# Careful

> Write a checklist of destructive commands the user wants to think twice about (rm -rf, force push, hard reset, db drop, etc.) to .dragoon/CAREFUL.md. dragoon does NOT block commands at runtime - this is a discipline tool, a list the agent reads before risky operations. Use to set explicit guardrails for an AI agent or new contributor. Run as `node ~/.claude/skills/dragoon/skills/careful/scripts/careful.js`.

- Skill: `dragoon0x/careful` (Agent Skill, multi-file: 2 files)
- Install (CLI): `npx skillmds@latest add dragoon0x/careful`
- Raw SKILL.md: https://api.skillmd.com/api/skills/dragoon0x/careful/raw
- Safety review: pending
- Works with: Claude Code, Claude.ai, OpenAI Codex
- Category: AI & ML
- Author: dragoon0x (https://skillmd.com/u/dragoon0x)
- Updated: 2026-09-17
- Page: https://skillmd.com/skills/dragoon0x/careful

---


# /careful

Discipline-tool checklist for destructive commands.

## When to use

- Setting up a new project or onboarding an agent
- After a destructive accident, codify the rule
- The user says "set up guardrails", "what should the agent not do"

## What it writes

`.dragoon/CAREFUL.md` with two sections:
- destructive commands to confirm before running (rm -rf, force push, etc.)
- destructive commands the agent should NEVER run without explicit user prompt

This is **not** a runtime block. It's a read-before-act discipline aid.

## Run it

```
dragoon careful --apply
dragoon careful --show
```