Building a Codebase Classifier with Jev
A developer shares building a codebase classifier with Jev, suggesting it may solve overengineered code from agents, and asks what to test next.
The author shares building an agent-agnostic permission gate using Jev (TypeSafe) and hooks. In YOLO mode, dangerous commands like chmod -R are blocked; the agent asks the user, and each run needs re-confirmation.
Been building an agent-agnostic permission gate: Jev (TypeSafe) + hooks. Many harnesses copy Claude Code's hook format. Some barely have hooks at all. This makes me happy: agy in YOLO mode. chmod -R gets blocked, the agent asks me, I say yes, it runs once. Again? Blocked again.