careful

Prompt for confirmation before destructive commands via a PreToolUse Bash hook.

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

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) components.

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

  • Issues a warning and requires explicit confirmation before risky commands.
  • Allows per-command overrides to maintain workflow flexibility while reducing risk.
  • Suitable for development, staging, and production environments where destructive operations could impact others.

Quick Start

Enable careful mode in your workflow and run a destructive command to receive an explicit warning before proceeding.

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 prompt before running destructive bash commands?

You can add a warning prompt before destructive bash commands by using a PreToolUse hook that analyzes operations like rm -rf or git reset --hard and requires explicit confirmation before executing them.

Can I override the safety warning for a specific command if I know it is safe?

Yes, you can override the safety warning on a per-command basis. The hook allows overrides to maintain workflow flexibility while reducing risk, prompting for confirmation but never permanently blocking execution.

Does this safety guardrail work for production kubectl delete operations?

Yes, the safety guardrail works for production kubectl delete operations. It applies to development, staging, and production workflows, warning you before any command that could cause data loss or downtime.

What destructive commands are intercepted by the bash prehook?

The bash prehook intercepts destructive commands such as rm -rf, DROP TABLE, force-push, git reset --hard, and kubectl delete. It analyzes the command pattern and returns a permission decision to ask for confirmation.

When should I enable careful mode for my deployment workflow?

You should enable careful mode when touching production, debugging live systems, or working in a shared environment. It provides safety guardrails to prevent accidental data loss or downtime from destructive operations.