careful

Validate and warn before executing destructive shell commands with user override.

5|1|Updated Apr 5, 2026
One-click install
npx skills add https://github.com/forbotsake/forbotsake --skill careful-forbotsake
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: careful
Source: https://github.com/forbotsake/forbotsake/tree/main/.claude/skills/gstack/careful
Command: npx skills add https://github.com/forbotsake/forbotsake --skill careful-forbotsake

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Users risk catastrophic operations by running destructive commands on shared or production systems without guardrails.

Core Features & Use Cases

  • Pre-run warnings for risky commands (rm -rf, git reset --hard, kubectl delete)
  • User override to proceed after a warning
  • Logging and context capture for auditability

Quick Start

Enable careful mode and run your command as usual; before any destructive operation is executed, you will receive a warning and can choose to proceed or cancel.

Frequently Asked Questions about careful

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

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

To add safety guardrails for destructive bash commands, you can use a validation tool that intercepts risky shell operations and prompts a user override before execution. This prevents catastrophic actions in development, staging, or production environments.

What are pre-run warnings for shell commands and how do they work?

Pre-run warnings for shell commands work by validating your input against a list of destructive patterns like rm -rf or git reset --hard. If a match is found, the execution halts and requires explicit user override to proceed or cancel.

Can I override a destructive command warning if I am sure it is safe?

Yes, you can override a destructive command warning. When the pre-run check detects a risky operation, it halts execution and provides an interactive prompt allowing you to explicitly choose to proceed with the command or cancel it.

Does this destructive command protection work for staging and production environments?

Yes, this destructive command protection is applicable to development, staging, and production environments. It is specifically designed to halt or review risky actions wherever shared systems might be impacted by catastrophic operations.

How do I log shell commands for an audit trail after a warning override?

To log shell commands for an audit trail, the system automatically captures event logs and context whenever a destructive command warning is triggered and overridden. This ensures all risky actions are recorded for later review.