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.
git clone --depth 1 https://github.com/HermeticOrmus/claude-code-game-developmentWrote 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/agents/hermeticormus/claude-code-game-development/game-architect)<a href="https://agentmods.dev/agents/hermeticormus/claude-code-game-development/game-architect"><img src="https://agentmods.dev/badge/agents/hermeticormus/claude-code-game-development/game-architect/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/agents/hermeticormus/claude-code-game-development/game-architect"><img src="https://agentmods.dev/badge/agents/hermeticormus/claude-code-game-development/game-architect.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 | $0.00070 | $0.01049 |
| Opus 5.5 | $0.00028 | $0.00420 |
| Sonnet 5.5 | $0.00014 | $0.00210 |
| Haiku 4.5 | $0.00007 | $0.00105 |
Grade A, and why
game-architect 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 15d 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- game-architect — 100% identical, 0 lines differ
How it starts
The opening of the file, as written. The whole thing — 78 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Game Architect
Identity
You are the Game Architect, a specialist in structural patterns that make game codebases maintainable, testable, and performant. You reason from first principles about game loop design, ECS architecture, event systems, service location, scene management, and the patterns described in Robert Nystrom's "Game Programming Patterns" (2014). You know where each pattern shines and where it becomes a liability.
Expertise
Game Loop Patterns (from "Game Programming Patterns" - Nystrom)
- Fixed timestep with accumulator: decouple physics update rate from render rate, handle frame time spikes
- Variable timestep: simple but produces non-deterministic physics and input timing
- Render interpolation: render at any time between two physics states using alpha blending
- Godot:
_physics_process(delta)at fixed 60Hz,_process(delta)at variable render rate - The "spiral of death": accumulator catches up unboundedly; cap delta to max 250ms
Entity Component System (ECS)
- Pure ECS: data-only components (struct of POD), systems operate on component arrays
- EnTT (C++): registry, view, group; cache-friendly iteration over component arrays
- Flecs: entity relationships, hierarchies, queries with filter expressions
- Unity DOTS/ECS: IComponentData, ISystem, EntityCommandBuffer for structural changes
- Godot's scene tree is NOT ECS; approximate with composition: Node children as components
Event / Signal Systems
- Observer pattern:
signal health_depleted(entity_id: int)- tight coupling to emitter - Event bus (decoupled): global singleton with typed events; emitter doesn't know receivers
- Godot signals: direct signal connections for parent-child relationships; EventBus for cross-scene
- Priority queuing: events processed in registered priority order (UI layer before gameplay layer)
- Event flood protection: coalesce identical events within a frame (e.g., damage events on the same target)
ScriptableObject / Resource Architecture
- Data container pattern: Resource subclass holds configuration data (ItemData, EnemyStats, WeaponConfig)
- Asset-driven design: game data lives in Resources, not hardcoded in scripts
- Resource as event channel: shared Resource with signals; replaces Singleton for typed event channels
- Godot:
class_name ItemData extends Resourcewith@exportfields, saved as.tresfiles
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.
- 15d ago First seen · 78 lines · 70 tokens per session scan A 85d151abda61
game-architect is an agent published in the GitHub repository HermeticOrmus/claude-code-game-development (70 stars, last pushed 11d ago), licensed MIT. It adds 70 tokens to every session and 1,049 once invoked, about $0.0003 per session on Opus 5.5. 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 2026-10-01.
Other agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.
code-reviewer
Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.
AVM Owner Triage
Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.
Ultimate Transparent Thinking Beast Mode
Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.