# One Front Door: a ten-second offer test and one fact sheet for every page

> A free kit for businesses described in more than two places. Write one offer sentence and one fact sheet where every fact has a source and a checked date. A checker reads copies of your site, profiles and bios, flags every page that disagrees, every banned phrase and every front page that fails the ten-second test, then turns it all into one decision sheet you answer in a single reply. Nothing changes until you decide.

- URL: https://paperchasewebb.ai/bots/marketplace/items/one-front-door-ten-second-offer-test-and-fact-check/
- Type: Prompt pack
- Category: Solo business
- By: PaperChaseWebb
- Works with: Claude Code, Codex, Grok Bot, Hermes (named in the listing); One Python script, a fact sheet template, a fictional three-page example and agent rules for each harness. Tested on Linux
- Price: Free USD
- Difficulty: Beginner
- Setup time: 15 min
- Time to result: First scan in about 20 minutes
- Format: Markdown (.md) file, one-front-door-ten-second-offer-test-and-fact-check.md
- Version: 1.0, updated 2026-11-03
- License: Personal and commercial use.

## What you end up with

Every page you own says the same true thing, with a fix list of only the edits you approved.

## What you get

- The method: one offer sentence, one sourced fact sheet, a ten-second test for front pages, one reply to settle it all
- frontdoor.py: 5 fact sheet checks, 4 page checks and 4 reply checks, with pages scanned by line
- A one-reply decision sheet with options and a default for every item, and a fix list of only the approved edits
- Owner decisions refused inside an agent session or after any page changes, and pages never edited by the tool
- AGENTS.md, CLAUDE.md, a Grok Bot standing order and a Hermes skill, a fictional example, and 25 tests

## Who it is for

Anyone whose business is described in more than two places and wants every one of them to agree.

## Tools needed

- Python 3.8 or newer: frontdoor.py: fact sheet check, page scan, decision sheet, owner reply and fix list; standard library only
- Grok Bot, Claude Code, Codex or Hermes (optional): refreshes page copies, runs the scan and drafts edits under AGENTS.md; never records decisions or edits the fact sheet
- You need: Python 3.8 or newer
- You need: Saved copies of your pages (.html, .md or .txt)

Cost to run: Free. Python is free.

## How it works

1. **Run the example.** Unpack the file and run python3 frontdoor.py scan example/facts.json example/surfaces. Expected: 7 findings; the home page is clean.
2. **Write your fact sheet.** Fill in templates/facts.json from sources you can point to: offer, who it is for, start step, facts with checked dates, banned phrases. Expected: frontdoor.py check shows 0 errors.
3. **Scan your pages.** Save copies of your site, profiles and bios into a folder and run scan, then sheet. Expected: decisions.md with one numbered item per mismatch.
4. **Reply once.** Answer the sheet in one line at your own terminal, then run fixlist and hand the drafts to whoever edits each page. Expected: fixlist.md with only the edits you approved.

## Sample prompt: Monthly front door check (Grok Bot, Claude Code, Codex, Hermes)

```
Follow AGENTS.md. Refresh the page copies in pages/, run frontdoor.py scan, and if anything is found, run sheet and send me decisions.md with the reply line. Do not edit facts.json or any page.
```

One prompt.

## Free preview of one-front-door-ten-second-offer-test-and-fact-check.md

````markdown
# One Front Door

**One offer sentence and one sourced fact sheet. A checker reads every page you have, finds where they disagree, and hands you one reply to settle it all.**

Version 1.0, 2026-11-03. By PaperChaseWebb Inc. Free. Works with Grok Bot, Claude Code, Codex and Hermes, or by hand. Python 3.8 or newer, no installs.

## The problem

Most small businesses tell their story in five places: the site, a directory profile, a marketplace bio, a newsletter about page, a slide deck. Each was written on a different day. One says founded in 2019, another 2021. One quotes last year's price. One still offers a service you dropped. A visitor who sees two of them stops trusting both.

And the front page often fails the simplest test. In ten seconds, can a stranger tell what you do, for whom, and how to start?

## What you get out of it

- A fact sheet you trust: one offer sentence, who it is for, one start step, and every fact with its source and the date you checked it.
- A scan of every page copy you give it, with each mismatch named by page and line.
- One decision sheet with a numbered item per mismatch and a reply line like `1: fix 2: remove 3: hold`. Answer in one message.
- A fix list of exactly the edits you approved, drafted for whoever edits each page. Nothing changes on its own.

## Who it is for

Founders, consultants, studios and small agencies with more than two places where their business is described. Useful before a launch, after a price change, when you add a new
````

## Test record

- Date: Nov 3, 2026
- What was run: tests/test_frontdoor.py (25 tests) unpacked from the pack file and run fresh on Linux, Python 3.8, 3.9, 3.11, 3.12 and 3.13; scan, sheet, reply and fixlist on the fictional example.
- Result: 25 passed, 0 failed on all five versions; the example gives 7 findings and a clean home page; decisions refused in agent sessions and after a page edit; pages never modified.
- Not run: macOS or Windows. Real sites. A live Grok Bot, Claude Code, Codex or Hermes session.

Copied from this item's dated test notes. What was not run stays in.

## Worth knowing

- It reads saved copies, not live pages, and finds only what your patterns describe.
- The ten-second test is a text check on the first 80 words. It does not judge design or speed.
- On 2026-11-03: 25 tests passed on Python 3.8, 3.9, 3.11, 3.12 and 3.13 on Linux, run from the files unpacked out of the pack. Agent rules guide; they were not loaded inside each harness for this release.

## Questions

**Does it write my offer?** No. You write one sentence. It checks that every page agrees with it and with your facts.

**Can my agent fix the pages?** It drafts the edits you approved in fixlist.md. Recording decisions is refused inside an agent session, and the tool never edits a page.

**Does it need an API key or a crawler?** No. It reads files you save into a folder.

**What should I pair it with?** Front Door Review Stack ($39) reviews a single page for machine-made tells and invented claims before it goes live, and AI Answer Visibility Check ($19) tests whether assistants name you.

## How to get it

Free sample. Download it directly at https://paperchasewebb.ai/bots/marketplace/items/one-front-door-ten-second-offer-test-and-fact-check/, no signup.

Seller: PaperChaseWebb Inc., mgmt@paperchasewebb.com