careful

Detect destructive shell commands and warn before execution.

Updated Mar 26, 2026
One-click install
npx skills add https://github.com/FxHollow/100000mrr-landing --skill careful-fxhollow
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: careful
Source: https://github.com/FxHollow/100000mrr-landing/tree/main/.agents/skills/gstack/careful
Command: npx skills add https://github.com/FxHollow/100000mrr-landing --skill careful-fxhollow

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

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".

Core Features & Use Cases

  • Provides pre-execution checks for destructive commands across common tooling (bash, Git, Kubernetes, Docker).
  • Allows user override with explicit confirmation to preserve productivity in safe contexts.
  • Records usage analytics and prompts with guidance when risks are detected.

Quick Start

Enable careful mode and confirm the warning prompt before executing any destructive command.

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 using pattern-based pre-execution checks that detect operations like rm -rf, DROP TABLE, and git reset --hard. The system warns you before execution and requires explicit confirmation to override the warning in shared environments.

Can I add safety guardrails for kubectl delete and Docker operations in production?

Yes, safety guardrails can be added for kubectl delete and Docker operations in production. The system implements pre-execution checks across Bash, Git, Kubernetes, and Docker workflows, prompting you with risk guidance and requiring confirmation before proceeding.

How do destructive command warning prompts handle build artifacts during execution?

Destructive command warning prompts handle build artifacts by applying safe exceptions for common build artifacts. This pattern-based detection mechanism prevents unnecessary warnings during standard builds while still guarding actual risky operations with an override prompt.

What is the best way to warn before executing risky Git commands like force-push?

The best way to warn before executing risky Git commands like force-push is to use a pretooluse detection mechanism. It intercepts the command, records usage analytics, and prompts you with guidance to confirm the override before the operation proceeds.

Does the destructive command safety mode work without additional dependencies?

Yes, the destructive command safety mode works without additional dependencies. It functions independently to intercept and warn on risky operations across Bash, Git, Kubernetes, and Docker, allowing you to enable careful mode directly.

When should I not use a destructive command guard?

You should not use a destructive command guard when you are working in an isolated local environment where rapid execution is prioritized over safety. In these contexts, the confirmation prompts for operations like rm -rf may interrupt workflow productivity without providing necessary safety benefits.