careful

Detect destructive Bash commands and prompt for confirmation before execution.

2|Updated Mar 16, 2026
One-click install
npx skills add https://github.com/OmerFarukOruc/symphony-orchestrator --skill careful-omerfarukoruc
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: careful
Source: https://github.com/OmerFarukOruc/symphony-orchestrator/tree/main/.claude/skills/gstack/careful
Command: npx skills add https://github.com/OmerFarukOruc/symphony-orchestrator --skill careful-omerfarukoruc

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

  • Warn-before-destructive-actions: detects dangerous Bash commands and prompts for confirmation.
  • Customizable guardrails: supports user overrides to proceed when necessary.
  • Safe production workflows: reduces risk when touching prod or debugging live systems.
  • Usage analytics: logs a lightweight usage event for auditing.

Quick Start

Enable careful mode before running potentially destructive Bash commands.

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 destructive Bash commands, use a PreToolUse hook that detects dangerous patterns like rm -rf or git reset --hard and prompts for confirmation. It logs activity and allows user overrides to proceed when necessary.

How can I prevent accidental data loss when debugging live systems in production?

Preventing accidental data loss in production environments involves enabling safety guardrails that warn before executing destructive operations. The system detects commands like DROP TABLE or kubectl delete, logs the attempt, and requires explicit user confirmation to proceed.

Can I override the warning prompt if I need to force a destructive command to run?

Yes, you can override the warning prompt for destructive commands. The safety guardrails are customizable and support user overrides, allowing you to bypass the confirmation and proceed with executing the flagged Bash command when necessary.

Does this safety guardrail work with specific dangerous commands like git force-push?

Yes, the safety guardrail works with specific dangerous commands including git force-push, rm -rf, DROP TABLE, git reset --hard, and kubectl delete. It uses Bash pattern checks to detect these operations and intercept them before execution.

What are the limitations of using Bash pattern checks for command safety?

A key limitation of using Bash pattern checks for command safety is that it specifically intercepts Bash commands at execution. It relies on predefined destructive patterns, meaning unrecognized novel destructive operations might not trigger the confirmation prompt.

When do I need to enable safety mode for shared environment workflows?

You need to enable safety mode for shared environment workflows when touching production, debugging live systems, or running potentially destructive Bash commands. This activates the PreToolUse hook to intercept dangerous operations and log usage events for auditing.