careful

Warn before destructive shell and deployment commands to prevent data loss.

Updated Apr 24, 2026
One-click install
npx skills add https://github.com/SakshamKandel/Salt-Route-Consulting- --skill careful-sakshamkandel
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: careful
Source: https://github.com/SakshamKandel/Salt-Route-Consulting-/tree/main/.agents/skills/careful
Command: npx skills add https://github.com/SakshamKandel/Salt-Route-Consulting- --skill careful-sakshamkandel

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Safety guardrails for destructive commands prevent accidental data loss by warning users before executing dangerous actions.

Core Features & Use Cases

  • Warn before destructive actions such as rm -rf, DROP TABLE, git reset --hard, kubectl delete, and similar operations.
  • Allow user override with explicit confirmation while logging usage for auditing.
  • Improve safety in prod, staging, or shared environments by reducing the risk of unintended changes.

Quick Start

Enable safety mode by invoking the skill before performing a destructive command to receive a warning and the option to proceed or cancel.

Frequently Asked Questions about careful

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

FAQPage Schema
How do I add warnings before running destructive shell commands like rm -rf?

To add warnings before destructive shell commands, you can use a safety hook that intercepts command input and prompts for confirmation. This prevents accidental data loss by requiring explicit user override before executing actions like rm -rf.

Can I get a warning prompt before executing git reset --hard or kubectl delete?

Yes, you can receive warning prompts before executing git reset --hard or kubectl delete by enabling a safety mode. This mode intercepts dangerous deployment operations, prints warnings, supports user overrides, and records usage analytics for auditing.

What is the best way to prevent accidental data loss in production environments?

The best way to prevent accidental data loss in production environments is to implement guardrails that intercept destructive actions. By warning users and requiring explicit confirmation before executing dangerous commands, you reduce the risk of unintended changes.

Does this safety mode allow me to override the destructive command warning?

Yes, the safety mode allows you to override the destructive command warning. You can proceed with the execution by providing explicit confirmation, while the system logs the usage analytics to maintain an audit trail of the override.

How do I enable safety mode for destructive bash and deployment operations?

To enable safety mode for destructive bash and deployment operations, invoke the safety skill before performing a dangerous command. This activates a hook that prints warnings and gives you the option to proceed or cancel the action.

What types of destructive commands are intercepted by safety guardrails?

Safety guardrails intercept a wide range of destructive commands including rm -rf, DROP TABLE, git reset --hard, and kubectl delete. These commands are targeted across development, staging, and production environments to prevent unintended data loss.