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/engine-overviewnpx skills add vchelaru/FlatRedBall2 --skill engine-overviewgit 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/engine-overview)<a href="https://agentmods.dev/skills/vchelaru/flatredball2/engine-overview"><img src="https://agentmods.dev/badge/skills/vchelaru/flatredball2/engine-overview.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 | $0.00069 | $0.01399 |
| Opus 5 | $0.00034 | $0.00700 |
| Sonnet 5 | $0.00014 | $0.00280 |
| Haiku 4.5 | $0.00007 | $0.00140 |
Grade A, and why
engine-overview 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 — 102 lines — stays where its author put it; the contents beside it link to each section on GitHub.
FlatRedBall2 Engine Overview
FlatRedBall2 is a 2D game engine built on MonoGame. It provides physics, collision, rendering, input, and UI (via Gum) out of the box. Game code creates Screens, Entities, and wires them together.
What the Engine Does Automatically
- Physics:
pos += vel*dt + acc*(dt^2/2),vel += acc*dt,vel -= vel*drag*dt— every frame, for every entity - Collision resolution: All registered
CollisionRelationshippairs are tested and resolved after physics - Rendering: Everything added via
screen.Add(renderable)is drawn, sorted by Layer + Z - Input polling:
Inputupdates keyboard, mouse, and gamepad state each frame - Gum UI updates: Click/hover/focus events routed to all active Gum elements
- Screen transitions: Old screen torn down, new screen initialized — entities, factories, Gum elements all cleaned up automatically
- Camera: Initialized from window viewport; transforms world coordinates to screen
What Game Code Must Implement
- Entity subclasses — override
CustomInitialize(add shapes, input) andCustomActivity(per-frame logic) - Screen subclasses — override
CustomInitialize(create factories, entities, collision relationships, UI) - Collision relationships — call
AddCollisionRelationshipin screen'sCustomInitialize - Game1.cs — initialize
FlatRedBallService.Default, callUpdate/Draweach frame - Save/load — the engine offers nothing here; use standard .NET (
System.IO+System.Text.Json, or your serializer of choice). There is no FRB2 save API to search for.
Frame Loop Order
Each frame runs in this order:
- Screen transition (if pending) — old screen destroyed, new screen initialized
- Input update — keyboard, mouse, gamepad polled
- Gum update — UI input events routed
- Physics — entity positions updated from velocity/acceleration/drag
- Collision — registered relationships resolved; positions corrected
- Entity
CustomActivity— each entity's per-frame logic - Screen
CustomActivity— screen-level logic (sees post-collision, post-entity state) - Draw — all registered renderables drawn
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 · 102 lines · 69 tokens per session scan A 227aee6a21c4
engine-overview is a skill published in the GitHub repository vchelaru/FlatRedBall2 (14 stars, last pushed yesterday), licensed MIT. It adds 69 tokens to every session and 1,399 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 2026-09-04.
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).
unity-addressables
Manage Addressables groups, entries, profiles and content builds (com.unity.addressables, reflection-based).
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.
motion
How an agent turns a character mesh into a usable animated FBX — and how to judge whether the result is shippable.