careful

Detect destructive shell, database, and container commands before execution.

1|2|Updated Jan 4, 2024
One-click install
npx skills add https://github.com/NaKMiers/Port4lio --skill careful-nakmiers
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: careful
Source: https://github.com/NaKMiers/Port4lio/tree/main/.agents/skills/careful
Command: npx skills add https://github.com/NaKMiers/Port4lio --skill careful-nakmiers

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires python3.

What problem does it solve?

Safety guardrails prevent destructive commands from executing blindly by warning and requiring explicit confirmation.

Core Features & Use Cases

  • Warning on dangerous patterns like rm -rf, DROP TABLE, TRUNCATE, git push --force, git reset --hard, kubectl delete, and docker system prune.
  • Optional override to allow proceeding after a confirmed warning.
  • Local analytics logging of usage for auditability while preserving command content.

Quick Start

Activate careful mode and run a destructive command to see the warning and choose to proceed or cancel.

Frequently Asked Questions about careful

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

FAQPage Schema
How do I prevent accidental data loss from destructive shell commands like rm -rf and git reset --hard?

To prevent accidental data loss from destructive shell commands, you can use safety guardrails that detect patterns like rm -rf and git reset --hard, warning you before execution and requiring explicit confirmation to proceed.

What destructive database and container operations are intercepted by command filtering?

Command filtering intercepts destructive database and container operations such as DROP TABLE, TRUNCATE, kubectl delete, and docker system prune, applying pattern matching to block execution until explicitly confirmed.

Does command filtering work in production and shared environments?

Yes, command filtering works in production and shared environments by applying safety guardrails across shell, database, and container operations to ensure predictable, auditable interventions before any destructive command executes.

How to override a destructive command warning when I am sure I want to proceed?

To override a destructive command warning, you can use the optional override feature to allow proceeding after a confirmed warning, ensuring that the execution is intentional and logged for auditability.

Do I need python3 to run safety guardrails for bash command filtering?

Yes, you need python3 installed as a dependency to run safety guardrails for bash command filtering, which logs local analytics for auditability while preserving command content.