All-In Price Desk: agent fixes for your menus, price pages and checkout, fees in the first price, owner approved
by PaperChaseWebb
Let an agent tidy your menus, rate cards, listings and checkout pages, check order records and review draft answers to "what is this fee?", without inventing a price, a discount or a fee, calling your fee a tax or promising a refund. It writes fixed copies and never publishes, refunds, charges or replies. A fix check refuses a removed price line, a deleted fee purpose, a new offer or a new phone number. You approve at your terminal and publish it yourself.
- Price
- $29
- Difficulty
- Intermediate
- Setup
- 45 min
- Format
- .md file
all-in-price-desk-fees-in-the-first-price-owner-approved.md · 201 KB · instant download after checkout
Want this built for you instead? We can build it for you.
What you end up with
Each price page shows what a customer really pays or names every fee with its amount and purpose where your state allows it, checkout names each charge before payment, nothing optional is pre-selected, and you know which orders charged the wrong fee, one approved change at a time, with nothing deleted and no claim that anything is compliant.
What you get
- 21 sections and an appendix in one .md file, with a one-line unpack for all 74 files
- price_check.py pages: 19 checks on each page against your own items, prices and fees and a dated rules table for the FTC fee rule and nine states, from a base price without a mandatory fee and "prices plus fees" to a fee with no purpose, your fee called a tax, "no hidden fees" next to a fee, a pre-selected tip and a checkout that never names the tax
- price_check.py orders: 8 checks on exported order records, so you see fees not in settings, wrong fee amounts, optional fees charged without a choice and totals that do not add up
- price_check.py replies: 13 checks on draft replies about fees, such as a fee called a city fee, a refund promised, a fee denied, "the system added it" and card details asked for, with owner stops for chargebacks and legal threats
- price_check.py fix: 12 checks that compare the agent's copy with the original, so a deleted line, a removed price or fee purpose, a new discount, phone or figure fails
- A claims check that stops reports saying a page is compliant or that the agent published, refunded, waived or sent anything
- The owner step: approve.py needs a real terminal and part of the file hash, refuses agent sessions and piped input, and checks the original has not changed before you mark it published
- An eval set for a made-up lake rental with 3 pages, an order record file and 14 reply threads, rules and two skills for Grok Bot, Claude Code, Codex and Hermes, six prompts and templates
- The test harness: 69 unit tests and 557 planted faults you can repeat
Who it is for
Small businesses and agencies who want an agent to tidy price pages and draft fee answers, with a person approving every change, every refund and every reply.
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: The kit is the only purchase. Everything runs locally with Python; the checker makes no network calls, logs in to nothing and changes nothing on any live page or checkout.
Time to result: The worked example in 5 minutes; your own pages and orders checked in about an hour
How it works
Unpack and test
Save the kit as pack.md in an empty folder, run the unpack line from Appendix A, then sh test_all.sh.
Expected: 74 files written; 69 tests OK; 557 of 557 planted faults caught.
Watch the flow
Run sh example/run_example.sh and read it next to section 17.
Expected: A restaurant's three pages with 26 findings, its order records with 3, a bad reply with 3, the agent's first-try fixes caught with 11, the second tries clean, a first-try report with 3 findings and a piped approval refused.
Put in your prices
Fill in site/settings.json and site/facts.md from the templates, save your pages in site/pages/, export orders to site/orders.csv, then run python3 desk/price_check.py site and python3 desk/price_check.py pages.
Expected: A short list of settings and page lines to fix first.
Fix and sweep the orders
Have your agent follow skills/price-page-fix and skills/fee-reply-review, then run price_check.py fix queue/fixes and approve each file at your terminal.
Expected: Fixed pages in queue/fixes with 0 high findings, and a list of orders and replies for you to decide.
Sample prompts, free to use
Follow skills/price-page-fix for every page in site/pages. Do not publish anything. List the codes fixed and the codes left for me, with the reason for each.
Prompt 1 of 6.
Run price_check.py orders on site/orders.csv. Refund nothing. List each order id, what was charged wrong and the amount, so I can decide.
Prompt 2 of 6.
