Greenwash

The README opens with

A GitHub App that catches AI coding agents cheating to make CI green.

When a coding agent can't fix a failing build, it sometimes makes the build pass anyway. It weakens an assertion, skips the test, hard-codes the answer the test expects, or marks the CI step as non-blocking. The build turns green and the reviewer moves on.

Greenwash reads every changed hunk of every pull request and asks narrow yes/no questions about it — "does this delete a test assertion or replace it with a weaker one?" — using TypeSafe's structured-judgment models. Findings show up as a check run with line annotations and a single pull request comment, each with a probability instead of a verdict.