careful

Scan Bash commands for destructive operations and prompt before execution.

2|Updated Apr 4, 2026
One-click install
npx skills add https://github.com/adityasingh2400/SwarmSell --skill careful-adityasingh2400
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: careful
Source: https://github.com/adityasingh2400/SwarmSell/tree/main/.claude/skills/careful
Command: npx skills add https://github.com/adityasingh2400/SwarmSell --skill careful-adityasingh2400

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 safety prompts before executing destructive Bash commands.
  • Allows user overrides to proceed after conscious confirmation.
  • Suitable for development, staging, and production debugging where safety and audibility matter.

Quick Start

Enable safety mode and prompt before every 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 accidental execution of destructive bash commands like rm -rf or git reset --hard?

To prevent destructive bash commands from executing accidentally, you can enforce shell guardrails that scan operations like rm -rf or git reset --hard before execution and prompt for confirmation. This safety hook intercepts commands and records usage metadata for audit.

Can I override safety prompts when running destructive shell commands in production?

Yes, you can override safety prompts for destructive shell commands in production environments. The guardrails support overridable prompts, allowing you to consciously confirm and proceed with operations like DROP TABLE or kubectl delete after the initial warning.

Does this safety guardrail work for staging and development environments?

Yes, the safety guardrail applies during shell usage in development, staging, and production environments. It supports Bash workflows across all stages, ensuring destructive operations require confirmation regardless of the deployment tier.

How do I enable a careful mode for debugging live systems?

To enable careful mode for debugging live systems, activate the safety hook to scan commands before execution. It automatically triggers when asked to enter safety mode, prod mode, or careful mode, warning before potentially destructive operations.

What bash commands are caught by destructive command guardrails?

Destructive command guardrails catch operations such as rm -rf, DROP TABLE, force-push, git reset --hard, and kubectl delete. The safety hook scans Bash workflows before execution, warns the user, and records usage metadata for audit purposes.

What is the best way to add safety prompts for shared environment shell usage?

The best way to add safety prompts for shared environment shell usage is implementing an overridable safety hook. It scans commands before execution, warns about destructive operations, and records usage metadata, ensuring audibility when working in shared spaces.