careful

Scan Bash commands for destructive patterns and prompt before execution.

2|Updated May 8, 2026
One-click install
npx skills add https://github.com/xotong/claude-marketplace --skill careful-xotong
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: careful
Source: https://github.com/xotong/claude-marketplace/tree/main/plugins/gstack/skills/careful
Command: npx skills add https://github.com/xotong/claude-marketplace --skill careful-xotong

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Safeguards your shell by warning before executing destructive commands such as rm -rf, git reset --hard, kubectl delete, and similar risky actions, helping prevent data loss in shared or production environments.

Core Features & Use Cases

  • Provides guardrails for destructive commands with optional overrides.
  • Logs usage analytics to help teams monitor risky actions.
  • Operates across Bash workflows and collaborative development setups.

Quick Start

Enable careful mode in your shell to start receiving warnings before executing dangerous commands.

Frequently Asked Questions about careful

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

FAQPage Schema
How do I prevent destructive shell commands like rm -rf from executing accidentally?

To prevent destructive shell commands from executing accidentally, you can use a PreToolUse Bash hook that scans commands for risky patterns and prompts you for confirmation before execution.

Can I add guardrails to warn before running git reset --hard or kubectl delete?

Yes, you can add guardrails that intercept Bash workflows to warn before running commands like git reset --hard or kubectl delete, providing optional overrides for confirmed actions.

How does command safety monitoring work in shared development environments?

Command safety monitoring in shared development environments works by implementing a PreToolUse hook that scans shell commands for destructive patterns, prompting users before execution and logging usage analytics.

What is the best way to safeguard production environments against risky shell actions?

The best way to safeguard production environments against risky shell actions is enabling a Bash hook that warns before executing destructive commands, preventing data loss through confirmation prompts.

Do I need to configure anything to start receiving warnings for destructive commands?

You simply need to enable careful mode in your shell to start receiving warnings for destructive commands, requiring no additional dependencies or complex environment setup to activate the guardrails.

Can I override the confirmation prompt when a destructive command warning is triggered?

Yes, you can override the confirmation prompt when a destructive command warning is triggered, as the guardrails provide optional overrides to allow execution of risky actions after explicit user confirmation.