careful

Detect destructive Bash commands and prompt for confirmation before execution.

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

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Safety guardrails prevent destructive commands from causing data loss by warning before executing risky operations and requiring explicit confirmation. This is essential for working in prod, debugging live systems, or shared environments where mistakes can have outsized impact.

Core Features & Use Cases

  • Pre-execution warnings for dangerous commands in Bash workflows.
  • Configurable prompts with overrides to proceed when safe and intentional.
  • Safe-guarded workflows for maintenance windows, debugging sessions, and collaboration in shared environments.

Quick Start

Enable safety mode by running the /careful command before executing risky operations.

Frequently Asked Questions about careful

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I add a safety prompt before running destructive bash commands?

To add a safety prompt before running destructive bash commands, use a PreToolUse hook that detects destructive patterns like rm -rf and requires explicit confirmation before execution.

Can I get a warning before executing git reset hard or kubectl delete?

Yes, you can get a warning before executing git reset --hard or kubectl delete by enabling a shell workflow guard that detects destructive commands and prompts for confirmation.

Does the destructive command guard block normal build artifact cleanup?

No, the destructive command guard does not block normal build artifact cleanup because it includes safe exceptions for common build artifacts to avoid interrupting standard workflows.

What is the best way to prevent accidental data loss in shared environments?

The best way to prevent accidental data loss in shared environments is implementing pre-execution safety guardrails that warn before risky operations and require configurable prompts to proceed.

How do I override the safety warning when I intentionally run a risky command?

You can override the safety warning when intentionally running a risky command by using the configurable prompt overrides to proceed when the operation is safe and intentional.