rh-guard

A guardrail for coding-agent hooks (Claude Code, Cursor, and others) that combines hard structural denials with a Jev-powered sidecar to catch reward-hacking behavior — tampering with graders, hidden tests, or the evaluation process itself.

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