careful

Warn before executing destructive shell, Git, and Kubernetes commands.

1|Updated Nov 13, 2025
One-click install
npx skills add https://github.com/concept2cure/ClinicalSageAI-2-replit --skill careful-concept2cure
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: careful
Source: https://github.com/concept2cure/ClinicalSageAI-2-replit/tree/main/.claude/skills/gstack/careful
Command: npx skills add https://github.com/concept2cure/ClinicalSageAI-2-replit --skill careful-concept2cure

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires git, python3.

What problem does it solve?

This Skill provides safety guardrails for destructive commands, warning before actions like rm -rf, DROP TABLE, git reset --hard, kubectl delete, and similar operations. Users can override each warning when they are sure the action is safe.

Core Features & Use Cases

  • Pre-execution checks for dangerous commands across Bash, Git, and Kubernetes workflows.
  • Configurable prompts that let trusted users proceed or cancel, reducing accidental data loss.
  • Suitable for prod and development environments, CI pipelines, and shared machines where safety is critical.

Quick Start

Be sure to enable careful mode before running any potentially 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 data loss from destructive bash commands?

Preventing accidental data loss from destructive bash commands requires pre-execution safety checks that identify high-risk actions like rm -rf and warn you before they run. This Skill provides configurable guardrails that prompt you to proceed or cancel.

Can I get a warning before running git reset hard or kubectl delete?

Yes, you can get warnings before running git reset hard or kubectl delete by using pre-execution checks. This Skill detects dangerous version control and container cleanup operations, issuing a configurable override prompt to confirm before execution.

How do I add safety guardrails for destructive commands in a CI pipeline?

Adding safety guardrails for destructive commands in a CI pipeline involves applying pre-checks to high-risk shell operations. This Skill enforces safety by intercepting dangerous commands and requiring configurable override prompts, making it suitable for automated and shared environments.

Does this destructive command warning system require any specific dependencies?

Yes, the destructive command warning system requires git and python3 as dependencies. You need these installed in your development or production environment to enable the pre-execution checks and override prompts.

Can trusted users override the warning when running dangerous shell operations?

Yes, trusted users can override the warning when running dangerous shell operations. The guardrails issue a configurable prompt for each detected destructive command, allowing you to explicitly proceed when you are sure the action is safe.

What is the best way to intercept and block destructive commands in production environments?

The best way to intercept and block destructive commands in production environments is implementing pre-execution checks with override capabilities. This Skill identifies high-risk actions across bash and version control workflows, warning before execution to prevent accidental data loss.