careful

Detect destructive bash commands and prompt before execution.

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

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires python3, git.

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 implementation that inspects Bash commands and prompts before execution.
  • Detects destructive patterns such as rm -rf, git reset --hard, git push --force, kubectl delete, and SQL drops in appropriate contexts.
  • Logs usage analytics locally to ~/.gstack/analytics to help teams monitor dangerous actions.

Quick Start

Enable careful mode in your workflow and proceed only after 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 prompts to prevent destructive bash commands like rm -rf from executing accidentally?

Safety prompts intercept destructive bash commands by implementing a pretool hook that inspects operations like rm -rf, prompting the user for permission before execution to prevent accidental data loss.

Does this safety guardrail protect against git push --force and git reset --hard in shared environments?

Yes, the guardrail detects git push --force and git reset --hard operations, prompting the user before execution to prevent accidental data loss in shared or production environments.

How does command safety analysis handle kubectl delete and SQL drops in production contexts?

Command safety analysis inspects kubectl delete and SQL drop operations in production or shared environments, returning a permission decision and prompting the user before destructive execution occurs.

Do I need python3 and git installed to use bash command guardrails?

Yes, python3 and git are required dependencies for implementing the pretool hook that analyzes bash commands, returns permission decisions, and logs usage locally for audit purposes.

Can I override the warning prompt when running destructive bash commands intentionally?

Yes, users can override each warning prompt individually, allowing intentional destructive operations while maintaining safety guardrails for accidental command execution prevention.

Where does the destructive command guardrail log usage analytics for audit purposes?

The guardrail logs usage analytics locally to the ~/.gstack/analytics directory, helping teams monitor dangerous actions and maintain an audit trail of destructive command executions.