careful

Intercept destructive shell and deployment commands for confirmation before execution.

46|13|Updated Jul 30, 2025
One-click install
npx skills add https://github.com/aimasteracc/tree-sitter-analyzer --skill careful-aimasteracc
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: careful
Source: https://github.com/aimasteracc/tree-sitter-analyzer/tree/main/.claude/skills/careful
Command: npx skills add https://github.com/aimasteracc/tree-sitter-analyzer --skill careful-aimasteracc

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Safety guardrails for destructive commands prevent accidental data loss and production outages by warning before dangerous operations.

Core Features & Use Cases

  • Real-time warnings for destructive commands such as rm -rf, git reset --hard, kubectl delete, and SQL DROP/TRUNCATE.
  • User-overridable warnings and safety modes for critical environments (prod, shared systems).
  • Hooks into CLI workflows to intercept commands before execution and prompt for confirmation.

Quick Start

Enable careful mode to prompt 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 prompts to prevent destructive bash commands from running?

You can add safety prompts for destructive bash commands by implementing runtime guardrails via a PreToolUse hook. This intercepts commands before execution, warning you before operations like rm -rf or git reset --hard can cause data loss.

Can I intercept kubectl delete commands before they execute in a production environment?

Yes, you can intercept kubectl delete commands before execution in production. The hook applies across development, staging, and production workflows, prompting for confirmation before running unsafe deployment commands that could cause outages.

How do runtime guardrails stop accidental data loss from SQL DROP or TRUNCATE statements?

Runtime guardrails stop accidental data loss from SQL DROP or TRUNCATE statements by hooking into CLI workflows. The system detects these destructive commands and prompts the user for explicit confirmation before allowing the operation to proceed.

Do I need special configuration to enable confirmation prompts for dangerous shell commands?

No special configuration is required to enable confirmation prompts for dangerous shell commands. The guardrails work immediately from the frontmatter, though you can apply optional overrides in SKILL.md to customize safety modes for critical shared environments.

Can I override the safety warnings for destructive commands in my staging workflow?

Yes, you can override safety warnings for destructive commands in staging workflows. The system allows user-overridable warnings and configurable safety modes, so you can adjust the interception behavior based on your specific environment requirements.