Skip to content
#

command-approval

Star

Here are 4 public repositories matching this topic...

Language: All
Filter by language
All 4 Python 2 JavaScript 1 TypeScript 1

ursuciprian / reflex

Star 4

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.

mcp opencode typesafe codex autonomous-agents human-in-the-loop devsecops laya guardrails prompt-injection llm-guardrails agent-security claude-code codex-cli claude-code-hooks ai-coding-agents command-approval jev system-one pre-execution-hook
  • Updated Oct 2, 2026
  • JavaScript

Add this topic to your repo

To associate your repository with the command-approval topic, visit your repo's landing page and select "manage topics."

Learn more