Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add rondorkerin/gamestack/plugin install gamestackWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/rondorkerin/gamestack/engine-router)<a href="https://agentmods.dev/skills/rondorkerin/gamestack/engine-router"><img src="https://agentmods.dev/badge/skills/rondorkerin/gamestack/engine-router.svg" alt="Measured on agentmods" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00111 | $0.01276 |
| Opus 5 | $0.00056 | $0.00638 |
| Sonnet 5 | $0.00022 | $0.00255 |
| Haiku 4.5 | $0.00011 | $0.00128 |
Grade A, and why
engine-router scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 8d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 62 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Engine Router
Preamble (auto-loaded)
!cat "${CLAUDE_PLUGIN_ROOT}/shared/PREAMBLE.md"; echo; cat "${CLAUDE_PLUGIN_ROOT}/ETHOS.md"
FALLBACK: if the line above rendered literally or empty (
disableSkillShellExecution), Read${CLAUDE_PLUGIN_ROOT}/shared/PREAMBLE.mdand${CLAUDE_PLUGIN_ROOT}/ETHOS.mdnow and follow PREAMBLE.md as instructions, then continue.
gamestack splits a game into two jobs: the design brain (engine-agnostic, first-party) and the engine hands (per-platform, the curated engine packs). This skill is the design→engine handoff — it consumes the finished design bible and sends implementation to whichever engine pack owns the target platform. It does not sequence design phases (that is game-design-process); it only routes a ready design to code.
The preamble has already detected the engine and loaded ${CLAUDE_PLUGIN_ROOT}/overlays/<engine>.md — that overlay holds the spec→pack-skill mapping for this target. Use it as the translation table below.
When to use this
- A design/spec is ready and it's time to write engine code
- Choosing a target engine, or supporting more than one
- Mid-build, deciding "is this a design question or an engine question?" and pulling the right skill
The core stance
- Design once, implement per engine. The world bible, systems, combat feel, and procgen rules from the foundation skills are engine-independent. Don't re-derive them inside an engine — translate them.
- Never put design logic in an engine skill, or engine APIs in a design skill. If you're reaching for
Node/Actor/THREE.Scenewhile still deciding what interesting decision a system creates, stop — that's a foundation question (game-design-fundamentals). - One spec, one handoff artifact. The design pipeline's output (specs, content, quality verdicts) is the contract the engine pack consumes. Engine choice never changes the spec.
Routing table
| Phase / question | Layer | Skill to pull |
|---|---|---|
| Concept, pillars, core loop, "is this an interesting decision?" | Foundation (design) | game-design-fundamentals |
| World structure, navigation, spatial pacing | Foundation (design) | open-world-design |
| Generating + reviewing content without sameness | Foundation (design) | procedural-generation, procgen-review |
| Combat & game feel (juice, telegraphing, encounters) | Foundation (design) | combat-design |
| Sequencing the whole design end to end | Foundation (process) | game-design-process |
| Implement in Godot 4.x (GDScript, systems, optimization, export) | Engine hands | godot pack (/plugin install godot@gamestack) |
| Implement in Unreal (C++ gameplay framework, rendering, networking) | Engine hands | unreal pack (/plugin install unreal@gamestack) |
| Debug a Unity build (logging, runtime commands, watching) | Engine hands | unity-jahro pack (/plugin install unity-jahro@gamestack) |
| Implement in Unity (general authoring) | Engine hands | ⬜ roadmap — no curated pack yet; use general C#/Unity knowledge + the foundation specs |
| Implement in Three.js / web | Engine hands | ⬜ roadmap — no curated pack yet; use the foundation specs + general Three.js knowledge |
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 8d ago First seen · 62 lines · 111 tokens per session scan A 442a8d8b0718
engine-router is a skill published in the GitHub repository rondorkerin/gamestack (27 stars, last pushed 2mo ago), licensed MIT. It adds 111 tokens to every session and 1,276 once invoked, about $0.0006 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
ux-design
Guided, section-by-section UX spec authoring for a screen, flow, or HUD. Reads game concept, player journey, and relevant GDDs to provide context-aware design guidance. Produces ux-spec.md (per screen/flow) or hud-design.md using the studio templates.
architecture-review
Validates completeness and consistency of the project architecture against all GDDs. Builds a traceability matrix mapping every GDD technical requirement to ADRs, identifies coverage gaps, detects cross-ADR conflicts, verifies engine compatibility consistency across all decisions, and produces a PASS/CONCERNS/FAIL…
localize
Full localization pipeline: scan for hardcoded strings, extract and manage string tables, validate translations, generate translator briefings, run cultural/sensitivity review, manage VO localization, test RTL/platform requirements, enforce string freeze, and report coverage.
vertical-slice
Pre-Production validation — build a production-quality end-to-end build to confirm the full game loop is achievable before committing to Production. Run after GDDs, architecture, and UX specs are complete. Produces a PROCEED/PIVOT/KILL verdict that gates the Pre-Production → Production transition.
quick-design
Lightweight design spec for small changes — tuning adjustments, minor mechanics, balance tweaks. Skips full GDD authoring when a system GDD already exists or the change is too small to warrant one. Produces a Quick Design Spec that embeds directly into story files.
day-one-patch
Prepare a day-one patch for a game launch. Scopes, prioritises, implements, and QA-gates a focused patch addressing known issues discovered after gold master but before or immediately after public launch. Treats the patch as a mini-sprint with its own QA gate and rollback plan.