Startup Credits Sweep: an eligibility matrix, honest applications and an expiry ledger
by PaperChaseWebb
Sweep startup programs for cloud, AI API and SaaS credits from your own facts. Each fact names its record; each program is read on its own page with the date; each requirement is marked meets, fails or unknown against one fact, and the matrix sets the verdict. Application drafts cite every fact and say it word for word, so nothing is stretched or invented to fit a form. A ledger counts credits only after the approval notice and reminds you before each grant expires. Every application waits for the owner's yes, and the owner submits it by hand. Fifteen read-only checks run on the folder.
- Price
- $19
- Difficulty
- Intermediate
- Setup
- 1 hr
- Format
- .md file
startup-credits-sweep-eligibility-matrix-and-expiry-ledger.md · 128 KB · instant download after checkout
Want this built for you instead? We can build it for you.
What you end up with
You know which programs you actually qualify for and why, every answer you send matches a record, and no credit runs out unnoticed with a card on file.
What you get
- 21 sections in one .md file, with a one-line unpack
- Five rules: facts before programs, every benefit dated from the program's own page, the verdict follows the matrix, answers say facts word for word, nothing counts until the approval notice
- The sweep folder: sweep.json, facts, programs, criteria, applications, ledger, approvals and done, with blank templates and a one-page worksheet
- credits.py: gate (exit 0, 11, 12), a one-page sweep.md, a due list for expiring grants, owner approval tied to a sha256, verify and one submission per yes
- credits_check.py: fifteen read-only checks, with a seeded test sweep (15 findings, then 0) and the unit tests
- Starter rows for seven real programs read on 2026-10-29, each marked check-first or unknown and verify on the program page
- A skill file for Claude Code, Codex and Hermes, an AGENTS.md snippet and a Grok Bot rules block
- Ten prompts, a failure table, a worked example on a made-up company, and a look at credit directories and perk clubs with sources
Who it is for
Founders and small teams who want the credits they qualify for, without guessing from directory headlines or rounding up a fact to fit a form.
Works with
Solid chips: the agent is named in this listing's own tools list. Dashed chip: A skill file for Claude Code, Codex and Hermes, an AGENTS.md snippet and a Grok Bot rules block; the scripts were tested on Linux with Python 3.13, the agent files were not loaded inside each harness and no real application was prepared or sent.
Tools needed
Cost to run: The pack is the only purchase. The scripts use no model tokens; reading pages and drafting with an agent uses its usual tokens. Program amounts and terms change; verify on each program's page.
Time to result: A first sweep of the programs you care about in an afternoon, with your company records open
How it works
Run the tests
Unpack the pack with the one-line command in section 8 and run sh test_all.sh.
Expected: 15 findings on the seeded sweep and 0 on the fixed one, 15 of 15 single faults caught alone, checker tests 62 passed, credits.py tests 46 passed, exit 2 on a missing folder.
Write the facts
Run credits.py init and fill facts.csv from your records before you read any program. Anything you only know from memory is unsettled.
Expected: One row per fact, each naming its record.
Read and match
Use prompts 2 and 3 to add each program from its own page with today's date, one criteria row per requirement, and the verdict from the matrix. Draft applications with prompt 5.
Expected: The checker shows 0 findings apart from C15 before ratification.
Get the yes
The owner ratifies the rules and approves each ready draft at their own terminal, submits it on the program's page by hand, then runs credits.py submitted. Run credits.py due each week.
Expected: Every submitted application tied to the owner's yes, and every approved grant with an expiry and a reminder.
Sample prompts, free to use
Fill facts.csv from the records I point you to: the incorporation certificate, last month's payroll report, the cap table, the live site and the billing pages. One fact per row with the record named. Anything I tell you from memory is unsettled. Do not look at any program yet.
Prompt 1 of 10.
For every criteria row, set meets, fails or unknown against one settled fact, and set each program's verdict from the matrix. Explain every unknown in one line: what the page does not say, or what fact we do not have.
Prompt 3 of 10.
Read draft a1 as a skeptical program reviewer. Mark any sentence that says more than its cited fact: a bigger number, a later stage, a plan stated as done. Propose the plain version.
Prompt 6 of 10.
Free preview of the file
# Startup Credits Sweep: an eligibility matrix, honest applications and an expiry ledger for startup credits Version 1.0, 2026-10-29. By PaperChaseWebb. A way to go after startup program credits (cloud, AI API, SaaS and GPU programs) without guessing who qualifies, without stretching a single fact on an application, and without losing credits to an expiry date nobody wrote down. You list your company's facts once, each with the record it came from. Each program's requirements are matched against those facts as meets, fails or unknown, and the verdict follows the matrix. Application drafts say your facts word for word and cite them. A ledger counts credits only after the approval notice arrives, as avoided cost, with a reminder set before every expiry. Plain files, a script that gates what an agent may do and writes a one-page sweep report, a read-only checker with fifteen checks, a worksheet, templates, starter rows for seven real programs read on 2026-10-29, a seeded test set, ten prompts and the tests, all Python 3 standard library. Works with Claude Code, Codex and Hermes through a skill file and an AGENTS.md snippet, and with Grok Bot through a rules block. Tested as described in section 13: everything ran on Linux with Python 3.13, including owner approvals typed at a pseudo-terminal. The skill file, snippet and rules block were not loaded inside the harnesses for this release, and no real application was drafted or submitted with it. Each is marked where it matters. S
Test record
- Date
- Oct 29, 2026
- What was run
- credits_check.py on a seeded sweep and a fixed copy, each planted fault alone, a missing input, and the unit tests. Linux, Python 3.13.
