careful

Detect and warn on destructive shell commands before execution.

Updated Mar 27, 2026
One-click install
npx skills add https://github.com/Jesse-L-M/scz-target-engine --skill careful-jesse-l-m
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: careful
Source: https://github.com/Jesse-L-M/scz-target-engine/tree/main/.claude/skills/gstack/careful
Command: npx skills add https://github.com/Jesse-L-M/scz-target-engine --skill careful-jesse-l-m

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

It provides safety guardrails that detect and warn before destructive commands, reducing the risk of accidental data loss in shell and production environments.

Core Features & Use Cases

  • Warns before operations like rm -rf, git push --force, kubectl delete, or git reset --hard.
  • Allows user override to proceed after a warning, enabling safe debugging in shared environments.
  • Logs usage to help teams audit and improve safety practices.

Quick Start

Enable careful mode to have every Bash command checked for destructive patterns before execution.

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 shell commands like rm -rf?

You can prevent accidental data loss by enabling prechecks that scan for destructive shell commands before execution. The system detects patterns like rm -rf and git reset --hard, warning you before any action proceeds.

What shell commands are considered destructive and require a pre-run check?

Destructive shell commands requiring a pre-run check include rm -rf, DROP TABLE, git reset --hard, git push --force, and kubectl delete. These patterns are flagged to prevent irreversible data loss in production environments.

Can I override the safety warning if I need to run a risky command during debugging?

Yes, you can override the safety warning to proceed with a risky command during debugging. The precheck system allows user override so you can execute necessary changes while still logging the usage for team audits.

Does this precheck tool work for automated shell workflows or only interactive sessions?

This precheck tool works for both automated shell workflows and interactive sessions. It enforces pre-run checks for destructive patterns across production environments, ensuring safety during automated changes and manual debugging.

How do I audit team usage of destructive commands in a shared environment?

To audit team usage of destructive commands in a shared environment, you can review the usage logs generated by the precheck guardrails. These logs track when risky patterns are detected and overridden, helping improve safety practices.