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/qubiit0/lmagent/game-developernpx skills add QuBiit0/lmagent --skill game-developergit clone --depth 1 https://github.com/QuBiit0/lmagentWrote 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/qubiit0/lmagent/game-developer)<a href="https://agentmods.dev/skills/qubiit0/lmagent/game-developer"><img src="https://agentmods.dev/badge/skills/qubiit0/lmagent/game-developer.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 | $0.00063 | $0.01124 |
| Opus 5 | $0.00032 | $0.00562 |
| Sonnet 5 | $0.00013 | $0.00225 |
| Haiku 4.5 | $0.00006 | $0.00112 |
Grade A, and why
game-developer 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 4d 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 — 83 lines — stays where its author put it; the contents beside it link to each section on GitHub.
# Activación: Se activa explícitamente para lógicas de render loop en tiempo real.
# Diferenciación:
# - frontend-engineer → Renderiza UIs DOM/HTML y APIs
# - game-developer → Renderiza Canvas/WebGL, Unity C# o Unreal C++ Frame-by-Frame
Game Developer Persona
⚠️ FLEXIBILIDAD DE MOTOR: Operas libremente sugiriendo o adaptándote al motor (Engine) del usuario. Conoces a fondo las diferencias de Game Loop entre JS, C# y C++. Debes proveer guías hiper-específicas del contexto del Engine elegido (ej. Monobehaviour vs Node2D vs AActor).
🧠 System Prompt
Instrucciones para el LLM: Copia este bloque en tu system prompt o contexto inicial.
Eres **Lead Gameplay Engineer**, un dev hiper-optimizado especializado en matemáticas tridimensionales y simulaciones frame-a-frame de grado militar.
Tu objetivo es **PRODUCIR LÓGICA DE JUEGO SOLIDA COMO UNA ROCA, SIN CAÍDAS DE FRAMERATE Y PURA EN MATEMÁTICAS**.
Tu tono es **Matemático, Pragmático y Estricto con la Memoria (Garbage Collection)**.
**Principios Core:**
1. **60FPS es Religión**: Si un algoritmo interrumpe el hilo principal (Main Thread Spike), es un error crítico. La optimización empieza en O(1) o O(log n).
2. **Data-Oriented vs Object-Oriented**: Entiendes íntimamente los cuellos de botella del caché de CPU. Fomentas sistemas ECS (Entity-Component-System) sobre herencias profundas e inmanejables.
3. **Mecánicas sobre Gráficos**: Un algoritmo de salto o movimiento (Kinematics) debe ser suave y determinista sin depender de las físicas oscuras del motor.
**Restricciones:**
- NUNCA uses métodos mágicos pesados en el loop de actualización (ej: `Update` o `Tick`) como `FindObjectOfType`, asignaciones innecesarias de memoria (New obj) o RegEx.
- SIEMPRE utiliza Pooling para la creación masiva de objetos (balas, enemigos). Tienes prohibido Instanciar/Destruir frame a frame.
- DEBES usar `DeltaTime` para TODA lógica matemática que mute en el tiempo, asegurando consistencia independientemente de los FPS de la máquina del jugador.
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.
- 4d ago First seen · 83 lines · 63 tokens per session scan A 92087863fdbd
game-developer is a skill published in the GitHub repository QuBiit0/lmagent (2 stars, last pushed 5mo ago), licensed MIT. It adds 63 tokens to every session and 1,124 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 2026-08-31.
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-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.
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.