# Gsp Scope Guard

> Use when a game project is expanding too broadly and needs scope protection without losing the core goal.

- **Type:** Skill
- **Install:** `agentstack add skill-mike007jd-game-superpowers-gsp-scope-guard`
- **Verified:** Yes — security-reviewed for prompt injection and unsafe behavior
- **Seller:** [mike007jd](https://agentstack.voostack.com/s/mike007jd)
- **Installs:** 0
- **Category:** [Agent Skills](https://agentstack.voostack.com/c/agent-skills)
- **Latest version:** 0.1.0
- **License:** MIT
- **Upstream author:** [mike007jd](https://github.com/mike007jd)
- **Source:** https://github.com/mike007jd/game-superpowers/tree/main/publish/clawhub/gsp-scope-guard

## Install

```sh
agentstack add skill-mike007jd-game-superpowers-gsp-scope-guard
```

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

## About

# Game Scope Guard

## Goal
Keep scope under control while preserving the value of the request.

## Core rule
Do **not** equate “scope control” with “remove everything interesting.”

## By mode
- **yolo-super / guided-build**: protect the user’s core requested feature set. Cut edge cases, not the fantasy.
- **refactor-open**: protect the outcome, but allow larger architecture change when it prevents endless patching.
- **surgical-live**: minimize blast radius first; here scope control often means tighter change boundaries.

## Good cuts
- optional content multiplication
- edge-case polish outside the critical path
- tooling not needed for the current target
- deep progression systems when the target does not require them

## Bad cuts
- requested core mechanic
- requested style / feel / UX quality if that is central to the ask
- essential fail/retry and onboarding clarity
- architecture cleanup that is necessary to make the requested change stable

## Outputs

Follow the `gsp-orchestrator` output strategy:
- **inline** (default): state scope decisions and rationale in conversation.
- **minimal** or **full**: record the rationale in `docs/game-studio/plan.md` or `docs/game-studio/build-strategy.md`.

## Pair with
Use `gsp-scope-profile` early to define the intended scope. This skill protects it later.

## Source & license

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

- **Author:** [mike007jd](https://github.com/mike007jd)
- **Source:** [mike007jd/game-superpowers](https://github.com/mike007jd/game-superpowers)
- **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: passed — Imported from the upstream source.

## Links

- Listing page: https://agentstack.voostack.com/l/skill-mike007jd-game-superpowers-gsp-scope-guard
- Seller: https://agentstack.voostack.com/s/mike007jd
- 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%.