careful

Flags dangerous commands in popular CLIs and asks for confirmation before executing them.

Updated Mar 30, 2026
One-click install
npx skills add https://github.com/nhattran998/personal-athlete-agent --skill careful-nhattran998
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: careful
Source: https://github.com/nhattran998/personal-athlete-agent/tree/main/.agents/skills/gstack-careful
Command: npx skills add https://github.com/nhattran998/personal-athlete-agent --skill careful-nhattran998

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". (gstack)

Core Features & Use Cases

  • Provides proactive warnings and optional confirmations before executing dangerous commands across shells and deployment tools.
  • Allows configurable override with a user-accessible risk threshold and audit trail.
  • Ideal for production maintenance, debugging in shared environments, and safeguarding critical systems.

Quick Start

Activate careful mode and begin operations with the system warning prior to any destructive command.

Frequently Asked Questions about careful

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I add safety prompts to prevent destructive bash commands from executing?

Safety prompts intercept destructive bash commands like rm -rf, warning you before execution and requiring explicit confirmation to proceed or abort the operation.

Can I get a warning before running git reset --hard or force-push?

Yes, warnings trigger before destructive git operations such as force-push and git reset --hard, prompting you to confirm or abort the command execution.

Does this safety guardrail work with kubectl delete commands in Kubernetes?

Yes, the guardrail limits scope to common tools including Kubernetes, warning you before executing kubectl delete operations and providing a clear confirm or abort decision path.

What is the best way to safeguard production environments during debugging?

Safeguard production environments by activating careful mode, which proactively warns and requests confirmation before executing dangerous commands across shells and deployment tools.

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

Yes, you can override each warning using a user-accessible risk threshold, allowing you to proceed with destructive operations while maintaining an audit trail for safety.

When do I need safety prompts for destructive operations in a shared environment?

Use safety prompts when touching production, debugging live systems, or working in shared environments to prevent accidental data loss from destructive shell, git, or docker commands.