Jev in production › Agent tool and action selection
A Claude Code hook asks Jev which installed skill fits a prompt; author published it as a negative result, finding it unlikely to help a strong model.
What happens when you add Jev to Claude Code as a skill router: the code, the log, and the week that ended with removing it.
jev-skill-router is a reference implementation for people building with TypeSafe's Jev, a model that writes no text and answers typed questions with probabilities. It is a Claude Code hook: on every prompt it asks Jev which installed skill fits and logs the answer. In shadow mode, the default, that is all it does; in inject mode it also gives Claude a one-line hint. Either way, Claude still sees every skill and makes the final pick. A bundled script checks that log against what Claude Code did next. It is Python 3.10+, standard library only, MIT licensed, version 0.2.0, and needs a paid TypeSafe API key.
For the project's own README, linking back here: