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 kyu-n/gdx-claude-skills --skill libgdx-gdx-aigit clone --depth 1 https://github.com/kyu-n/gdx-claude-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/kyu-n/gdx-claude-skills/libgdx-gdx-ai)<a href="https://agentmods.dev/skills/kyu-n/gdx-claude-skills/libgdx-gdx-ai"><img src="https://agentmods.dev/badge/skills/kyu-n/gdx-claude-skills/libgdx-gdx-ai/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/kyu-n/gdx-claude-skills/libgdx-gdx-ai"><img src="https://agentmods.dev/badge/skills/kyu-n/gdx-claude-skills/libgdx-gdx-ai.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 | $0.00140 | $0.02793 |
| Opus 5 | $0.00070 | $0.01396 |
| Sonnet 5 | $0.00028 | $0.00559 |
| Haiku 4.5 | $0.00014 | $0.00279 |
Grade A, and why
libgdx-gdx-ai scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 12d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 233 lines — stays where its author put it; the contents beside it link to each section on GitHub.
libGDX gdx-ai Extension
Reference for steering behaviors, A* pathfinding, behavior trees, finite state machines, and scheduling in the gdx-ai extension.
Dependency
// In core module only — pure Java, no native dependencies
implementation "com.badlogicgames.gdx:gdx-ai:$aiVersion"
Works on all backends including headless. No platform-specific jars needed.
Steering Behaviors
Steerable Interface
Steerable<T extends Vector<T>> extends Location<T> and Limiter. Your entity implements it, providing: getPosition(), getOrientation(), setOrientation(), newLocation(), vectorToAngle(), angleToVector(), getLinearVelocity(), getAngularVelocity(), getBoundingRadius(), isTagged()/setTagged(), and all Limiter getters/setters for max linear/angular speed/acceleration.
vectorToAngle/angleToVector convention: vectorToAngle(v) = atan2(-v.x, v.y), angleToVector(out, a) sets out.x = -sin(a), out.y = cos(a). Getting this wrong causes steering to point in the wrong direction.
SteeringAcceleration — The Output Container
SteeringAcceleration<T> has public fields T linear and float angular. Create ONE per entity, reuse each frame: new SteeringAcceleration<>(new Vector2()).
calculateSteering() only fills the output container — it does NOT move the entity. You must apply the acceleration to velocity and position yourself each frame.
Common Setup Pattern
// 1. Create behavior — target via constructor or setter
Arrive<Vector2> arrive = new Arrive<>(steerable, targetLocation)
.setArrivalTolerance(0.5f) // stop within this distance
.setDecelerationRadius(3f) // start slowing here
.setTimeToTarget(0.1f); // response speed (lower = snappier)
// Or set target separately:
// Arrive<Vector2> arrive = new Arrive<>(steerable)
// .setTarget(targetLocation)
// ...;
// 2. Each frame — calculate then apply
arrive.calculateSteering(steeringOutput);
linearVelocity.mulAdd(steeringOutput.linear, deltaTime);
if (linearVelocity.len2() > maxLinearSpeed * maxLinearSpeed)
linearVelocity.setLength(maxLinearSpeed);
position.mulAdd(linearVelocity, deltaTime);
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.
- 12d ago First seen · 233 lines · 140 tokens per session scan A 1921268ca37f
libgdx-gdx-ai is a skill published in the GitHub repository kyu-n/gdx-claude-skills (4 stars, last pushed 7mo ago), licensed MIT. It adds 140 tokens to every session and 2,793 once invoked, about $0.0007 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 2026-08-31.
Other skills, from other repositories
cesiumjs-models-particles
CesiumJS models, glTF, and particle effects - Model, KHRmeshoptcompression, CAD glTF extensions, EdgeDisplayMode, ModelAnimation, ModelNode, ParticleSystem, emitters, GPM extensions. Use when loading compressed or CAD-style glTF/GLB models, controlling edge rendering, playing model animations, positioning particles…
cesiumjs-materials-shaders
CesiumJS materials and post-processing — Material, Fabric JSON, MaterialAppearance, ImageBasedLighting, PostProcessStage, PostProcessStageLibrary, bloom, depth of field, ambient occlusion, FXAA, tonemapping, BlendingState. Use when defining Fabric materials for entities or primitives, configuring PBR image-based…
atmosphere-shader
Generate physically-based atmospheric scattering shaders — sky domes, planetary atmospheres, LUT-optimized pipelines, depth-aware post-processing. Four modes — sky-dome, atmosphere-post, planet, lut. Triggers on atmospheric scattering, sky shader, sunset rendering, planet atmosphere, Rayleigh scattering, Mie…
particle-swarm-sim
Generate 20,000+ particle swarm simulators in two modes: sandbox (complete Three.js host runtime with gesture controls, security validation, code injection pipeline) and sim (behavior function bodies that position/color particles via a sandboxed API). The AI writes ONLY a function body — the host handles rendering…
sprite-forge
Generate game sprites, SVG characters, ASCII art, animated mascots, and isometric turnarounds from images or descriptions. Five output modes: SVG characters, game sprite sheets with atlas metadata, 8-way isometric turnarounds, ASCII/Unicode terminal art, GSAP-animated mascots. Triggers on sprite, pixel art, SVG…
meshy-3d-generation
Generate 3D models, textures, images, rig characters, and animate them using the Meshy AI API. Handles API key detection, setup, and all generation workflows via direct HTTP calls. Use when the user asks to create 3D models, convert text/images to 3D, texture models, rig or animate characters, or interact with the…