careful

Detect and warn on high-risk destructive bash commands before execution.

Updated May 22, 2026
One-click install
npx skills add https://github.com/shekerkamma/peopletech-marketplace --skill careful-shekerkamma
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: careful
Source: https://github.com/shekerkamma/peopletech-marketplace/tree/main/plugins/gstack/careful
Command: npx skills add https://github.com/shekerkamma/peopletech-marketplace --skill careful-shekerkamma

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill eliminates the risk of accidental data loss, system damage, and production outages caused by unvetted destructive command execution, especially when working in live production environments, shared team workspaces, or debugging critical systems.

Core Features & Use Cases

  • Destructive Pattern Detection: Automatically flags high-risk operations including recursive file deletion, database drops, forced git pushes, hard git resets, and Kubernetes resource deletions.
  • Safe Exception Handling: Allows common non-destructive cleanup commands (such as removing node_modules, build artifacts, or cache directories) to run without unnecessary warnings.
  • Use Case: When performing a routine cleanup on a production server, the Skill warns you if your command matches a destructive pattern, preventing accidental deletion of critical user data or system files.

Quick Start

Activate the careful skill before running any bash commands in production or shared environments to receive automatic warnings for destructive operations.

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 in production?

You can block unapproved destructive git commands by using a safety guardrail that detects forced pushes and hard resets before they execute. The Skill warns you when these destructive patterns match, preventing unintended repository damage.

What's the best way to add safety guardrails for Kubernetes resource deletion?

Adding safety guardrails for Kubernetes resource deletion requires a detection layer that identifies destructive command patterns prior to running them. This Skill intercepts these operations and issues warnings, ensuring you do not accidentally remove critical cluster resources.

Can I run routine cleanup commands like removing node_modules without triggering destructive command warnings?

Yes, you can override safety warnings for destructive commands when operations are intentional. The Skill enables user override of its alerts, allowing approved destructive operations to proceed while still blocking unvetted high-risk patterns by default.

Does this safety mechanism work automatically for all bash command runs in shared environments?

Yes, the safety mechanism works automatically for all bash command runs in shared environments. It applies to live debugging and production workspaces, scanning commands for destructive patterns like recursive deletion and database drops before execution.