careful

Warn before destructive Bash commands like rm -rf and git reset --hard.

Updated Mar 24, 2026
One-click install
npx skills add https://github.com/pcaokhai/gradion-response-report-api --skill careful-pcaokhai
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: careful
Source: https://github.com/pcaokhai/gradion-response-report-api/tree/main/.claude/skills/gstack/careful
Command: npx skills add https://github.com/pcaokhai/gradion-response-report-api --skill careful-pcaokhai

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

  • Preemptive warnings for dangerous commands in Bash tools and scripts.
  • Allow override to proceed after confirmation, with optional logging.
  • Works across development, staging, and production workflows to prevent data loss.

Quick Start

Activate careful mode to warn before destructive commands and selectively override warnings as needed.

Frequently Asked Questions about careful

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

FAQPage Schema
How do I prevent accidental data loss from destructive bash commands like rm -rf?

Prevent accidental data loss from destructive bash commands by implementing a PreToolUse hook that intercepts operations like rm -rf, warns before execution, and allows a user override. It protects interactive shells and automation pipelines by blocking or warning on matches.

Can I get a warning prompt before running git reset --hard or kubectl delete in production?

Yes, you can get a warning prompt before running git reset --hard or kubectl delete in production by enabling careful mode. It interrogates dangerous commands in your development workflow, blocks them, and selectively allows you to override warnings after confirmation.

What is the best way to add safety guardrails to destructive commands in automation pipelines?

The best way to add safety guardrails to destructive commands in automation pipelines is to use a PreToolUse hook that interrogates bash commands, warns on destructive matches, and logs incidents. This approach prevents data loss across staging and production workflows.

Does careful mode block force-push and DROP TABLE operations or just warn the user?

Careful mode blocks force-push, DROP TABLE, and similar destructive operations by warning the user before execution. You can selectively override the warning to proceed with the command, while the system optionally logs the incident for review.

When do I need safety guardrails for destructive commands in a shared environment?

You need safety guardrails for destructive commands in a shared environment when touching prod, debugging live systems, or executing operations like git reset --hard. Implementing warning prompts prevents irreversible data loss across development, staging, and production workflows.