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 agentmods add skills/vchelaru/flatredball2/glue-project-loadingnpx skills add vchelaru/FlatRedBall2 --skill glue-project-loadinggit 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/glue-project-loading)<a href="https://agentmods.dev/skills/vchelaru/flatredball2/glue-project-loading"><img src="https://agentmods.dev/badge/skills/vchelaru/flatredball2/glue-project-loading.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 | $0.00000 | $0.01510 |
| Opus 5 | $0.00000 | $0.00755 |
| Sonnet 5 | $0.00000 | $0.00302 |
| Haiku 4.5 | $0.00000 | $0.00151 |
Grade A, and why
glue-project-loading 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 — 109 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Loading Glue Projects
FRB2 reads the JSON files Glue writes and builds Screens and Entities from them at runtime. There is
no generated C#: src/Glue/ is the whole implementation, GlueProject is the entry point.
Booting one is a single call in Game1.Initialize, after base.Initialize():
FlatRedBallService.Default.Initialize(this, "Content/FrbEditor/MyGame.gluj");
The project names its own start-up screen, Gum project and resolution, so nothing else is passed —
the engine wires the screen's Save/Project itself. The path must be relative: it resolves
through TitleContainer, which throws on a rooted path, so an absolute one loads the project and
then fails every asset it references. To load a project but boot your own screen instead, use
Initialize<MyScreen>(game, new EngineInitSettings { GlueProjectFile = … }).
Where to start
| Task | Go to |
|---|---|
| Boot a project | Initialize(game, "Content/FrbEditor/MyGame.gluj") |
| Load without booting | GlueProject.Load(glujPath, content) |
| Find/create an element | GlueProject.FindScreen/FindEntity/CreateScreen/CreateEntity |
| Move between screens | Screen.MoveToScreen(string glueName) |
| Read/write an authored variable | the indexer on GlueScreen/GlueEntity, or Get<T> |
| Claim a Glue type for FRB2 | GlueTypeMap |
Every loaded element shares one C# type
GlueScreen and GlueEntity are what a loaded element is; only its Save data distinguishes it.
So MoveToScreen<T>() and Factory<T> cannot tell two loaded screens apart — the by-name overloads
(MoveToScreen(string), GlueProject.CreateEntity(name, screen)) exist for exactly this reason.
Both directions work: a loaded screen can still MoveToScreen<AHandWrittenScreen>().
Names are Glue's own, with the folder: Screens\Level1, Entities\Player. Either separator is
accepted and case is ignored, but the prefix is required — a bare leaf is ambiguous, since a screen
and an entity can share one.
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 First seen · 109 lines · 0 tokens per session scan A ef031ffd636e
glue-project-loading is a skill published in the GitHub repository vchelaru/FlatRedBall2 (14 stars, last pushed yesterday), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,510 tokens. 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
gameobject-component-destroy
Destroy one or more Components from a target GameObject. Missing (null) components are skipped — they cannot be destroyed. Use 'gameobject-find' and 'gameobject-component-get' to identify the components first.
unity-version-split
Split a C# file into Unity 6.5+ and pre-Unity 6.5 variants. Use when a file needs different implementations for different Unity versions due to API changes (e.g., EntityId vs int, GetEntityId vs GetInstanceID).
playtest-report
Generates a structured playtest report template or analyzes existing playtest notes into a structured format. Use this to standardize playtest feedback collection and analysis.
unity-manual-component
Manually add, configure, reorder, and copy components on GameObjects using Unity Editor UI. For one-off Inspector workflows that do not need REST automation.
godot-signals-groups
Build event-driven, decoupled Godot 4.7 gameplay with signals and node groups: declare and emit custom signals, connect with Callables (incl. bind/one-shot), and broadcast to many nodes via groups and callgroup. Use when wiring node communication in a Godot project, replacing tight references with signals…
threejs-exposure-color-grading
Build a measured exposure and grading path in Three.js. Use for a 64x36 encoded luminance meter, asynchronous readback, weighted log-average exposure, asymmetric adaptation, single tone-map ownership, and a generated 32-cube post-tone-map LUT.