frmoretto/hardstop
πͺMarketplacefrmoretto/hardstop
|Don't let AI destroy your hard work! HardStop is a rock-solid protection for AI-generated commands. Pre-execution safety validation for Claude Code, Claude Cowork. Catches dangerous commands before they run: whether from AI mistakes, hallucinations, prompt injection, or misunderstood instructions. Seatbelts for the agentic AI era.
Overview
HardStop is a safety-first Claude Code plugin that provides pre-execution validation for AI-generated commands. It acts as a protective barrier, catching dangerous commands before they run -- whether caused by AI mistakes, hallucinations, prompt injection, or misunderstood instructions.
Key Features
- Pre-execution safety validation for all AI-generated commands
- Detection of dangerous operations like destructive file operations and system changes
- Protection against AI hallucinations, prompt injection, and misinterpreted instructions
- Compatible with Claude Code and Claude Cowork environments
- Configurable safety rules to match team policies and risk tolerance
Who is this for?
HardStop is essential for any developer using AI coding agents who wants an extra layer of protection against accidental destructive commands. It is especially critical for teams working in production environments where a single misexecuted command could cause significant damage.
Add this Marketplace
/plugin marketplace add frmoretto/hardstop