# Gs:careful

> |

- **Type:** Skill
- **Install:** `agentstack add skill-thanh-abaii-gstack-windows-port-gstack-careful`
- **Verified:** Pending review
- **Seller:** [thanh-abaii](https://agentstack.voostack.com/s/thanh-abaii)
- **Installs:** 0
- **Category:** [Agent Skills](https://agentstack.voostack.com/c/agent-skills)
- **Latest version:** 0.1.0
- **License:** MIT
- **Upstream author:** [thanh-abaii](https://github.com/thanh-abaii)
- **Source:** https://github.com/thanh-abaii/gstack-windows-port/tree/main/skills/gstack-careful

## Install

```sh
agentstack add skill-thanh-abaii-gstack-windows-port-gstack-careful
```

Requires the [AgentStack CLI](https://agentstack.voostack.com/docs/cli). Works with Claude Code, Cursor, and any MCP-compatible agent.

## About

## Preamble (run first)

```bash
python "bin/gstack-boot.py" --skill careful | iex
```

> **Safety Advisory:** This skill includes safety checks that check bash commands for destructive operations (rm -rf, DROP TABLE, force-push, git reset --hard, etc.) before execution. When using this skill, always pause and verify before executing potentially destructive operations. If uncertain about a command's safety, ask the user for confirmation before proceeding.

# /gs: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
New-Item -ItemType Directory -Force ~/.gstack/analytics
echo '{"skill":"careful","ts":"'$(date -u +%Y-%m-%dT%H:%M:%SZ)'","repo":"'$(basename "$(git rev-parse --show-toplevel | Out-Null)" | Out-Null ; echo "unknown")'"}'  >> ~/.gstack/analytics/skill-usage.jsonl | Out-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.

## Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

- **Author:** [thanh-abaii](https://github.com/thanh-abaii)
- **Source:** [thanh-abaii/gstack-windows-port](https://github.com/thanh-abaii/gstack-windows-port)
- **License:** MIT

Install and usage instructions live in the source repository linked above.

## Pricing

- **Free** — Free

## Security capabilities

Automated source analysis of v0.1.0 — what this tool can access:

- **Network access:** no
- **Filesystem access:** no
- **Shell / process execution:** no
- **Environment & secrets:** no
- **Dynamic code execution:** no

*"Yes" means the capability is present in the source — more access means more to trust, not that it is unsafe.*


## Versions

- **0.1.0** — security scan: flagged — Imported from the upstream source.

## Links

- Listing page: https://agentstack.voostack.com/l/skill-thanh-abaii-gstack-windows-port-gstack-careful
- Seller: https://agentstack.voostack.com/s/thanh-abaii
- Browse the marketplace: https://agentstack.voostack.com/browse

---
Listed on AgentStack — the marketplace for AI agent skills and MCP servers. Every listing is security-reviewed. Creators keep 70%.