matanryngler/deployshield

README preview

# 🛡️ DeployShield

[![Tests](https://github.com/matanryngler/deployshield/actions/workflows/test.yml/badge.svg)](https://github.com/matanryngler/deployshield/actions/workflows/test.yml)
[![Release](https://img.shields.io/github/v/release/matanryngler/deployshield)](https://github.com/matanryngler/deployshield/releases)
[![License: MIT](https://img.shields.io/badge/License-MIT-yellow.svg)](https://opensource.org/licenses/MIT)
[![Python Support](https://img.shields.io/badge/python-3.9%2B-blue.svg)](https://www.python.org/downloads/)

**DeployShield** is a cross-platform production safety guardrail for **Claude Code** and **Gemini CLI**. It intercepts terminal commands before execution and blocks dangerous operations (writes, deletes, etc.) while allowing read-only commands to pass through.

## 🚀 Why DeployShield?

Large Language Models (LLMs) are incredibly capable but can accidentally execute destructive commands in production environments. DeployShield provides a **deterministic safety layer** that doesn't rely on probabilistic model instructions.

- **Deterministic Protection**: Uses a curated safe-list of read-only subcommands.
- **Recursive Safety**: Deeply scans subshells, backticks, `sudo`, and `bash -c`.
- **Context-Aware**: Granular control—block writes in `production` while allowing them in `dev`.
- **Zero-Dependency**: Fast, lightweight, and runs on any system with Python 3.8+.

---

View full repository on GitHub →