careful

Intercept and validate shell commands against destructive patterns before execution.

Updated Jul 26, 2026
One-click install
npx skills add https://github.com/yocxy2/gstack3 --skill careful-yocxy2
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: careful
Source: https://github.com/yocxy2/gstack3/tree/main/careful
Command: npx skills add https://github.com/yocxy2/gstack3 --skill careful-yocxy2

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires python3, and includes scripts (resource) components.

What problem does it solve?

This Skill prevents accidental execution of high-risk commands that could lead to data loss, system instability, or production downtime.

Core Features & Use Cases

  • Destructive Command Detection: Automatically intercepts commands like rm -rf, DROP TABLE, and git push --force before they execute.
  • Context-Aware Safety: Provides a warning prompt for dangerous operations while allowing safe exceptions for common build artifacts.
  • Use Case: When working in a production environment or a shared repository, this skill acts as a safety net, ensuring you confirm any command that could permanently delete files or rewrite history.

Quick Start

Enable safety mode by telling the assistant to be careful before you start running potentially destructive shell 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 shell commands like rm -rf?

You can prevent accidental execution of destructive shell commands by using a pre-execution hook that intercepts and validates bash commands against a list of destructive patterns to block operations like recursive deletions before they run.

What commands are intercepted by a bash safety guardrail?

A bash safety guardrail intercepts high-risk commands by pattern matching against operations like recursive deletions, database drops such as DROP TABLE, and forced git operations like git push --force to prevent accidental data loss.

How do I add safety guardrails for git push --force in a shared repository?

To add safety guardrails for git push --force in a shared repository, enable a pre-execution hook that validates commands against destructive patterns and provides a warning prompt to confirm any command that could rewrite history.

Does the careful skill require Python3 to block database drop operations?

Yes, the careful skill requires Python3 as a dependency to run its scripts that intercept and validate shell commands, blocking database drops and other destructive operations in sensitive environments.

Can I use command interception for risk management on production servers?

Yes, you can use command interception for risk management on production servers by operating a pre-execution hook that validates bash commands against destructive patterns, ensuring you confirm any operation that could cause production downtime.

Are there limitations to context-aware safety when blocking destructive bash commands?

Context-aware safety for blocking destructive bash commands provides warning prompts for dangerous operations while allowing safe exceptions for common build artifacts, but requires pattern matching logic to accurately identify risks without blocking safe commands.