careful

Detects risky Bash commands and prompts for confirmation before execution.

1|Updated Mar 1, 2026
One-click install
npx skills add https://github.com/anishs1207/agentic-cli --skill careful-anishs1207
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: careful
Source: https://github.com/anishs1207/agentic-cli/tree/main/.agents/skills/gstack-careful
Command: npx skills add https://github.com/anishs1207/agentic-cli --skill careful-anishs1207

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Destructive commands in Bash can cause system damage or data loss; this skill provides guardrails, warnings, and controlled overrides to prevent unintended consequences.

Core Features & Use Cases

  • Real-time detection of dangerous patterns (rm -rf, git reset --hard, kubectl delete, etc.) and proactive prompts to confirm before execution.
  • Pre-tool checks and hooks that inspect commands across prod, staging, and shared environments to prevent risky operations.
  • Safe override mode that allows trusted users to proceed with explicit confirmation when necessary.

Quick Start

Use in your terminal to enable safety checks and confirm dangerous commands before execution.

Frequently Asked Questions about careful

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

FAQPage Schema
How do I prevent destructive bash commands from running automatically?

Preventing destructive bash commands requires a PreToolUse hook that scans for risky patterns like rm -rf and prompts for confirmation before execution. This skill implements those guardrails to intercept dangerous operations in real-time.

What bash patterns are considered destructive and require warnings?

Destructive bash patterns include rm -rf, git reset --hard, and kubectl delete. This skill detects these risky commands proactively and issues warnings to prevent unintended system damage or data loss.

Can I override command warnings when I need to run a necessary destructive operation?

You can override command warnings using the safe override mode, which allows trusted users to proceed with explicit confirmation. The skill records decisions and enables controlled execution when necessary.

Does this command guardrail work in shared terminal and production environments?

This command guardrail works across prod, staging, and shared terminal environments. It implements pre-tool checks to inspect commands and prevent risky operations where destructive actions risk outages or data loss.

How do I add safety checks to dangerous terminal commands?

Add safety checks by enabling this skill in your terminal to automatically detect dangerous patterns and confirm commands before execution. It acts as a PreToolUse hook to guard risky bash operations.