# Gs Careful

> Safety guardrails - warns before destructive commands (rm -rf, DROP TABLE, force-push). CARL TRIGGERS: be careful, careful mode, destructive command warning, safety warning. SOURCE: garrytan/gstack/careful, integrated as gs-careful on 2026-05-29.

- Skill: `yousefnabil-soc/gs-careful` (Agent Skill, multi-file: 3 files)
- Install (CLI): `npx skillmds@latest add yousefnabil-soc/gs-careful`
- Raw SKILL.md: https://api.skillmd.com/api/skills/yousefnabil-soc/gs-careful/raw
- Safety review: pending
- Works with: Claude Code, Claude.ai, OpenAI Codex
- Category: Coding & Dev Tools
- Author: YousefNabil-SOC (https://skillmd.com/u/yousefnabil-soc)
- Updated: 2026-09-17
- Page: https://skillmd.com/skills/yousefnabil-soc/gs-careful

---


> INTEGRATION NOTE: Extracted from gstack and renamed gs-careful (Phase 1B) to coexist with the host environment's CARL routing. Original gstack docs follow. Sibling gstack skills referenced below map to gs-* when installed (the 19-skill set); gstack-only infra (browse binary, gstack bin/ toolchain, ~/.gstack GBrain) is not installed here, so dependent steps degrade gracefully.

<!-- AUTO-GENERATED from SKILL.md.tmpl — do not edit directly -->
<!-- Regenerate: bun run gen:skill-docs -->


## When to invoke this skill

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. Use when asked to "be careful", "safety mode",
"prod mode", or "careful mode".

# /careful — Destructive Command Guardrails

Safety mode is now **active**. Every bash command will be checked for destructive
patterns before running. If a destructive command is detected, you'll be warned
and can choose to proceed or cancel.

```bash
mkdir -p ~/.gstack/analytics
echo '{"skill":"careful","ts":"'$(date -u +%Y-%m-%dT%H:%M:%SZ)'","repo":"'$(basename "$(git rev-parse --show-toplevel 2>/dev/null)" 2>/dev/null || echo "unknown")'"}'  >> ~/.gstack/analytics/skill-usage.jsonl 2>/dev/null || true
```

## What's protected

| Pattern | Example | Risk |
|---------|---------|------|
| `rm -rf` / `rm -r` / `rm --recursive` | `rm -rf /var/data` | Recursive delete |
| `DROP TABLE` / `DROP DATABASE` | `DROP TABLE users;` | Data loss |
| `TRUNCATE` | `TRUNCATE orders;` | Data loss |
| `git push --force` / `-f` | `git push -f origin main` | History rewrite |
| `git reset --hard` | `git reset --hard HEAD~3` | Uncommitted work loss |
| `git checkout .` / `git restore .` | `git checkout .` | Uncommitted work loss |
| `kubectl delete` | `kubectl delete pod` | Production impact |
| `docker rm -f` / `docker system prune` | `docker system prune -a` | Container/image loss |

## Safe exceptions

These patterns are allowed without warning:
- `rm -rf node_modules` / `.next` / `dist` / `__pycache__` / `.cache` / `build` / `.turbo` / `coverage`

## How it works

The hook reads the command from the tool input JSON, checks it against the
patterns above, and returns `permissionDecision: "ask"` with a warning message
if a match is found. You can always override the warning and proceed.

To deactivate, end the conversation or start a new one. Hooks are session-scoped.