careful

Detect destructive Bash commands and prompt for confirmation before execution.

Updated Mar 27, 2026
One-click install
npx skills add https://github.com/AlejandroFigini/artist-portfolio --skill careful-alejandrofigini
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: careful
Source: https://github.com/AlejandroFigini/artist-portfolio/tree/main/.agent/skills/careful
Command: npx skills add https://github.com/AlejandroFigini/artist-portfolio --skill careful-alejandrofigini

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires python3.

What problem does it solve?

Safety guardrails for destructive commands to prevent accidental data loss across Bash environments and collaborative workflows.

Core Features & Use Cases

  • Pre-tool-use pattern matching to detect dangerous commands such as rm -rf, git reset --hard, and kubectl delete.
  • User override capability with explicit warnings to maintain workflow flexibility but preserve safety.
  • Automatic logging of usage context for auditing while avoiding exposure of sensitive content.

Quick Start

Install and enable the PreToolUse hook so destructive commands are warned before execution.

Frequently Asked Questions about careful

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

FAQPage Schema
How do I prevent accidental data loss from destructive Bash commands?

Preventing accidental data loss from destructive Bash commands requires pre-tool-use hooks that scan operations like rm -rf, prompt for confirmation, and enforce safety patterns before execution proceeds.

Can I add safety guardrails for git reset --hard and kubectl delete?

Safety guardrails can detect dangerous operations including git reset --hard and kubectl delete by implementing pre-tool-use pattern matching that warns users and requires explicit confirmation before proceeding.

What is a pre-tool-use hook for warning against destructive commands?

A pre-tool-use hook for destructive commands is an interception mechanism that scans Bash operations against safety patterns, prompts for user override with explicit warnings, and logs usage context for auditing.

Do I need python3 to enable Bash command warnings in shared environments?

Yes, python3 is required as a dependency to run the pre-tool-use hooks that scan for destructive Bash commands and enforce safety guardrails in shared production computing environments.

How do I override destructive command warnings when I need to proceed?

You can override destructive command warnings through explicit user confirmation prompts, which maintain workflow flexibility while preserving safety and logging the usage context for auditing purposes.

What are the limitations of pattern matching for dangerous Bash operations?

Pattern matching for dangerous Bash operations is limited to detecting known destructive syntax like rm -rf or git reset --hard, meaning novel or obfuscated destructive commands may bypass the predefined safety patterns.