careful

Validate shell commands for destructive patterns before execution.

Updated Apr 5, 2026
One-click install
npx skills add https://github.com/bizzybae/qstack --skill careful-bizzybae
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: careful
Source: https://github.com/bizzybae/qstack/tree/main/gstack-original/careful
Command: npx skills add https://github.com/bizzybae/qstack --skill careful-bizzybae

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Protects your workflow by warning before executing destructive commands such as rm -rf, git reset --hard, or kubectl delete, preventing accidental data loss in shared environments.

Core Features & Use Cases

  • Destructive command detection: flags and warns before execution to prevent accidental data loss.
  • Safety mode: validates each command for risky patterns across shells and environments.
  • Override capability: allows trusted users to proceed after confirmation.

Quick Start

Enable careful mode to warn before executing any destructive 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 data loss from destructive shell commands in CI pipelines?

Preventing accidental data loss from destructive shell commands requires pre-execution validation. This warns before executing risky patterns like rm -rf, git reset --hard, or kubectl delete in local development, CI pipelines, and shared environments.

How can I add guardrails to block destructive bash commands like rm -rf?

Adding guardrails to block destructive bash commands involves enabling a safety mode that validates each command for risky patterns. It checks against destructive operations and prompts for confirmation before allowing execution to proceed.

Can I override the safety warning when executing destructive shell actions?

Yes, you can override the safety warning when executing destructive shell actions. The override capability allows trusted users to proceed with the command after confirming the warning prompt, ensuring flexibility when intentionally running operations like kubectl delete.

Does this destructive command detection work across different shell environments?

Yes, destructive command detection works across different shell environments. Safety mode validates each command for risky patterns across shells, local development setups, and shared environments to consistently prevent accidental data loss.

What is the best way to warn before executing destructive git reset or kubectl delete commands?

The best way to warn before executing destructive git reset or kubectl delete commands is pre-execution validation. It flags and warns before execution to prevent accidental data loss, with an option to override for trusted users.