Your feed can be perfectly valid and still be the #1 reason for disapproval

The feed disagreeing with the landing page Google actually crawls is the #1 data-related Merchant Center disapproval cause -- and it's invisible to any validator that only reads the feed file.

This is one of the things Product Feed & Merchant Center Compliance already handles. Get your products into Google Shopping and keep them from being rejected.

Buy for $1292 of 3 clean-room builds passed · full refund if it fails on your machine

Is this you?

A feed can pass every structural and spec check and still get disapproved, because Google separately crawls the landing page each item links to and compares its price, currency, sale window and availability against the feed -- and a mismatch there is reported as a disapproval, not a warning. Price mismatch is ranked the #1 data-related disapproval cause industry-wide, and it's simply not a property the feed file itself can reveal.

Why this one is easy to get wrong

An agent asked to "generate a Google Shopping feed" reasons entirely about the feed as an artifact -- validate its structure, check required fields, ship it. There's no reason from that framing alone to go crawl a second, separate surface (the live product page) and compare it against the file just produced, because the two are built and reasoned about as unrelated outputs.

What you get instead

comparePage() checks, first match wins: page unreachable, missing structured data (and whether it's JS-only, rendered but invisible to Google's non-JS crawl), currency mismatch, then price mismatch against the exact same effectivePrice() function the feed uses, then availability mismatch. crawlCatalog() runs this against every item and returns findings in catalogue order, so two runs of the same catalogue produce an identical, diffable report.

Source: ARCHITECTURE.md 'Consistency (the check that is not about the feed)' — checkable in the pack you receive

How you actually use this

You don’t install a library or wire up an SDK. Your own coding agent builds the code in your project, and you keep it — no runtime dependency on us.

Step 1
Download and unzip
You get a folder: the docs that tell an agent what to build, a starting skeleton, and the test suite that decides when it's done.
Step 2
Open it in Claude Code or Cursor
Point your coding agent at the folder. Nothing to install, no account with us, no API key.
Step 3
Paste one prompt
The pack contains the exact prompt. Paste it as your first message and leave it alone — it works through the build itself, choosing a cheaper or stronger model per task.
Step 4
Run ./verify.sh
One command. It prints a pass or fail for every check. Green means the build is done — the same script we ran to produce the receipt on this page.

Typical build: about 44 minutes of your agent working, mostly unattended. Then you integrate the working module into your app the way you would any code you’d written yourself.

Why you can believe this

2 of 3 runs passed

We ran this pack from an empty folder 3 times and published exactly what happened — every check, the model, the token cost, the wall time. Not a testimonial, and not our opinion: the same verify.sh you run yourself. Read the full receipt →

Buy for $129 14-day refund if verify.sh fails →