A config-driven Claude Code hook that stops an AI agent from running a destructive command against a production database by accident.
-
Updated
Jul 16, 2026 - Python
A config-driven Claude Code hook that stops an AI agent from running a destructive command against a production database by accident.
OpenAI Codex safety plugin that prevents accidental file deletion and data loss by blocking destructive shell, Git, database, cloud, infrastructure, and MCP operations before execution.
Static safety analyzer for EF Core migrations. Catches DropColumn + AddColumn data loss, missing defaults, empty Down() methods, and unsafe rename operations before they reach production.
Add a description, image, and links to the database-safety topic page so that developers can more easily learn about it.
To associate your repository with the database-safety topic, visit your repo's landing page and select "manage topics."