Text Message Consent Desk: safe text fixing rules and a ten-check text scan (free sample)
by PaperChaseWebb
From Text Message Consent Desk: the mistakes agents make when they tidy a business's texts, nine rules to paste into your agent, and a read-only script that runs ten checks on one saved text, from a missing STOP line and opt-outs that ask for a log-in to link shorteners, fake Re: lines, offers inside reminders, late send times and compliance claims.
- Price
- Free
- Difficulty
- Beginner
- Setup
- 5 min
- Format
- .md file
text-message-consent-desk-safe-text-fix-rules-ten-check-text-scan-free-sample.md · 10 KB · direct download, no signup
What you end up with
You can see whether a text, or an agent's fix of it, has the brand name, STOP line and send time it needs before it goes out.
What you get
- Why agent text fixes need checking
- Nine rules for agents that fix texts
- sms_mini.py: ten read-only checks for one saved text
- A made-up bike shop text with six findings and a clean fixed copy
Who it is for
Anyone who wants a quick check on a text, or on an agent's fix of it, before it goes out.
Works with
Solid chips: the agent is named in this listing's own tools list. Dashed chip: Plain Markdown, so it also pastes into other agents such as Grok Bot, Hermes, OpenClaw or Muse. We list those as compatible by format only, not as tested.
Tools needed
Cost to run: Free.
Time to result: About five minutes to a first scan
Sample prompts, free to use
Run python3 sms_mini.py on [fixed text] with --brand "[your business]". Fix every finding without deleting words or prices, inventing an offer or moving the send time, or hand it to me. Do not send or schedule anything.
The rules and script are in the file.
Free preview of the file
# Text Message Consent Desk: safe text fixing rules and a ten-check text scan (free sample) Version 1.0, 2026-11-01. By PaperChaseWebb. For anyone letting an AI agent tidy up the marketing or reminder texts a business sends. One page and one Python 3 script, standard library only, read-only: it reads one saved text, prints findings and changes nothing. It sends nothing and opens no network connection. No API key, no login. Tested on Linux with Python 3.13, 3.12, 3.11, 3.9 and 3.8: 4 unit tests, and 56 of 56 planted faults caught. The example business is made up. Not legal advice. ## Why agent fixes need checking Since April 11, 2025, the FCC counts a reply of stop, quit, end, revoke, opt out, cancel or unsubscribe as an opt-out, to be honored within 10 business days. Marketing texts need written consent first, a brand name, a STOP line, and a send time between 8 a.m. and 9 p.m. where the reader is. Most small business texts are missing one or two of these. An agent can fix them fast, and it gets them wrong in the same few ways: - It cuts the text to fit and the price goes with it. - It adds a discount nobody approved. - It tells people to reply NO, or log in, to stop. - It leaves a bit.ly link that carriers filter. - It moves the send time to make things fit. - It writes that the texts are "fully TCPA compliant". ## Rules to paste into AGENTS.md, CLAUDE.md, a Grok Bot standing order or Hermes notes 1. Never send or schedule a text, test texts included. Write a fixed co
Test record
- Date
- Nov 1, 2026
- What was run
- tests/test_mini.py (4), 56 planted faults against sms_mini.py, and the copy extracted from the sample page. Linux, Python 3.13, 3.12, 3.11, 3.9 and 3.8.
- Result
- 4 passed, 0 failed on all five versions; 56 of 56 faults caught; the extracted copy was identical to the tested script and found 6 problems on the example text and 0 on its fix.
- Not run
- Your settings, the fix check, the records and send list checks and the eval set (the full kit does those).
Copied from this item's dated test notes. What was not run stays in.
Worth knowing
- The sample checks one text on its own. Your settings, the fix check against the original, the records and send list checks, the eval set, owner approval and agent setups are in the full kit.
- Not legal advice. It does not say a text meets any law or will be delivered.
- On 2026-11-01 sms_mini.py passed 4 unit tests and 56 of 56 planted faults on Linux with Python 3.13, 3.12, 3.11, 3.9 and 3.8, and the copy extracted from the sample page was identical to the tested script.
Questions
Does it change my files or send anything?
No. It reads the file you name and prints findings. It opens no network connection, sends nothing and changes nothing.
What is in the full kit?
A 16-check scan using your own settings, a 12-check fix check against the original text, a records check, a send list check against consent, opt-outs, quiet hours and your weekly cap, owner approval at a terminal, a 7-text eval set, and setup for Grok Bot, Claude Code, Codex and Hermes. $29.
Details
Version 1.0 · Updated Nov 1, 2026 · Markdown version of this page
License: Personal and commercial use. Download terms
Related
Text Message Consent Desk: agent fixes for texts and send lists, opt-ins checked, every STOP honored, owner approved
Let an agent tidy your marketing and reminder texts and build each send list, without texting anyone who said stop, anyone with no record of signing up, or anyone outside quiet hours in their own time zone. It writes fixed copies and lists and never sends or edits your records. A fix check refuses deleted prices, moved send times and invented offers. A list check tests every number against your consent records, replies and send history. You approve at your terminal and send it yourself.
Email Sender Fix Desk: safe unsubscribe fix rules and a ten-check email scan (free sample)
From Email Sender Fix Desk: the mistakes agents make when they fix newsletter footers and sender records, nine rules to paste into your agent, and a read-only script that runs ten checks on one saved email, from missing one-click unsubscribe headers and unsubscribe links to a missing postal address, fake Re: subjects, leftover placeholders and inbox promises.
Review Reply Desk: safe reply rules and a ten-check review reply scan (free sample)
From Review Reply Desk: why review replies need checking, eight rules to paste into your agent, and a read-only script that runs ten checks on a reply draft, from public offers and requests to change a review to last names, invented numbers and links you did not approve.