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

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.

Works with

Solid chips: the agent is named in this listing's own tools list. Dashed chip: One Python script, a fact sheet template, a fictional three-page example and agent rules for each harness. Tested on Linux.

Tools needed

Cost to run: Free. Python is free.
Time to result: First scan in about 20 minutes

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 prompts, free to use

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.

Free preview of the file

# 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

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.

Details

Version 1.0 · Updated Nov 3, 2026 · Markdown version of this page
License: Personal and commercial use. Download terms

Related

Prompt pack$39

Front-Door Review Stack: catch machine-made tells, UX breaks and invented claims before a page goes live

by PaperChaseWebb

A review gate for agent-built landing, pricing, product and profile pages: a hard floor that blocks publishing, a truth pass for every claim, 20 UX principles as yes or no questions, 36 machine-made tells with fixes, a real browser pass and a fresh-eyes reviewer. Includes front_door_check.py, AGENTS.md with six owner stops, two skills and templates.

Works withClaude CodeCodexGrok BotHermes+1Plain .md; the checker needs Python 3.8 or newer

Vibe coding · Intermediate · 30 min setup

Prompt pack$19

AI Answer Visibility Check: does an assistant name you when a buyer asks, and who gets named instead

by PaperChaseWebb

Ask each buyer question three times per assistant in fresh chats, paste the answers, and get a dated record of where you were named, where you were missed, who was named instead and which sources each answer cited. Fifteen read-only checks keep it honest: no brand in the question, three runs before a gap, answers hashed as given, nothing older than a month treated as current, and only your own brand. Page changes wait for the owner's yes.

Works withClaude CodeCodexGrok BotHermesA 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 assistant was asked anything for the worked example

Solo business · Beginner · 45 min setup

Prompt pack$19

Compounding Offer Audit: score an offer on six tests, find its weakest point, change one thing

by PaperChaseWebb

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.

Works withClaude CodeCodexGrok BotHermesA 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 the audit was not run on a real business

Solo business · Intermediate · 1 hr setup