careful

Detect destructive commands in Bash and other tools before execution.

Updated Mar 20, 2026
One-click install
npx skills add https://github.com/rmarino550/gstack --skill careful-rmarino550
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: careful
Source: https://github.com/rmarino550/gstack/tree/main/careful
Command: npx skills add https://github.com/rmarino550/gstack --skill careful-rmarino550

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) components.

What problem does it solve?

This Skill acts as a safety guardrail, warning users before executing potentially destructive commands like rm -rf, DROP TABLE, git reset --hard, and more, to prevent accidental data loss or system damage.

Core Features & Use Cases

  • Destructive Command Detection: Monitors and warns for commands that can cause irreversible damage.
  • User Override: Allows users to override warnings if they are certain of their actions.
  • Use Case: Ideal for use in production environments, when debugging live systems, or in shared environments where destructive actions can impact multiple users.

Quick Start

Activate the careful skill and proceed with your command. If a destructive command is detected, you will receive a warning.

Frequently Asked Questions about careful

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I prevent accidental destructive bash commands like rm -rf?

To prevent accidental destructive bash commands, you need a safety guardrail that monitors command execution and warns before running commands like rm -rf. This skill detects destructive patterns and prompts an override warning.

Does git reset --hard warning work with this bash safety tool?

Yes, bash safety guardrails include detection for git reset --hard. The tool monitors command inputs and triggers a warning before execution, allowing you to cancel or override the destructive git action.

What is the best way to add guardrails for destructive commands in a shared environment?

Adding command checking guardrails is the best way to secure shared environments. This skill monitors administrative and development workflows, warning users before executing irreversible commands like DROP TABLE or rm -rf.

Can I override the safety warning if I am certain I need to run a destructive command?

Yes, you can override the safety warning. When the command checker detects a destructive action, it issues a warning but allows users to proceed if they are certain of their actions and wish to bypass the guardrail.

How does command checking work for administrative workflows?

Command checking for administrative workflows works via script execution and command matching. The skill monitors your bash inputs against a list of destructive patterns and intercepts them with a warning before system damage occurs.

Are there limitations to using script execution for command matching in bash?

The primary limitation of script-based command matching is that it requires script execution to intercept commands. It specifically targets recognized destructive patterns, meaning highly obscure or custom destructive commands might not trigger the warning.