What it does
The CLI handles scoring and thresholds locally, caches by content, and can pair changed-code checks with local coverage evidence.
Agent tooling
Supercov
Supercov asks named quality and security questions about source files, then turns Jev's answers into inspectable findings.
Bookmark: Supercov
Keep this in your collection.
Leave a noteWhat would you try with this?
: Supercov
Only you can see your notes.
Screenshot unavailable. Open the experiment ↗
How you can use it
A developer can install this tool as a plugin for an AI coding assistant. The assistant runs the software to check your project files. It sends the code to Jev, an outside AI service. Jev answers simple yes or no questions about each file. The service looks for problems like hidden secrets.
The software calculates a final score using those answers. Every part of a score points directly to a claim you can check. The AI highlights security risks, but it cannot catch every dangerous mistake.