Setup EngineSAFE

Turn Claude Code into a full game dev studio — 49 AI agents, 72 workflow skills, and a complete coordination system mirroring real studio hierarchy.

The instruction file, verbatim from the audited commit — this is the text the model reads, and the surface the audit's instruction layer examines. Quoted here so you can judge it without cloning anything.

---
name: setup-engine
description: "Configure engine and version. Pins it in CLAUDE.md; WebSearch fills reference docs when the version is beyond LLM training data."
argument-hint: "[engine] | [engine version] | refresh | upgrade [old-version] [new-version] | no args for guided selection"
user-invocable: true
allowed-tools: Read, Glob, Grep, Write, Edit, Bash, WebSearch, WebFetch, Agent, AskUserQuestion, Bash(bash "*/.claude/skills/setup-engine/../../hooks/yaml-helper.sh" resolve_config *)
model: sonnet
---

When this skill is invoked:

!`bash "${CLAUDE_SKILL_DIR}/../../hooks/yaml-helper.sh" resolve_config --keys workflow`

**Tier awareness.** The `workflow` tier resolved above governs which design
artifact this skill expects and the finish path it recommends in §12:
- **`minimal`** — the design artifact is the one-page `design/game-brief.md`
  (no GDDs, systems decomposition, or per-system design at this tier).
  `/setup-engine` runs *first* in the minimal path, so a missing brief here is
  normal, not a gap. The finish path is the 4-step floor.
- **`standard` / `full`** — the design artifact is `design/gdd/game-concept.md`
  and the finish path is the full pipeline.

If the block did not render (shell preprocessing disabled), assume `minimal` (the default).

## 1. Parse Arguments

Four modes:

- **Full spec**: `/setup-engine godot 4.6` — engine and version provided
- **Engine only**: `/setup-engine unity` — engine provided, version will be looked up
- **No args**: `/setup-engine` — fully guided mode (engine recommendation + version)
- **Refresh**: `/setup-engine refresh` — update reference docs (see Section 10)
- **Upgrade**: `/setup-engine upgrade [old-version] [new-version]` — migrate to a new engine version (see Section 11)

---

## 2. Guided Mode (No Arguments)

If no engine is specified, run an interactive engine selection process:

### Check for existing game concept
Read the design artifact for the resolved tier (see **Tier awareness** above):
- **`standard` / `full`**: read `design/gdd/game-concept.md` if it exists —
  extract genre, scope, platform targets, art style, team size, and any engine
  recommendation from `/brainstorm`.
- **`minimal`**: read `design/game-brief.md` if it exists — extract genre,
  scope, platform, and art direction from its fields. Its absence is **expected**
  at `minimal` (the brief is authored *after* engine setup in the minimal path), so
  do not treat a missing brief as a gap — proceed straight to guided selection.
- If no concept **or** brief exists, inform the user:
  > "No game concept found. Consider running `/brainstorm` first to discover what
  > you want to build — it will also recommend an engine. Or tell me about your
  > game and I can help you pick."

  (At `minimal` this is optional, not a prerequisite — you can pick an engine now
  and write the brief next.)

### If the user wants to pick without a concept, ask in this order:

**Question 1 — Prior experience** (ask this first, always, via `AskUserQuestion`):
- Prompt: "Have you worked in any of these engines before?"
- Options: `Godot` / `Unity` / `Unreal Engine 5` / `Multiple — I'll explain` / `None of them`
- If they pick a specific engine → recommend that engine. Prior experience outweighs all other factors. Confirm with them and skip the matrix.
- If "None" or "Multiple" → continue to the questions below.

**Questions 2-6 — Decision matrix inputs** (only if no prior engine experience):

**Question 2 — Target platform** (ask this second, always, via `AskUserQuestion` — platform eliminates or heavily weights engines before any other factor):
- Prompt: "What platforms are you targeting for this game?"
- Options: `PC (Steam / Epic)` / `Mobile (iOS / Android)` / `Console` / `Web / Browser` / `Multiple platforms`
- Platform rules that feed directly into the recommendation:
  - Mobile → Unity strongly preferred; Unreal is a poor fit; Godot is viable for simple mobile
  - Console → Unity or Unreal; Godot console support requires third-party publishers or significant extra work
  - Web → Godot exports cleanly to web; Unity WebGL is functional; Unreal has poor web support
  - PC only → all engines viable; other factors decide
  - Multiple → Unity is the most portable across PC/mobile/console

1. **What kind of game?** (2D, 3D, or both?)
2. **Primary input method?** (keyboard/mouse, gamepad, touch, or mixed?)
3. **Team size and experience?** (solo beginner, solo experienced, small team?)
4. **Any strong language preferences?** (GDScript, C#, C++, visual scripting?)
5. **Budget for engine licensing?** (free only, or commercial licenses OK?)

### Produce a recommendation

Do NOT use a simple scoring matrix that eliminates engines. Instead, reason through the user's profile against the honest tradeoffs below, then present 1-2 recommendations with full context. Always end with the user choosing — never force a verdict.

**Engine honest tradeoffs:**

**Godot 4**
- Genuine strengths: 2D (best in class), stylized/indie 3D, rapid iteration, free forever (MIT), open source, gentlest learning curve, best for solo devs who want full control
- Real limitations: 3D ecosystem is thin compared to Unity/Unreal (fewer tutorials, assets, community answers for 3D-specific problems); large open-world 3D is very hard and largely untested in Godot; console export requires third-party publishers or significant extra work; smaller professional job market
- Licensing reality: Truly free with no revenue thresholds ever. MIT license means you own everything.
- Best fit: 2D games of any scope; stylized/atmospheric 3D; contained 3D worlds (not open-world); first game projects where learning curve matters; projects where budget is a hard constraint at any scale

**Unity**
- Genuine strengths: Industry standard for mid-scope 3D and mobile; massive asset store and tutorial ecosystem; C# is a professional language; best console certification support for indie; strong community for almost every genre
- Real limitations: Lic

SAFEgrade B · trust 89/100 Nothing in the source contradicts what it says it does. Grade A is reserved for packages that have also passed the behavioural sandbox.

What the source does

Filesystem

none-observed

Network

none-observed

Shell

none-observed

Dependencies

pinned

Secrets in source

none-found

Findings (0)

No findings outside the package's declared scope.

Gates applied: no_behavioural_pass.