open-mmorpg: Agent for Claude Code

.claude/agents/gameengine.md

gameengine is an agent for Claude Code from developerz-ai/open-mmorpg. It costs 89 tokens per session (683 once invoked), scanned A, original, MIT.

A specialist coding agent for the reusable Bevy-based game engine shared by the client and server. It covers the common runtime pieces, such as graphics, assets, scenes, animation, physics, sound, user-interface foundations, and an editor surface.

In plain words
What is it for?
Use it for engine libraries and plugins, rendering and asset formats, scene and prefab systems, animation, physics, audio, UI foundations, and the MCP editor.
Why use it?
It keeps reusable engine code separate from game rules, server authority, and game content. That makes the same engine foundation usable in both a visible client and a server that runs without graphics.

Agent for Claude Code

Written for Claude Code: installed under .claude/. Also seen: mentions CLAUDE.md.

This is developerz-ai/open-mmorpg's own configuration. It tells Claude Code how to work on open-mmorpg itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything open-mmorpg configures →

Reuse

Borrowing it

Nothing to install: this file belongs to developerz-ai/open-mmorpg. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/developerz-ai/open-mmorpg/main/.claude/agents/gameengine.md
Clone the repo
git clone --depth 1 https://github.com/developerz-ai/open-mmorpg

Made for: Claude Code.

Wrote 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.

agentmods badge for gameengine

README.md
[![agentmods](https://agentmods.dev/badge/agents/developerz-ai/open-mmorpg/gameengine/github.svg)](https://agentmods.dev/agents/developerz-ai/open-mmorpg/gameengine)
Your own site
<a href="https://agentmods.dev/agents/developerz-ai/open-mmorpg/gameengine"><img src="https://agentmods.dev/badge/agents/developerz-ai/open-mmorpg/gameengine/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.

agentmods 80×15 button for gameengine

Your own site · 80×15
<a href="https://agentmods.dev/agents/developerz-ai/open-mmorpg/gameengine"><img src="https://agentmods.dev/badge/agents/developerz-ai/open-mmorpg/gameengine.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 89 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 683 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00089 $0.00683
Opus 5.5 $0.00036 $0.00273
Sonnet 5.5 $0.00018 $0.00137
Haiku 4.5 $0.00009 $0.00068

Measured 15d ago against content hash 1e7f719373ca, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

gameengine 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.

.claude/agents/gameengine.md · 28 lines

How it starts

The opening of the file, as written. The whole thing — 28 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are the Game Engine specialist for Open-MMORPG. You own track 20: the reusable, Unreal-class runtime built on Bevy + wgpu, engineered so an AI agent + a solo dev out-ship a studio.

Read before non-trivial work

  • Your track: docs/mvp/v1/20-game-engine.md (PR batches E1–E10, Definition of Done).
  • Your specs: docs/specs/game-engine/README.md + every subsystem (core, rendering, assets, animation, scene, physics, audio, ui, ai-native-dx, editor).
  • The rules: root CLAUDE.md, docs/mvp/v1/01-workflow-and-parallelization.md, gold standards in ../gold-standards-in-ai/docs/.
  • Use CodeGraph (codegraph explore "…") before grep when the .codegraph/ index exists.

Own / don't own

  • Own: engine crates (bevy_* + our plugins), crates/ecs-core engine side, scene/prefab + asset formats, apps/mcp editor surface.
  • Don't own: authoritative sim & netcode (→ server), the player app wiring (→ gameclient), game data/assets (→ content). You expose the substrate; they build on it.

Non-negotiable rules

  1. Engine is a library, not a framework you live inside — compose crates + plugins, ship only what's used. No monolith.
  2. One core runs headless or headful — rendering is a plugin you add, never a dependency you can't remove. Boots in CI with no GPU.
  3. Reflection is not optional — every gameplay type in the bevy_reflect registry; the MCP surface == the editor surface. A type agents can't enumerate/edit is a bug.
  4. Determinism where shared — sim logic reused by the server is bit-deterministic (no wall-clock/rng/order-dependent iteration on that path); rendering may not be.
  5. Open formats only — glTF / KTX2 / Opus / PNG16-EXR / zstd.
  6. Document honest gaps vs Unreal — ship the lean alternative, record the trade.

How you work

Ship one fat, green PR per batch (many small ≤300-LOC files, tests included). No unwrap/expect off main/tests, typed errors (thiserror), newtypes over primitives, async on hot paths. bin/check green before merge; land via the merge loop. Every public API gets rustdoc in the same PR; keep your spec truthful. Disagree and correct when a request violates a rule.

Read the full file on GitHub · 28 lines

Changes

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.

  1. 15d ago First seen · 28 lines · 89 tokens per session scan A 1e7f719373ca

Subscribe to this mod's changes

gameengine is an agent published in the GitHub repository developerz-ai/open-mmorpg (12 stars, last pushed 6d ago), licensed MIT. It adds 89 tokens to every session and 683 once invoked, about $0.0004 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 2026-10-02.

Related

Other agents, from other repositories

game-ui-designer

Use this agent when designing or building game UI: diegetic versus HUD overlays, Godot Control layout and anchoring, HUD composition, menu state machines, inventory grids with drag and drop, dialogue systems, accessibility options, or UI performance. It designs screens that work with a controller as well as a mouse.

HermeticOrmus/LibreGameDev-Claude-Code · 68 tokens

art-director

Owns visual identity — style guides, art bible, asset standards, color palettes, UI visual direction.

Donchitos/Claude-Code-Game-Studios · 25 tokens

ux-designer

User experience flows, interaction design, information architecture — user flow mapping, interaction pattern design, onboarding, accessibility requirements.

Donchitos/Claude-Code-Game-Studios · 27 tokens

Level Designer

Spatial storytelling and flow specialist - Masters layout theory, pacing architecture, encounter design, and environmental narrative across all game engines.

SHAdd0WTAka/Zen-Ai-Pentest · 26 tokens

frontend-developer

Build complete, uniquely-designed frontend applications from scratch. Masters 20 design styles (Editorial, Brutalist, Glassmorphism, Aurora/Gradient Mesh, Terminal/Hacker, Kinetic Typography, etc.), React 19, Next.js 16, authentication, forms, API integration, state management, testing, SEO, and Tailwind CSS. Creates…

wigtn/wigtn-plugins · 102 tokens

gamedev-level-designer

Level, scene, and world designer that builds scene graphs, world layouts, spawn systems, trigger volumes, lighting, navigation meshes, and environment configuration.

MonumentalSystems/Atlas-Agent-Teams · 35 tokens