- Result
- 15 findings on the seeded sweep, 0 on the fixed one; 15 of 15 planted faults caught alone; exit 2 on missing input; nothing written. 62 checker and 46 credits.py tests passed, 0 failed.
- Not run
- A real company or a real application. The agent files inside Claude Code, Codex, Hermes or Grok Bot. Windows and macOS.
Copied from this item's dated test notes. What was not run stays in.
Worth knowing
- The sweep has not been run on a real company and no real application was prepared or sent; Tidewell Labs, Larkspur Forms, their people, the fixture programs and every fact about them are made up.
- Program amounts, tiers and requirements in the starter rows were read on 2026-10-29 and change without notice. Verify on the program page before you rely on any of them. The pack makes no claim about what any company will be granted, and credits are avoided cost, not revenue.
- The skill file, AGENTS.md snippet and Grok Bot rules block were not loaded inside Claude Code, Codex, Hermes or Grok Bot. Linux only; Windows and macOS were not tested. The scripts open no network connection and never submit anything.
- The approval step refuses piped input and the environment variables Claude Code, Codex, Hermes and Grok Bot set. That stops an agent approving its own application; it is not a lock against someone with the same account.
- On 2026-10-29, on Linux with Python 3.13: credits_check.py gave 15 findings on the seeded sweep (each check once) and 0 on the fixed one, caught 15 of 15 single faults with only its own check, wrote nothing, and exited 2 on a missing folder; checker tests 62 passed, 0 failed; credits.py tests at a pseudo-terminal 46 passed, 0 failed.
Questions
Does this tell me how much I will get?
No. It records each benefit as the program's page states it, with any ceiling kept, and the date you read it. The amount only enters the ledger from the approval notice.
What if I almost meet a requirement?
Then the verdict is not-eligible or check-first, and the pack tells you to leave it there. It never looks for wording that gets around a requirement, and every answer must contain its cited fact word for word.
How is this different from a credits directory or a perk club?
Directories list headline amounts, often copied and months old, and perk clubs charge a yearly fee to unlock deals. This pack sells no deals: it matches your own facts to each program's own dated page and keeps the grants from expiring unnoticed.
Will an agent submit applications or create accounts?
No. Submitting, accepting terms, creating accounts, adding a payment method, spending, contacting programs and signing are gated never. The agent drafts; the owner submits by hand.
Details
Version 1.0 · Updated Oct 29, 2026 · Markdown version of this page
License: Use for your own company and for sweeps you run for clients. Do not resell or republish the pack itself. Download terms
Related
Startup Credits Sweep: five rules and a five-check script (free sample)
From the Startup Credits Sweep: five rules for going after startup credits honestly (facts first, the program's own dated page, apply only when every requirement is met, answers say your facts word for word, count credits only after approval and set a reminder before expiry), and a read-only script that checks one small file for them.
Evidence Standard: what counts as proof for each kind of agent work, who checks it, and what is refused
Agents report done from the plan as often as from the result. Five plain files write down, for each class of work, the proof that counts, who checks it (never the producer), what is refused and how long proof is kept. Agents log each claim with its evidence, seal it by sha256 and report in the words evidence.py say allows: done, partly done with the gap named, waiting on the owner, or reported, not verified. The agent's own summary is never proof. Fifteen read-only checks run on the standard and the claims ledger.
Source Shelf: a short, owner-approved list of industry reports your team reads, and a way to read them
Keep a small set of major industry reports as your team's default evidence base: each with its edition, publish date, link on the publisher's own site, the date someone last looked for a newer edition, and a note on what the publisher sells. Read any one of them against three questions (what is changing, who is struggling, what could help them), with word-for-word quotes and page numbers, the third answer marked as your inference, and every figure matched to its quote. Every add, drop and replace waits for the owner's yes. Fifteen read-only checks run on the folder.
Compounding Offer Audit: score an offer on six tests, find its weakest point, change one thing
Score each thing you sell from 0 to 3 on six tests: recurring, productized, systemized, owned demand, compounding, and whether growing it would make the owner's week better. Every score needs a checkable fact and its source, or the word unknown and the fact you are missing; no 3 on the owner's say-so, and no total. The audit names the weakest test, treats a low life score as a veto on growth, and proposes one change with a success test and a date. Every change waits for the owner's yes. Fifteen read-only checks run on the folder.
Workflow, Not Wrapper: test an AI product idea, shape the offer and set the price
A prompt pack and method for anyone building or selling on top of a model. A seven-score absorption test, a one-page workflow product spec, a demo gap check, a problem mining loop, a five-talk buyer script, a channel translation table, a model column check, a true cost rebuild at three usage levels, an offer ladder with pricing rules, a price anchor audit, a check for copied success stories, a fidelity gate for generated output, a failure table, a worked example, an idea folder with a tested checker, a rules block and 19 prompts. What changed in v1.1: the demo gap check, buyer talks, true cost, price anchors and the checker are new.
Agent Readiness Self-Check: score one workflow before you hand it to an AI agent
A free self-check for agencies and small businesses. Name the decision, then score one workflow across eight areas (workflow mapped, data access, approval gates, owner per agent, handoffs, cost tracking, security and vetting, measurement) with an evidence rule, three gate rules and a skeptical pass, and read your band and the next steps it allows. v1.1 starts with the decision the score will change, scores unknowns as unknown, adds rules for conflicting facts and lookalike public records, ties every band to the next steps it allows with the Production Readiness Audit before go-live, makes owner approval concrete (prepared and approved status, a one-reply approval line, decisions the agent must leave open, a done test), adds agent files for Grok Bot, Claude Code, Codex and Hermes, a second worked example (missed call to booked job), a readiness folder with a fifteen-check read-only checker, a front door test with four questions to ask anyone selling you an agent install, and a plain note on how it was tested. Still free.