@realnribal's pre-execution risk gate: Jev scores rm -rf ./node_modules at ~50% and blocks rm -rf / at 99%.

Agent demo with a gif. A pre-execution risk gate for AI agents using Jev (TypeSafe AI). The same command pattern differs: rm -rf ./node_modules is about 50% risk and asks first; rm -rf / is 99% risk and is blocked instantly. The post says a regex gate cannot tell them apart and Jev can. For people gating agent shell commands before they run.