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 vchelaru/FlatRedBall2 --skill gum-integrationgit clone --depth 1 https://github.com/vchelaru/FlatRedBall2Wrote 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/vchelaru/flatredball2/gum-integration)<a href="https://agentmods.dev/skills/vchelaru/flatredball2/gum-integration"><img src="https://agentmods.dev/badge/skills/vchelaru/flatredball2/gum-integration.svg" alt="Measured on agentmods" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Excessive Agency · line 184 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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 | $0.00084 | $0.05386 |
| Opus 5 | $0.00042 | $0.02693 |
| Sonnet 5 | $0.00017 | $0.01077 |
| Haiku 4.5 | $0.00008 | $0.00539 |
Grade A, and why
gum-integration 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 2d 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 — 391 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Gum Integration in FlatRedBall2
See
content-boundaryskill first. UI composition is a human task — AI should scaffold named controls in a flat list and let the human compose the layout in the Gum Tool. Do not try to hand-author a polished visual hierarchy in code.
Gum is FlatRedBall2's UI system, backed by the Gum.MonoGame NuGet package. It is automatically initialized by FlatRedBallService.Initialize — no setup required. Gum also bundles Gum.Shapes (dashed strokes, gradients, drop shadows) and can render in world space, not only screen-space UI — so it's the home for advanced shape visuals that FRB's AARect/Circle/Polygon don't provide (see shapes).
Three Gum Usage Modes
Choose the mode that matches the project setup (see gumcli skill for how to create the project):
| Mode | Description | When to use |
|---|---|---|
| Code-only | No .gumx file. All controls created in C# with new Button() etc. |
Prototypes, no Gum editor needed |
| Project + dynamic access | .gumx loaded; retrieve named elements at runtime via GetFrameworkElementByName<T>() |
Editor integration, no codegen |
| Project + codegen | .gumx loaded + gumcli generates strongly-typed C# classes; instantiate and use typed properties directly |
Best DX; recommended for new projects |
Two Levels of Gum API
Forms Controls — interactive UI (Gum.Forms.Controls)
High-level controls with built-in click, hover, focus, and Tab/accessibility keyboard navigation:
| Control | Use for |
|---|---|
Button |
Clickable buttons |
Label |
Display-only text |
TextBox |
Text input |
CheckBox |
Toggle on/off |
StackPanel |
Vertical/horizontal layout container |
Panel |
Free-layout container |
Use Forms controls for menus, buttons, and any interactive element. Label is also the right choice for simple score/status text.
Visual Types — non-interactive rendering (MonoGameGum.GueDeriving)
What ships with it
1 file 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.
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.
- 2d ago First seen · 391 lines · 84 tokens per session scan A f221507a0a90
gum-integration is a skill published in the GitHub repository vchelaru/FlatRedBall2 (14 stars, last pushed today), licensed MIT. It adds 84 tokens to every session and 5,386 once invoked, about $0.0004 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 2026-09-04.
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.
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.
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.
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…
build-game-map-editor
Build, extend, or audit production-linked browser map editors for Three.js and isometric games. Use when Codex needs to create a private director view, derive a versioned editor document from authored placements, add outliner, layer, selection, drag, snap, inspector, or camera controls, expose enemy aggro, leash, or…