Back to agent tooling
Agent tooling

construct-auto-classifier

Effect-based safety gate for AI coding agents' shell commands (OpenCode, Antigravity): fast structural rules, then TypeSafe's Jev or a chat model judges what a command does. Certified with Jev at zero dangerous commands allowed.

Added
2026-09-20
Language
TypeScript
Stars at snapshot
2

Source: community catalog. Details and metrics reflect the published community snapshot and are not a performance endorsement.