careful

Warn before executing destructive commands in shells, Git, and Kubernetes.

1|Updated May 4, 2026
One-click install
npx skills add https://github.com/sanskarbasnet/fstack --skill careful-sanskarbasnet
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: careful
Source: https://github.com/sanskarbasnet/fstack/tree/main/careful
Command: npx skills add https://github.com/sanskarbasnet/fstack --skill careful-sanskarbasnet

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. (fstack)

Core Features & Use Cases

  • Warns before destructive commands across Bash, Git, Kubernetes, and database operations.
  • Allows per-command overrides to proceed or cancel.
  • Integrates as a PreToolUse hook to guard tool executions and log activity.

Quick Start

Enable careful mode to receive warnings before destructive commands.

Frequently Asked Questions about careful

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

FAQPage Schema
How do I add safety warnings before running destructive bash and git commands?

You can add safety warnings before running destructive bash and git commands by using a PreToolUse hook that detects risky patterns like rm -rf and git reset --hard, prompting for approval before execution.

Can I block kubectl delete operations without disabling the command entirely?

Yes, you can block kubectl delete operations without disabling the command entirely by applying pattern-based detection that warns before execution while still allowing per-command overrides to proceed.

What is the best way to prevent accidental DROP TABLE and force-push actions in a shared environment?

The best way to prevent accidental DROP TABLE and force-push actions in a shared environment is to enable safety guardrails that intercept destructive operations and require explicit user approval before proceeding.

Does this safety hook support overriding warnings for specific destructive commands?

Yes, the safety hook supports overriding warnings for specific destructive commands, allowing you to choose whether to proceed or cancel each risky action on a per-command basis during your workflow.

When do I need pattern-based detection for risky shell operations?

You need pattern-based detection for risky shell operations when touching production, debugging live systems, or working in shared environments where accidental execution of commands like rm -rf could cause irreversible damage.

What are the limitations of using guardrails for destructive command detection?

The limitations of using guardrails for destructive command detection include relying on predefined patterns for commands like git reset --hard and kubectl delete, meaning unrecognized risky operations might not be intercepted unless explicitly configured.