All projects

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.

JavaScript
Stars
4
Forks
0

Why it is listed

A pre-execution coding-agent hook combining deterministic command rules with an optional Jev engine for six typed risk questions. Policy retains execution control; safety claims are not independently certified.

Related projects

  • jev-advisor-gateway

    Local gateway that routes coding-agent tool decisions through Jev and can attach a read-only advisor (GPT or Claude).

    Shared topics: claude-code, codex

  • agent-fastpath

    Jev MCP server: a decision layer for coding agents, built on TypeSafe Jev (System One model). Ship gates, risk checks, file triage that keeps files out of context, and a safe headless browser, with calibrated confidence. For Claude Code, Codex, Cursor.

    Shared topics: claude-code, codex

  • agent-chaperone

    Screens an AI agent's tool calls before they run and tool results before the agent reads them. An MCP proxy plus a hooks adapter for a client's built-in tools.

    Shared topics: agent-security, claude-code