careful

Warn before executing destructive Bash, Git, kubectl, and SQL commands requiring confirmation.

Updated Mar 31, 2026

Search Tags:#bash #safety #guardrails #audit-logging #destructive-commands #warning #careful

Ready to run

npx skills add https://github.com/huichen/gstack --skill careful-huichen

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: careful
Source: https://github.com/huichen/gstack/tree/main/careful
Command: npx skills add https://github.com/huichen/gstack --skill careful-huichen

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Safety-critical operations often lead to catastrophic data loss or system downtime when destructive commands are executed accidentally in shared or production environments. This skill provides guardrails and warnings to prevent unintended deletions, and it allows explicit user overrides for controlled scenarios.

Core Features & Use Cases

Pre-run analysis of Bash commands for destructive patterns (e.g., rm -rf, git reset --hard, kubectl delete) and warning prompts.
Safe exceptions that allow common non-harmful targets to proceed without interruption.
Local usage logging for auditing and accountability during development and operations.

Quick Start

Describe the destructive operation you plan to run, and the skill will warn you before proceeding.

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 commands like rm -rf?▼

To add safety warnings before running destructive bash commands like rm -rf, you can use a guardrail skill that analyzes commands for destructive patterns and prompts for confirmation before execution. This prevents unintended data loss by intercepting operations like git reset --hard and kubectl delete.

Can I bypass the confirmation prompt for specific destructive commands when needed?▼

Yes, you can bypass the confirmation prompt for specific destructive commands. The safety guardrails allow explicit user overrides for controlled scenarios, and safe exceptions let common non-harmful targets proceed without interruption.

Does this destructive command guardrail work with git reset --hard and kubectl delete?▼

Yes, this destructive command guardrail works with git reset --hard and kubectl delete. It applies pre-run analysis and warning prompts across Bash and related tooling, including destructive SQL operations, to enforce safety checks before execution.

How do I log destructive bash commands for auditing during development?▼

To log destructive bash commands for auditing during development, this safety skill records interactions locally. It provides local usage logging for accountability, ensuring a traceable audit trail of warning prompts and override decisions during operations.

What are the limitations of using a bash command safety guardrail?▼

A limitation of using a bash command safety guardrail is that it requires user interaction for confirmation prompts, which may interrupt automated workflows. However, it respects user overrides to allow controlled situations where automated execution is necessary.