reflex

ursuciprian/reflex

Pre-execution risk gate for AI coding agents (Claude Code, Codex, opencode, pi, Hermes). Blocks or asks on risky shell commands, guards against prompt injection in what agents read, escalates to System 2 and a human queue. Optional TypeSafe Jev.

Agents & automationJavaScript

Stars: 0
Forks: 0

Why it is listed

No inclusion rationale available yet

View cited source

Topics

jevagent-securityai-coding-agentsautonomous-agentsclaude-codeclaude-code-hookscodexcodex-cli

Open on GitHub