Run price_check.py pages and replies. For each P03, P10, P17 and C04, tell me the price, number or offer so I can add it to settings.json or facts.md or take it out.
Prompt 4 of 6.
Free preview of the file
# All-In Price Desk: agent fixes for your menus, price pages and checkout, fees in the first price, owner approved Version 1.0, 2026-11-01. By PaperChaseWebb. For restaurants, short-term rentals, small hotels, event sellers, salons, studios and service shops, and the agencies that run their sites, who want an AI agent to tidy price pages, check order records and draft answers to "what is this fee?" without inventing a price, a discount or a fee, calling a business fee a tax, or promising a refund. Works with Grok Bot, Claude Code, Codex and Hermes. Python 3.8 or newer, standard library only, no API keys, no logins. The kit and the agent never change a live page or checkout, never refund or charge anything and never send anything. Tested with 69 unit tests and 557 planted faults on Linux with Python 3.13, 3.12, 3.11, 3.9 and 3.8. All business, contact and customer data in this kit is made up. Not legal advice. Prices now carry rules. The FTC fee rule asks lodging and ticket sellers to show the total price, every mandatory fee included, first and most clearly. In the table this kit reads, California, Minnesota, Virginia, Rhode Island, Massachusetts, Colorado, Oregon and Connecticut have their own all-in price rules in effect, and Illinois joins in January 2027. Some let a restaurant state a fee apart from the price if it says the amount and what the fee is for. Colorado also asks how a restaurant fee is shared. Most small price pages are close. They say "prices plus fees". A
Test record
- Date
- Nov 1, 2026
- What was run
- tests/test_lib.py (9), test_site.py (6), test_pages.py (11), test_orders.py (5), test_replies.py (8), test_fix.py (8), test_claims.py (4), test_modes.py (6), test_mini.py (4) and test_approve.py (8, on a real pseudo terminal); tests/mutate.py with 515 planted faults across pages, order records, replies, bad fixes, reports, agent rules and settings, plus 42 against price_mini.py; price_check.py set on the eval set; example/run_example.sh end to end; and the unpack line with test_all.sh. Linux, Python 3.13, 3.12, 3.11, 3.9 and 3.8.
- Result
- 69 passed, 0 failed on all five versions; 557 of 557 planted faults caught and all clean baselines clean; the eval set matched its expected codes and every fixed page had 0 high findings; the example caught the first-try fixes with 11 findings and the first-try report with 3, and refused piped approval; the unpack line wrote every file and test_all.sh passed there.
- Not run
- A live Grok Bot, Claude Code, Codex or Hermes session. Live checkouts, point of sale, booking systems and delivery apps. City and county rules, tax rates and laws outside the US. Languages other than English. macOS or Windows. Legal review.
Copied from this item's dated test notes. What was not run stays in.
Worth knowing
- The agent rules were checked by the checker but not loaded inside a live Grok Bot, Claude Code, Codex or Hermes session for this release. The eval fixes were written by hand to the rules. Give your agent the entrance exam in section 15 before you rely on it.
- Not legal advice. Nothing in the kit says a page, a reply or a business meets any law. The rules table is dated 2026-11-01; check it against the sources in section 20. City and county rules, tax rates and laws outside the US were not checked, and every state you sell in whose rule has started is treated as applying.
- The checker reads the pages, order records and replies you save. It does not read your live site, point of sale, booking system or delivery apps and cannot publish, refund or charge anything, so open each live page on a phone after each change and check the total before payment. English only.
- The owner step assumes the agent cannot run approve.py at a terminal. Run it as a separate user; agent rules alone are not a hard boundary.
- All businesses, people, prices and numbers in the kit are made up. Tested on Linux only; macOS and Windows were not tested.
- On 2026-11-01 on Linux: 69 unit tests and 557 of 557 planted faults passed on Python 3.13, 3.12, 3.11, 3.9 and 3.8; the eval set matched its expected codes; the unpack line wrote every file and test_all.sh passed in that folder.
Questions
Which agents does it work with?
Any agent that can read files and run a script. The kit has rules for AGENTS.md and CLAUDE.md, Claude Code and Codex notes, Hermes notes and a Grok Bot standing order. Those were checked by the checker, not loaded in each agent for this release.
