI follows them.
A PIPELINE IS A RECORD OF PROMISES; HYGIENE IS WHETHER IT IS TRUEStale, past due, no next step, no amount — fixed or closed, never forecast.
THE ODDS ARE YOURSWon divided by all that reached the stage, from your closed deals, recomputed each quarter; never borrowed, never set by the rep.
THE FORECAST IS ARITHMETIC, AND SAID SOAmount times odds is a weighted sum, not a prediction.
A DEAL TWICE AS LONG IN A STAGE AS THE MEDIAN IS NOT IN THAT STAGEAging names it; the review decides.
COVERAGE IS A RULE OF THUMBThree times the number is a convention; a team's win rate sets its own.
ONE CURRENCY AT A TIMEThe machine refuses to add two currencies into one figure.
What rides in the card.
In the card’s own voice, with a machine that shows its working.
THE GUIDEreferences/PIPELINE-HYGIENE.md
THE MACHINEpipeline.py · four commandsnew — the sheet (example rows) and stages.json beside it; hygiene — stale, past due, no next step, no amount; forecast — weighted forecast and coverage, by stage and owner; aging — days in stage against the median; outliers named. Every command prints its working and refuses a bad input; 13 checks in its selftest, every command on the record.
What it does once your AI has it.
new The sheet (example rows) and stages.json beside it
hygiene Stale, past due, no next step, no amount
forecast Weighted forecast and coverage, by stage and owner
aging Days in stage against the median; outliers named
On the record Five example deals: a dead one named three ways (stale, past due, no next step) and one with no amount; the forecast weighted by the example stage odds with coverage against the number; and the deal that has sat in its stage far longer than the rest.
What it will never do.
It will never borrow another company's stage odds; never let a rep set the odds on their own deals; never forecast a deal with no amount or no next step.
The forecast is a weighted sum on the sheet, not a prediction. Hygiene is about the record, not the deal. The odds are only as good as the closed-deal history they came from; a young team has rough odds and should say so. 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: who it is, its laws, when it says no, what it carries · SKILL.md — the door your AI reads first · START-HERE.md — the first five minutes, for you
PIPELINE-HYGIENE.md — the guide in references/, in the card's own voice
scripts/pipeline.py — the machine: new · hygiene · forecast · aging, standard library only, selftest 13/13
WITNESS.md + SELFTEST.md — every command on the record, as it printed · MANIFEST.md, every file hashed · AUDIT.md, the twelve checks
MY-LEDGER.md — the card's memory, on your own machine · TIN.md · LICENSE-NOTE.md · THE-CLAUSES.md · HOSTS.md
card.svg + card-machine.svg + card.json · card.html, the card as one offline file · the doors for ChatGPT, Gemini, Cursor, Claude Code and MCP hosts (rules/, system/, mcp/)
PROOF · SELFTEST 13/13 · 4 COMMANDS ON THE RECORD · WITNESSED IN CLAUDE 2026-10-09 · EDITION 1 · PUNCH 2FE56EB3154FCDE2F0AFA93B
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 843 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 WITNESSED RUN OF 2026-10-09
pipeline.py, every command showing its working.
A small Python program, standard library only. Your AI runs it; you can too. Every block below is pasted from the card’s own WITNESS.md, as printed.
new
the sheet (example rows) and stages.json beside it
hygiene
stale, past due, no next step, no amount
forecast
weighted forecast and coverage, by stage and owner
aging
days in stage against the median; outliers named
selftest
13 checks that prove the machine; it must print 13/13
new · THE SHEET (EXAMPLE ROWS) AND STAGES.JSON BESIDE IT
$ python3 scripts/pipeline.py new pipeline.csv
sheet written · pipeline.csv · 5 example deals (invented) · stages.json written beside it with EXAMPLE odds to replace with your own
hygiene · STALE, PAST DUE, NO NEXT STEP, NO AMOUNT
$ python3 scripts/pipeline.py hygiene pipeline.csv --today 2026-10-09
HYGIENE · pipeline.csv · 5 deals · 4 finding(s) · as of 2026-10-09 · stale after 14 days
STALE Harbor onboarding · no activity for 41 days
PAST DUE Harbor onboarding · close date 2026-09-30 is 9 days ago
NO NEXT STEP Harbor onboarding · nothing scheduled
NO AMOUNT Pioneer pilot · the forecast cannot count it
forecast · WEIGHTED FORECAST AND COVERAGE, BY STAGE AND OWNER
$ python3 scripts/pipeline.py forecast pipeline.csv --stages stages.json --quota 250000
FORECAST · open pipeline USD 300,000 · weighted USD 177,600
negotiation 1 deals · USD 90,000 · odds 80% · weighted USD 72,000
proposal 1 deals · USD 150,000 · odds 60% · weighted USD 90,000
evaluation 1 deals · USD 48,000 · odds 30% · weighted USD 14,400
discovery 1 deals · USD 12,000 · odds 10% · weighted USD 1,200
owner Rep A 2 deals · USD 60,000 · weighted USD 15,600
owner Rep B 1 deals · USD 90,000 · weighted USD 72,000
owner Rep C 1 deals · USD 150,000 · weighted USD 90,000
COVERAGE · 1.2x of USD 250,000 on the whole pipeline · 0.71x weighted · under 3x is thin by most teams' rule of thumb
NOTE · arithmetic on the sheet with the team's own odds, not a prediction; the odds come from closed deals, never from hope
aging · DAYS IN STAGE AGAINST THE MEDIAN; OUTLIERS NAMED
$ python3 scripts/pipeline.py aging pipeline.csv --today 2026-10-09
AGING · pipeline.csv · days in stage as of 2026-10-09
discovery 100 days · Harbor onboarding
discovery 8 days · Pioneer pilot
evaluation 14 days · Northwind support automation
negotiation 8 days · Summit renewal upsell
proposal 81 days · Atlas platform
THE NUMBERS, NAMES AND DATES IN THESE RUNS ARE THE STUDIO’S OWN EXAMPLES, INVENTED FOR THE RECORD; NO REAL COMPANY, PERSON OR PROPERTY IS NAMED.
QUESTIONS AT THE TABLE
Asked before the wire.
What does it need from me?
Pipeline.py hygiene · stale, past due. It asks first for the pipeline export with stage, amount, dates and next step, the team's stage odds from its closed deals, and the number to cover.
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 (13/13) and every command run on real example inputs, pasted into WITNESS.md as they printed; 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. The forecast is a weighted sum on the sheet, not a prediction. Hygiene is about the record, not the deal. The odds are only as good as the closed-deal history they came from; a young team has rough odds and should say so.
What will it never do?
It will never borrow another company's stage odds; never let a rep set the odds on their own deals; never forecast a deal with no amount or no next step.
