Skills
.Work. You
Rest

destructive-command-guard

Official

Block dangerous commands before execution.

Software Engineering#git#security#cli#safety#filesystem#guardrails#command blocking
Authoroakoss
Version1.0.0
Installs0

System Documentation

What problem does it solve?

This Skill prevents AI agents from accidentally executing destructive commands in the terminal, safeguarding against data loss and system instability.

Core Features & Use Cases

  • Pre-execution Blocking: Intercepts and blocks dangerous commands like rm -rf, git reset --hard, and git push --force before they run.
  • Modular Security Packs: Supports granular control over blocked commands via configurable packs (e.g., git, database, Kubernetes, cloud).
  • Use Case: When an AI agent attempts to run rm -rf / or git reset --hard HEAD~5, this Skill will block the command, providing a clear explanation and preventing accidental data destruction.

Quick Start

Configure the destructive-command-guard skill to protect your terminal sessions from accidental data loss.

Dependency Matrix

Required Modules

None required

Components

references

💻 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: destructive-command-guard
Download link: https://github.com/oakoss/agent-skills/archive/main.zip#destructive-command-guard

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.