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 perniemann/pnCore --skill pn-gamedev-philosophygit clone --depth 1 https://github.com/perniemann/pnCoreWrote 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/perniemann/pncore/pn-gamedev-philosophy)<a href="https://agentmods.dev/skills/perniemann/pncore/pn-gamedev-philosophy"><img src="https://agentmods.dev/badge/skills/perniemann/pncore/pn-gamedev-philosophy/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/perniemann/pncore/pn-gamedev-philosophy"><img src="https://agentmods.dev/badge/skills/perniemann/pncore/pn-gamedev-philosophy.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 | $0.00057 | $0.01271 |
| Opus 5 | $0.00028 | $0.00635 |
| Sonnet 5 | $0.00011 | $0.00254 |
| Haiku 4.5 | $0.00006 | $0.00127 |
Grade A, and why
pn-gamedev-philosophy 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 8d 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 — 174 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Game Development Philosophy
Purpose
Use this as a game and real-time 3D design rulebook for:
- Game loops and state machines
- Three.js / WebGL / WebGPU scenes
- Real-time physics and animation
- Asset loading and disposal
- Performance-critical rendering
- Input handling and update order
It is engine-agnostic where possible and aligned with current industry practices.
When to use
- Designing game architecture or real-time loops
- Structuring Three.js/R3F scenes or WebGL projects
- Reviewing performance, disposal, or timestep logic
- Establishing gamedev standards for a team or AI agent
- Auditing frame budget, LOD, or memory management
- Building tools, prototypes, or shipped games
For workflow, audit checklist, and templates, see reference.md.
Core Philosophy (non-negotiables)
Fixed timestep for physics
Physics and deterministic logic use a fixed delta (e.g. 1/60s). Variable delta causes numerical drift, collision tunneling, and non-determinism across hardware. Accumulate elapsed time; step in fixed increments; cap accumulator to avoid spiral of death.
Frame budget is law
Target refresh rate defines the budget (60 FPS ≈ 16.7ms, 120 Hz ≈ 8.3ms per frame). Profile to identify CPU vs GPU bottlenecks. Leave 1–2ms safety margin for spikes. Optimize the dominant cost first.
Disposal before allocation
WebGL does not auto-free. Geometries, materials, textures, render targets must be disposed when no longer needed. Dispose before removing references. Monitor renderer.info.memory; avoid per-frame allocations in hot paths.
Update order is explicit
Define and document: input → physics → game logic → animation → render. Systems that depend on others run after. No hidden ordering; deterministic and testable.
Hierarchy carries intent
Group objects logically (environment, characters, UI, effects). Use consistent naming (e.g. env_ground, char_player). Hierarchy enables correct transforms, visibility toggles, and disposal.
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.
- 8d ago First seen · 174 lines · 57 tokens per session scan A 9b0ade63e278
pn-gamedev-philosophy is a skill published in the GitHub repository perniemann/pnCore (0 stars, last pushed 5d ago), licensed MIT. It adds 57 tokens to every session and 1,271 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 2026-09-03.
Other skills, from other repositories
deepseek-harness
Use when building AI agent applications with a plugin-based architecture — Web UI, CLI, Python SDK, Cordis plugin system, multi-model orchestration. DeepSeek Harness (dsh): open-source agent harness by DeepSeek AI where everything is a plugin, powered by Cordis for spatiotemporal composability.
senior-frontend
Frontend development skill for React, Next.js, TypeScript, and Tailwind CSS applications. Use when building React components, optimizing Next.js performance, analyzing bundle sizes, scaffolding frontend projects, implementing accessibility, or reviewing frontend code quality.
screen-reader-testing
Test web applications with screen readers including VoiceOver, NVDA, and JAWS. Use when validating screen reader compatibility, debugging accessibility issues, or ensuring assistive technology support.
threejs-fundamentals
Three.js scene setup, cameras, renderer, Object3D hierarchy, coordinate systems. Use when setting up 3D scenes, creating cameras, configuring renderers, managing object hierarchies, or working with transforms.
onejs-setup-and-overview
Use this skill whenever the user wants to build or set up user interface in a Unity project using OneJS, React, TypeScript, or JSX, e.g. 'add a main menu to my game', 'build a settings screen', 'make a HUD', 'set up OneJS', 'my OneJS panel is blank', 'the UI is not hot reloading'. Covers confirming OneJS is installed…
apply-mantel-styles
Provides guidelines for applying Mantel's brand styles to diagrams and frontend components. Use when asked to create visuals that need to align with Mantel's branding.