Dicklesworthstone/destructive_command_guard
The Destructive Command Guard (dcg) is for blocking dangerous git and shell commands from being executed by agents.
This project helps software developers prevent their AI coding agents from accidentally deleting work. It acts as a safety net, blocking dangerous commands that might wipe out uncommitted code, delete critical files, or disrupt development workflows. Developers using AI tools like Claude Code, GitHub Copilot CLI, or Cursor IDE would benefit from this guard.
670 stars. Actively maintained with 36 commits in the last 30 days.
Use this if you are a software developer frequently using AI coding agents and want to prevent them from executing destructive commands that could erase hours of work.
Not ideal if you are not a software developer or do not use AI coding agents as part of your development process.
Stars
670
Forks
40
Language
Rust
License
—
Category
Last pushed
Mar 12, 2026
Commits (30d)
36
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/agents/Dicklesworthstone/destructive_command_guard"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Featured in
Related agents
ucsandman/DashClaw
🛡️Decision infrastructure for AI agents. Intercept actions, enforce guard policies, require...
microsoft/agent-governance-toolkit
AI Agent Governance Toolkit — Policy enforcement, zero-trust identity, execution sandboxing, and...
vstorm-co/pydantic-ai-shields
Guardrail capabilities for Pydantic AI — cost tracking, prompt injection detection, PII...
Pro-GenAI/Agent-Action-Guard
🛡️ Safe AI Agents through Action Classifier
project-codeguard/rules
Project CodeGuard is an AI model-agnostic security framework and ruleset that embeds...