A checker that reports zero policy problems is more dangerous than no checker

Google's policy-violation disapproval cause -- misrepresentation, restricted products -- has zero static rules by design, and the pack asserts that no rule is ever allowed to quietly claim it.

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 checker that silently reports '0 policy problems' alongside its other passing checks implies a judgment it never actually made -- policy violations (misrepresentation, restricted categories, claims judged across a whole site) are a human review call, not a property any static rule over a feed file or a landing page can determine, and a tool that implies otherwise is actively misleading.

Why this one is easy to get wrong

A diagnostic tool that reports pass/fail across a fixed list of causes reads as complete by construction -- every named cause gets a verdict, so silence on 'policy violation' looks the same as 'checked and clean' rather than 'never checked at all.' Distinguishing those two states requires a deliberate design decision, not something that falls out of building the other, genuinely checkable rules.

What you get instead

spec.disapproval_causes ships policy-violation with zero rules attached, on purpose, and diagnose()'s CauseGroup keeps every cause in the report -- including empty ones -- specifically so 'we checked and found nothing' and 'we never checked' render as visibly different sections. One of the pack's own acceptance checks exists purely to assert that no rule anywhere is ever allowed to claim the policy-violation cause, and formatReport()'s NOT CHECKED section prints on every run, including a fully clean one.

Source: ARCHITECTURE.md 'Disapproval causes' — 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 →