Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add OpenFairyGUI/FairyGUI-Skills --skill fairygui-runtimegit clone --depth 1 https://github.com/OpenFairyGUI/FairyGUI-SkillsWrote 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/openfairygui/fairygui-skills/fairygui-runtime)<a href="https://agentmods.dev/skills/openfairygui/fairygui-skills/fairygui-runtime"><img src="https://agentmods.dev/badge/skills/openfairygui/fairygui-skills/fairygui-runtime/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/openfairygui/fairygui-skills/fairygui-runtime"><img src="https://agentmods.dev/badge/skills/openfairygui/fairygui-skills/fairygui-runtime.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00070 | $0.00674 |
| Opus 5 | $0.00035 | $0.00337 |
| Sonnet 5 | $0.00014 | $0.00135 |
| Haiku 4.5 | $0.00007 | $0.00067 |
Grade A, and why
fairygui-runtime 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 yesterday.
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 — 42 lines — stays where its author put it; the contents beside it link to each section on GitHub.
FairyGUI Runtime Skill
Maintenance status
Final edition v1.1.0 (2026-09-08). This repository is archived and no longer maintained. Runtime examples remain historical reference material; verify APIs and lifecycle behavior against the installed engine/SDK before applying them.
OpenFairyGUI maintains project SDK/CLI/MCP automation; FairyGUI-Maker provides Agent authoring and preview workflows. Neither fully replaces this Skill's multi-engine runtime coverage. Use the capabilities already available for the requested task; following these links does not authorize installation or imply a working tool connection. Discussion and review remain read-only.
Workflow
- Identify the engine/SDK version, language and load model from the project and installed dependencies: Unity C#, Unity Puerts, Cocos Creator, LayaAir, ThreeJS or custom. Ask only when a material choice remains unknown.
- Identify the runtime task: architecture, root setup, package loading, ownership, data refresh, generated binding, extension class, list rendering, events, transition control, window lifecycle, memory, or performance.
- If the task needs deeper details, read the relevant reference file:
- Runtime setup: references/runtime-setup.md
- Runtime architecture and UI system organization: references/runtime-architecture.md
- Package loading: references/loading-packages.md
- UI lifecycle, ownership, disposal, and async race boundaries: references/ui-lifecycle-and-ownership.md
- Component binding and extensions: references/component-binding.md
- Data binding, refresh, model-to-view rules, and stale async guards: references/data-binding-and-refresh.md
- Lists and scrolling: references/lists-scrolling.md
- Events and animation: references/events-animation.md
- Engine-specific runtime patterns: references/engine-patterns.md
- Unity condensed examples: references/unity-patterns.md
- Cocos Creator condensed examples: references/cocoscreator-patterns.md
- LayaAir condensed examples: references/layaair-patterns.md
- Performance and lifecycle: references/performance-lifecycle.md
- Ground advice in the editor contract: package names, published file names, item URLs, child names, controllers, transitions, and generated binder order.
- Prefer business-state-driven UI updates: runtime code should drive named controllers, button states, loaders, and list data instead of manually patching many children.
- Provide code-level steps with lifecycle placement and cleanup.
What ships with it
14 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- agents/openai.yaml 329 B
- references/cocoscreator-patterns.md 3.3 KB
- references/component-binding.md 3.1 KB
- references/data-binding-and-refresh.md 5.9 KB
- references/engine-patterns.md 2.4 KB
- references/events-animation.md 2.7 KB
- references/layaair-patterns.md 2.8 KB
- references/lists-scrolling.md 2.6 KB
- references/loading-packages.md 2.8 KB
- references/performance-lifecycle.md 2.3 KB
- references/runtime-architecture.md 4.5 KB
- references/runtime-setup.md 3.0 KB
- references/ui-lifecycle-and-ownership.md 4.4 KB
- references/unity-patterns.md 3.5 KB
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.
- yesterday Changed · +7 lines · -23 tokens per session 45c66f3ea29b
- 11d ago First seen · 35 lines · 93 tokens per session scan A 280ddf72da9c
fairygui-runtime is a skill published in the GitHub repository OpenFairyGUI/FairyGUI-Skills (16 stars, last pushed 2d ago), licensed MIT. It adds 70 tokens to every session and 674 once invoked, about $0.0003 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
worker-visualizer
A real-time data/particle/simulation visualizer whose heavy compute runs in a Web Worker (off the main thread), optionally sharing memory with the UI via SharedArrayBuffer, and renders to a canvas at 60fps. Produced as a single self-contained index.html. Use when the brief asks for a "web worker", "simulation"…
react-three-fiber
React Three Fiber 3D renderer for json-render. Use when working with @json-render/react-three-fiber, building 3D scenes from JSON specs, rendering meshes/lights/models/environments, or integrating Three.js with json-render catalogs.
vgpu
Build, debug, test, and optimize WebGPU projects using vgpu, its CLI, or @vgpu packages. Use for vgpu API questions, WGSL workflows, browser or Node rendering, integrations, testing, and performance work.
matterjs
Use when implementing 2D physics interactions with Matter.js, including Engine/World setup, Render/Runner configuration, adding bodies and constraints, and scroll/interaction-friendly canvas scenes.
threejs-game-director
Entrypoint for building, upgrading, and finishing Three.js browser games. Routes work across the sibling threejs- skills for gameplay, graphics, UI, 3D/image/audio asset generation, debugging, and release. Use for build-a-game, upgrade, polish, premium, AAA, high-fidelity, showcase, from-scratch, endless runner…
sceneview-web
Build 3D and WebXR (AR/VR) experiences in the browser with SceneView for Web — Filament.js (WebGL2/WASM) wrapped in a Kotlin/JS DSL and a plain-JavaScript API on window.sceneview. Use whenever the user asks for "3D in the browser", "a web model viewer", "WebXR AR/VR", or any browser 3D/AR app where the dependency is…