careful

Detect destructive Bash commands and prompt for confirmation before execution.

Updated Mar 31, 2026
One-click install
npx skills add https://github.com/hetsheth-droid/toolbox-template --skill careful-hetsheth-droid
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: careful
Source: https://github.com/hetsheth-droid/toolbox-template/tree/main/incubating/gstack/careful
Command: npx skills add https://github.com/hetsheth-droid/toolbox-template --skill careful-hetsheth-droid

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. (gstack)

Core Features & Use Cases

  • PreToolUse hook checks commands for destructive patterns and prompts for confirmation or cancellation.
  • Safe exceptions for known safe targets to prevent false positives.
  • Local analytics logging to ~/.gstack/analytics for usage auditing and improvement.

Quick Start

Activate careful mode and run a potentially destructive command to see the warning prompt.

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 for destructive bash commands like rm and git push force?

You can add safety warnings for destructive bash commands using a PreToolUse hook that pattern-matches commands like rm -rf or git push force and prompts for confirmation before execution.

Can I get a warning before running destructive kubectl delete or docker commands in production?

Yes, safety guardrails can intercept destructive kubectl delete or docker commands in production environments, prompting you for confirmation or cancellation before the operation executes.

How do I prevent false positives when blocking destructive shell commands?

You can prevent false positives by defining safe exceptions for known targets, ensuring the pattern matching only halts genuinely destructive shell commands while allowing safe operations to proceed.

What is the best way to guard against accidental git reset hard in CI/CD pipelines?

The best way to guard against accidental git reset hard in CI/CD pipelines is implementing a PreToolUse hook that detects destructive patterns and requires explicit user override to proceed.

Does this destructive command blocker work across different command-line tools?

Yes, the destructive command blocker works across multiple command-line tools including git, bash, kubectl, and docker, applying safety guardrails in development, CI/CD, and production contexts.

Can I track usage analytics when overriding destructive command warnings?

Yes, usage analytics are logged locally to ~/.gstack/analytics, providing an audit trail of when destructive command warnings are triggered and overridden for future review and improvement.