careful

Audit bash commands for destructive patterns before execution.

Updated Jun 4, 2026
One-click install
npx skills add https://github.com/burgebj/gstack --skill careful-burgebj
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: careful
Source: https://github.com/burgebj/gstack/tree/main/careful
Command: npx skills add https://github.com/burgebj/gstack --skill careful-burgebj

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) components.

What problem does it solve?

Ensures safe operation in environments where destructive commands can cause harm. It acts as a guardrail to prevent accidental data loss and system damage.

Core Features & Use Cases

  • Command Auditing: Scans bash commands for potentially destructive patterns before execution.
  • Destructive Pattern Checks: Identifies patterns like rm -rf, DROP TABLE, and git reset --hard.
  • Custom Exceptions: Allows exceptions for patterns like rm -rf node_modules for common, non-destructive use cases.
  • User Warning & Decision: Alerts users and gives them the choice to proceed or cancel the destructive action.

Quick Start

Set 'be careful' to activate the protective mode before executing critical commands.

Frequently Asked Questions about careful

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

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

A command auditing guardrail scans bash commands for destructive patterns like rm -rf before execution, alerting you to prevent accidental data loss or system crashes.

What is the best way to add safety pre-checks for git reset --hard in production environments?

Implementing a command auditing pre-check intercepts destructive patterns like git reset --hard in production environments, requiring explicit user confirmation to prevent system damage.

Can I set custom exceptions for specific destructive command patterns?

Yes, you can configure custom exceptions to whitelist specific destructive command patterns, allowing safe operations like 'rm -rf node_modules' to execute without triggering the warning prompt.

How does command auditing handle SQL DROP TABLE statements?

Command auditing identifies SQL DROP TABLE statements as destructive patterns during the pre-execution scan, warning the user and providing the choice to cancel the action.

Do I need any dependencies to run command execution guardrails?

No, you do not need any dependencies to run these command execution guardrails, as the protective script operates independently without requiring external modules.

When should I not use a command execution guardrail?

You should not use a command execution guardrail when running fully automated, non-interactive scripts where pausing for user confirmation would cause the automation pipeline to hang or fail.