Will it change my menu, refund customers or reply for me?
No. The agent writes fixed copies into a queue folder and a list of orders and replies for you. You approve each file at a terminal, publish it yourself, and decide and send every refund and reply.
Can I keep a service fee or kitchen fee?
The kit does not decide that. It reads the rules for the states you sell in: where a restaurant may state a fee apart, the page check asks for its amount and purpose on every page with prices; elsewhere it shows the all-in price to use instead.
Does it work for rentals and tickets?
Yes. Mark your kind of business in settings. For lodging and tickets the FTC fee rule is in the table, and the eval set is a made-up lake rental with a cleaning fee and a resort fee.
Can you set it up for us?
Yes. Our Install sprint maps your items, fees and states, writes your settings and facts file and builds an eval set from your own pages, or Managed Ops runs the checks, fixes and order sweeps for you each week. Book a call or write to [email protected].
Details
Version 1.0 · Updated Nov 1, 2026 · Markdown version of this page
License: Use inside your own business or for your clients. Do not resell or republish the kit itself. Download terms
Related
All-In Price Desk: all-in price rules and a ten-check price page scan (free sample)
From All-In Price Desk: the ways small price pages slip, ten rules to paste into your agent, and a read-only script that runs ten checks on one menu, listing or checkout page, from "plus fees" and a fee with no amount or purpose to your fee called a tax, "no hidden fees" next to a fee, a pre-selected tip and a compliance claim.
Job Post Desk: agent fixes for your job ads and applicant replies, pay range shown, fair wording, owner approved
Let an agent tidy your job ads, check where each ad is still up and review draft replies to applicants, without dropping the pay range, inventing a bonus, asking for pay history or telling anyone they got the job. It writes fixed copies and never posts, takes down, rejects or replies. A fix check refuses a removed range, a deleted line, a new perk or a new email. You approve at your terminal and post it yourself.
Refund and Returns Desk: agent fixes for your return policy, delivery page and delay notice, policy matched, refund amounts checked, owner approved
Let an agent tidy your return policy, delivery page, product page and delay notice, check refunds and late orders against your order list, and review replies to refund requests, without inventing a window, a fee or free returns, or telling a customer a refund was made when it was not. It writes fixed copies and never touches the live site, refunds anything or sends anything. A fix check refuses a removed return window, a deleted sentence, a new promise or a new email. You approve at your terminal and paste it in yourself.
Subscription Renewal Desk: agent fixes for your checkout, terms and cancel page, plans matched, cancel path kept, owner approved
Let an agent tidy your subscription checkout, terms, cancel page and renewal reminder, plan the renewal, trial and price change notices from your subscriber list, and review replies to cancel requests, without dropping the renewal line, hiding the cancel path or making up prices and offers. It writes fixed copies and never touches the live site or sends anything. A fix check refuses a removed cancel link, a deleted sentence, a new discount or a new phone number. You approve at your terminal and paste it in yourself.
Review Reply Desk: AI-drafted review replies, checked for privacy and offers, approved by the owner
Let an agent draft your Google and Yelp review replies without the mistakes that cost money. A checker refuses drafts that use a last name or details from your records, offer a discount for a better review, ask for a review to be changed, argue, invent numbers or promises, or repeat your last reply word for word. Health topics, allergies and legal threats go to the owner, clinics get a stricter privacy mode, and nothing is posted until the owner approves it at a real terminal.
Don't Get Sued: a pre-launch legal-risk gate for AI-built apps and agents
A read-only agent gate for the fourteen legal risks that hit small builders most: marketing texts and email, trackers before consent, accessibility, kids' data, biometrics, plain-text personal data, AI disclosure, AI claims you cannot prove, takedowns, policies that do not match the product, renewals and refunds, licenses, and agents that act for users. Evidence rule, gate register, seeded test app, 12 prompts, counsel packet. Not legal advice.
Ask-first rules for AI agents: hard nos, approval cards and a test set
Paste-in rules that make an agent ask before it sends, spends, posts or deletes, define what a real yes is, and stop retries after a no, plus 12 test scenarios to check it.