I measured what my Claude.md, skills and hooks are worth
The config-drift-checker is a tool designed to monitor and test the configuration of AI coding agents like Claude Code. It ensures that changes to CLAUDE.md files, skills, or hooks do not negatively impact agent performance by running automated test cases.
Why it matters
As AI agents become integral to software development, managing configuration drift is critical to maintaining code quality and preventing silent failures in automated workflows.
CI for your agent setup. · site · demo report
A tool that tells your team when its coding-agent setup — CLAUDE.md , skills, hooks — stopped doing what it should, why , and what changed : a model change behind an alias, a Claude Code release, or a teammate's edit.
Your CLAUDE.md, skills and hooks are how your code gets written now. They are configuration that other people change underneath you: Claude Code shipped 25 versions in the 30 days before this was written, the model behind sonnet changes server-side with no changelog, and a colleague can edit a skill in a PR nobody tests. Today you find out when a developer notices "it stopped running the tests before committing" — often weeks later.
config-drift-checker turns what your setup must do into test cases, runs the real agent against them, and keeps score over time:
Get smarter about the news
Sign up free for a feed built around what you actually care about, Dive Deeper research on any story, and the full text of every article.
Create free accountAlready have an account? Sign in