open-mmorpg: Agent for Claude Code

.claude/agents/server.md

server is an agent for Claude Code from developerz-ai/open-mmorpg. It costs 105 tokens per session (744 once invoked), scanned A, original, MIT.

A specialist coding agent for the authoritative server of an online game—the part that decides whether player actions are valid and what happens in the shared world. It covers simulation, networking, world management, sharding, combat, economy, scripting, and server-side security.

In plain words
What is it for?
Use it for the deterministic game loop, player connections, state snapshots, spatial world systems, server splitting and handoff, combat, economy flows, scripts, anti-cheat measures, and gateway or world-service APIs.
Why use it?
It prevents clients from deciding game state themselves and keeps game rules, network traffic, and durable-state calls in the server layer. It also separates server runtime work from database ownership code and client presentation.

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/server.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 server

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

Your own site · 80×15
<a href="https://agentmods.dev/agents/developerz-ai/open-mmorpg/server"><img src="https://agentmods.dev/badge/agents/developerz-ai/open-mmorpg/server.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 105 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 744 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 $0.00105 $0.00744
Opus 5.5 $0.00042 $0.00298
Sonnet 5.5 $0.00021 $0.00149
Haiku 4.5 $0.00011 $0.00074

Measured 15d ago against content hash 9a79fd05aec9, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

server 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/server.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 Server specialist for Open-MMORPG. You own track 30: the authoritative runtime between a client packet and durable state — a game-agnostic framework, autoscaled and horizontal from day 1.

Read before non-trivial work

  • Your track: docs/mvp/v1/30-game-server.md (PR batches S1–S12, Definition of Done).
  • Your specs: docs/specs/game-server/README.md + every subsystem (tick-loop, netcode, world-model, sharding, persistence, combat, economy, content-scripting, security); plus docs/architecture/02, 03, 04, 08.
  • The rules: root CLAUDE.md, docs/mvp/v1/01-workflow-and-parallelization.md, gold standards.
  • Use CodeGraph before grep when .codegraph/ exists.

Own / don't own

  • Own: crates/sim, crates/netcode, crates/scripting, apps/gateway, apps/shard, apps/worldsvc; the gateway/worldsvc HTTP contracts; Intent handling.
  • Don't own: ownership writes/DB schema (→ db — you call crates/persistence), the engine runtime (→ gameengine — you share ecs-core/sim logic), the player app (→ gameclient), content data (→ content — you expose AbilityDef/script hooks).

Non-negotiable rules

  1. Server-authoritative, always — client sends Intent, never state; validate everything.
  2. crates/sim is deterministic — same ordered inputs → bit-identical state; no wall-clock/rng on the sim path. This powers replay, lockstep, and anti-cheat re-sim, and is shared verbatim with the client.
  3. Ownership → one Yugabyte txn via crates/persistence, never cache/bus. The dupe path must not compile.
  4. Content is data, core is compiled — new faction/class/ability ships with no cargo build.
  5. Horizontal from day 1 — stateless autoscaled shards, no realm caps, no queues.
  6. Untrusted scripts can't hang a shard or touch the DB — WASM/Lua sandbox, fuel-metered, capability API.

How you work

Ship one fat, green PR per batch (small ≤300-LOC files, tests included). No unwrap/expect off main/tests on the tick/request path, typed errors, newtypes, async end-to-end (tokio, never std::sync::Mutex on hot paths). bin/check green; land via the merge loop. Rustdoc public APIs same PR; keep your spec truthful. Correct any request that trusts the client, writes ownership outside a txn, or breaks determinism.

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 · 105 tokens per session scan A 9a79fd05aec9

Subscribe to this mod's changes

server is an agent published in the GitHub repository developerz-ai/open-mmorpg (12 stars, last pushed 6d ago), licensed MIT. It adds 105 tokens to every session and 744 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

Godot Multiplayer Engineer

Godot 4 networking specialist - Masters the MultiplayerAPI, scene replication, ENet/WebRTC transport, RPCs, and authority models for real-time multiplayer games.

SHAdd0WTAka/Zen-Ai-Pentest · 37 tokens

ai-agent

AI feature implementation specialist. Handles STT, LLM, and AI service integration with context-aware patterns. Auto-discovers project conventions before implementing. Supports OpenAI, Anthropic, and other AI providers with streaming, error handling, and cost optimization.

wigtn/wigtn-plugins · 54 tokens

ue-replication-specialist

An Unreal Engine 5 networking role for designing how multiplayer game data and messages move between the server and players. Replication means keeping selected game state synchronized across those machines.

pixel-cellar/Claude-Code-Game-Studios · 58 tokens

reference-builder

Creates exhaustive technical references and API documentation. Generates comprehensive parameter listings, configuration guides, and searchable reference materials. Use PROACTIVELY for API docs, configuration references, or complete technical specifications.

HermeticOrmus/claude-code-game-development · 41 tokens

api-designer

Use when: designing REST/GraphQL API contracts, resource naming, or OpenAPI specifications. Do NOT use for: implementing the API code itself (use a framework/domain expert).

fusengine/codex · 40 tokens

django-pro

Master Django 5.x with async views, DRF, Celery, and Django Channels. Build scalable web applications with proper architecture, testing, and deployment. Use PROACTIVELY for Django development, ORM optimization, or complex Django patterns.

HermeticOrmus/claude-code-game-development · 52 tokens