careful

Detect destructive shell commands and require confirmation before execution.

Updated Mar 22, 2026
One-click install
npx skills add https://github.com/jm199seo/lostark-accessory-viewer --skill careful-jm199seo
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: careful
Source: https://github.com/jm199seo/lostark-accessory-viewer/tree/main/.claude/skills/gstack/careful
Command: npx skills add https://github.com/jm199seo/lostark-accessory-viewer --skill careful-jm199seo

SYSTEM DOCUMENTATION & REQUIREMENTS

Safety guardrails for destructive commands. Warns before rm -rf, DROP TABLE, force-push, git reset --hard, kubectl delete, and similar destructive operations. User can override each warning. Use when touching prod, debugging live systems, or working in a shared environment. Use when asked to "be careful", "safety mode", "prod mode", or "careful mode".

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 running accidentally?

You can prevent destructive shell commands by using safety guardrails that detect risky patterns like rm -rf and require explicit confirmation before execution. This intercepts dangerous operations across development, staging, and production environments, warning you before any irreversible action runs.

What are safety guardrails for command risk and how do they work?

Safety guardrails for command risk work by detecting destructive shell patterns and returning a permission decision with a warning. They identify operations like DROP TABLE, git reset --hard, or kubectl delete, pausing execution to record usage analytics while enabling safe overrides.

Can I override the warning when a destructive command block triggers?

Yes, you can override the warning when a destructive command block triggers. The safety guardrails enable safe overrides for each specific warning, allowing you to bypass the permission decision and proceed with executing the risky command if you confirm the action is intentional.

Does this safety mode work with kubectl delete and git force-push operations?

Yes, safety mode works with kubectl delete and git force-push operations. It targets high-risk commands including git reset --hard, DROP TABLE, and rm -rf, warning you before these destructive operations execute in shared, staging, or production-like environments.

When should I use careful mode for bash command risk prevention?

You should use careful mode for bash command risk prevention when touching prod, debugging live systems, or working in shared environments. It activates safety guardrails to intercept destructive commands when operating in production-like or sensitive infrastructure contexts.

What commands does a destructive command warning system target?

A destructive command warning system targets commands like rm -rf, DROP TABLE, git reset --hard, git force-push, and kubectl delete. It detects these risky shell patterns across devops workflows to prevent irreversible data loss or infrastructure damage.