dcg

Community

Block destructive commands before they run.

AuthorDicklesworthstone
Version1.0.0
Installs0

System Documentation

What problem does it solve?

DCG prevents destructive commands from executing in Claude Code workflows, reducing the risk of data loss during automated agent runs.

Core Features & Use Cases

  • Whitelist-first guard that blocks dangerous commands like git reset --hard, rm -rf, and git push --force.
  • SIMD-accelerated filtering with a modular pack system for fast, real-time command interception.
  • Use Case: Integrate with Claude Code to automatically guard destructive commands during agent-driven coding workflows.

Quick Start

Run the dcg tool in a test environment to observe how it blocks dangerous commands and logs the rationale for denial.

Dependency Matrix

Required Modules

None required

Components

Standard package

💻 Claude Code Installation

Recommended: Let Claude install automatically. Simply copy and paste the text below to Claude Code.

Please help me install this Skill:
Name: dcg
Download link: https://github.com/Dicklesworthstone/agent_flywheel_clawdbot_skills_and_integrations/archive/main.zip#dcg

Please download this .zip file, extract it, and install it in the .claude/skills/ directory.
View Source Repository

Agent Skills Search Helper

Install a tiny helper to your Agent, search and equip skill from 223,000+ vetted skills library on demand.