Jameskomo

Tests for your Claude Code setup that run on every release

Share on:

Tests for your Claude Code setup that run on every release. Know when a skill or hook stops working, and why.

config-drift-checker config-drift-checker How it works What it found Hosted GitHub Your Claude Code setup is code. Nobody tests it. config-drift-checker tests your CLAUDE.md, skills and hooks against a pinned baseline on every PR, canaries the latest model and Claude Code on every release, and opens a PR when the canary has earned it. Open source. It runs in your own GitHub Actions with your own API key, inside a budget you set, and nothing leaves your repository. Get it on GitHub See the drift index config-drift-checker · pull request #14 · after Claude Code 2.1.248 eval 1 case regressed agai

Related listings

design database schemas for your team and agents

China company code vs. US VIN check digit

a 3D imageboard where being there is the write permission

OpenTelemetry-native tracing for LLM apps and agents

retrieval methods visualized

A Context Registry for AI coding agents