clear-head

A Claude Code Stop hook that checks an AI assistant's factual claims against the evidence it actually read during the session, using TypeSafe's Jev as a fast, cheap judge, and blocks the turn with the specific unsupported claims listed if something doesn't hold up.

unverified — sourced from awesomejev.com; description independently written by AionEdge from the repo’s own GitHub metadata and README, not GitHub-API relevance-checked