Skip to content

Lost checkout discount rules audit per store

For a store whose old checkout scripts stopped running, it finds each discount, shipping and payment rule that quietly stopped and checks whether anything replaced it. You get one read-only report with fixes ranked by revenue impact.

Ecommerce and resaleWorks with Claude Code · Claude Desktop with MCP+1Community example

What it does

  • Lists each old script and splits it into single rules
  • Reads the live store admin to see if a native setting replaced each rule
  • Marks every rule as lost, replaced, partial or never ran
  • Ranks fixes by revenue impact, with native settings first
  • Writes developer specs for anything that needs custom code

Your approval boundaries

Approval required

These actions always wait for your yes:

  • Changing any store setting or discount
  • Placing a test order
  • Building or deploying any custom code

You decide what happens next.

More about this workflow

This setup is for online sellers and resale shops juggling listings, orders and buyers. It takes a repeat chore off your plate and hands back something you can check quickly.

First, it lists each old script and splits it into single rules. Next, it reads the live store admin to see if a native setting replaced each rule. Then it marks every rule as lost, replaced, partial or never ran. After that, it ranks fixes by revenue impact, with native settings first. Finally, it writes developer specs for anything that needs custom code. It works with your store admin and docs, each on its own login with limited access.

You get the prep work done and waiting for you. The agent stops and asks for your yes before changing any store setting or discount, placing a test order and building or deploying any custom code, and says plainly if a step cannot be undone.

“it never changes the store, never signs in or asks for passwords”
ShahzDevAventures ShahzDevAventures on GitHub · Nov 4, 2026
Before you startStore admin · Docs accessScoped permissionsClaude Code or Claude Desktop with MCP
Explore required tools and model recommendations

Tools and access

  • Shopify

    Handles the store admin part of this job. Grant read orders and products.

    API required: Yes. Needs a Shopify app with an access token and the admin scopes you approve.

  • Google Docs

    Handles the docs part of this job. Grant one folder, create and edit only.

    API required: Yes. Needs a Google Cloud OAuth app with the Docs API turned on.

Official links only. Not sponsored, no affiliate links.

Model recommendations

Best pick

Gemini 3.8 Flash

Built for agent workflows, with a free tier to test on.

$0.75 per million input tokens and $3.75 per million output tokens through December 31, 2026. $1.50 and $7.50 from January 1, 2027.

Google docs as of October 11, 2026

Cheaper backup

Gemini 3.5 Flash-Lite

Low cost for many listings at once.

$0.30 per million input tokens, $2.50 per million output tokens.

Google docs as of October 11, 2026

Our own picks. Not sponsored, no affiliate links.

Build your prompt

Add your details, then copy the prompt into your tool.

1Your details

Fill these in and the prompt updates as you type.

pm or developer

2Your prompt

3 of 3 still empty
Fill these in before you run it: [STORE ADDRESS] [SCRIPTS REPORT EXPORT] [WHO DOES THE FIXES: pm or developer] You are the Lost checkout discount rules audit per store agent. For a store whose old checkout scripts stopped running, it finds each discount, shipping and payment rule that quietly stopped and checks whether anything replaced it. You get one read-only report with fixes ranked by revenue impact. Use only the details filled in above. If any [BRACKETED] item is still blank or unclear, stop and ask for it first. Do not guess. What you do on your own: - Lists each old script and splits it into single rules - Reads the live store admin to see if a native setting replaced each rule - Marks every rule as lost, replaced, partial or never ran - Ranks fixes by revenue impact, with native settings first - Writes developer specs for anything that needs custom code What you must never do without a yes from a person: - Changing any store setting or discount - Placing a test order - Building or deploying any custom code Rules: - Before any step on the list above, stop and ask. Say in plain words what you want to do, who it affects, and whether it can be undone. - If something cannot be undone, say so first, in one short line. - Write drafts, not final actions. A person sends, pays, posts, or deletes. - Keep a short log of every action you took and every source you read. - If you are unsure, ask instead of guessing.
View run instructionsPaste into: Claude Code, Claude Desktop with MCP, ChatGPT agent

Your answers stay in this browser only.

Run your workflow

Connect your tools with only the access this setup needs, then follow these steps.

Steps

Do these in order. Test on old data before it touches live work.

  1. 1Connect Shopify with its own login, not yours. Grant read orders and products.
  2. 2Connect Google Docs with its own login, not yours. Grant one folder, create and edit only.
  3. 3Paste the prompt where your harness takes instructions. See the note under the Copy button.
  4. 4Do a dry run on old or test data first. Check every draft and every stop point by hand before you let it near live work.
  5. 5Read its log after the first real run. Only widen access once a week of runs looks clean.

Safeguards and trust score

The score describes this example setup’s access, approval boundaries, ability to undo changes, and scope.

Access18 / 30

Can draft things that send or spend, so it sits close to risky actions.

Human approval30 / 30

Waits for a yes on: changing any store setting or discount, placing a test order, building or deploying any custom code.

Undo and logs14 / 20

Proposes changes to live records, so the setup needs a change log and a way back.

Scope18 / 20

Runs on its own login across 2 tools. Fewer connections means a smaller blast radius.

How to raise it

  • Access: Take away its ability to send, post or spend. Let it only write drafts, and have a person press send or pay from their own account +6
  • Undo and logs: Stop it from editing live records. Have it write the change as a proposal you apply, and keep a log of every change with a way to roll it back +3
  • Scope: Run it on one tool only, with its own login that can see just what this job needs +2

Do all of these to reach 91, up from 80.

Want help getting there? Get an AI Trust Audit from Pixeldesigns

Reviewed by Trustcase (example setup). How scoring works

Embed badge

Show this trust score on your site or README. It links back here.

Trustcase trust score badge
Markdown
[![Trustcase trust score for Lost checkout discount rules audit per store](https://trustcase.dev/badge/lost-checkout-discount-rules-audit-per-store.svg)](https://trustcase.dev/use-cases/lost-checkout-discount-rules-audit-per-store)
HTML
<a href="https://trustcase.dev/use-cases/lost-checkout-discount-rules-audit-per-store"><img src="https://trustcase.dev/badge/lost-checkout-discount-rules-audit-per-store.svg" alt="Trustcase trust score for Lost checkout discount rules audit per store" height="20"></a>

Other workflows that use the same tools

  • Proposal first draft

    Sales. Builds a proposal from your template and the discovery notes.

  • Refund checker

    Support. Checks refund requests against your policy and lays out the facts.

  • Weekly ops report

    Operations. Writes the Monday numbers summary so you do not build it by hand.