careful

Detect destructive shell commands and require confirmation before execution.

Updated Aug 23, 2026
One-click install
npx skills add https://github.com/JonOlsenCa/gstack-main --skill careful-jonolsenca
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: careful
Source: https://github.com/JonOlsenCa/gstack-main/tree/main/careful
Command: npx skills add https://github.com/JonOlsenCa/gstack-main --skill careful-jonolsenca

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Safety guardrails for destructive commands warn before execution of dangerous operations such as rm -rf, kubectl delete, git reset --hard, and similar destructive actions. This reduces the risk of accidental data loss or production impact, especially when working in shared environments or debugging live systems. Users can override each warning when they explicitly intend to proceed.

Core Features & Use Cases

  • Destructive command detection and warning for dangerous operations (rm -rf, git reset --hard, kubectl delete, etc.)
  • Safe override controls to proceed when necessary
  • Audit logging of warning events for context and accountability
  • PreToolUse hook integration to enforce safety before tool execution

Quick Start

Enable careful mode and run a potentially destructive command; you will receive a warning and can choose 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 a warning before destructive bash commands run?

To add a warning before destructive bash commands, a pre-execution hook scans shell input for dangerous patterns like rm -rf and requires explicit user confirmation to proceed or cancel.

What destructive commands should I protect against in production environments?

Destructive commands to protect against include rm -rf, kubectl delete, and git reset --hard. This Skill detects these dangerous operations and warns before execution to prevent accidental data loss.

Can I override the safety warning when I intentionally need to run a dangerous shell command?

Yes, you can override the safety warning when intentionally running a dangerous shell command. The guardrails provide safe override controls allowing you to proceed with execution when necessary.

Does this destructive command guardrail work for live debugging scenarios?

Yes, this destructive command guardrail works for live debugging scenarios. It applies to production environments, shared workspaces, and live debugging where destructive actions could impact users.

How do I track when destructive command warnings are triggered in a shared workspace?

To track destructive command warnings in a shared workspace, this Skill provides audit logging of warning events. This logging delivers context and accountability for all safety guardrail triggers.