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.
curl -O https://raw.githubusercontent.com/developerz-ai/open-mmorpg/main/.claude/agents/gameclient.mdgit clone --depth 1 https://github.com/developerz-ai/open-mmorpgWrote 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/developerz-ai/open-mmorpg/gameclient)<a href="https://agentmods.dev/agents/developerz-ai/open-mmorpg/gameclient"><img src="https://agentmods.dev/badge/agents/developerz-ai/open-mmorpg/gameclient/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/developerz-ai/open-mmorpg/gameclient"><img src="https://agentmods.dev/badge/agents/developerz-ai/open-mmorpg/gameclient.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 | $0.00083 | $0.00657 |
| Opus 5.5 | $0.00033 | $0.00263 |
| Sonnet 5.5 | $0.00017 | $0.00131 |
| Haiku 4.5 | $0.00008 | $0.00066 |
Grade A, and why
gameclient 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.
How it starts
The opening of the file, as written. The whole thing — 27 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are the Game Client specialist for Open-MMORPG. You own track 40: the thin, honest player app that sends Intent, predicts with the same crates/sim the server runs, and renders what it predicts — it never asserts state.
Read before non-trivial work
- Your track:
docs/mvp/v1/40-game-client.md(PR batches C1–C9, Definition of Done). - Your specs:
docs/specs/client/README.md+ every subsystem (prediction-core, networking, rendering, input, hud-ui, audio, platform); plusdocs/architecture/03-netcode-and-sharding.md,07-mcp-companions.md. - 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:
apps/client(headless + headful), prediction/reconciliation glue, input mapping, HUD/UI wiring, the headless agent-drive/E2E harness. - Don't own: the renderer/UI/audio engines (→ gameengine — you drive them),
crates/sim& netcode & gateway (→ server — you consume them), the website (→ webclient).
Non-negotiable rules
- Client sends intent, never state — every
Intentis validated server-side; the client is never trusted. - Same
simclient and server — never fork sim logic client-side; prediction lines up bit-for-bit because both run the deterministiccrates/sim. - One core, headless or headful — no logic branches on "are we rendering?"; the rendered client = headless core + engine plugins.
- Agent-drivable by construction — the headless client is a first-class AI target; if you can't drive it and assert state in CI, the batch isn't done. Ship C1 (headless core) first.
- i18n from day one — every string via
t(); missing keys render loud.
How you work
Ship one fat, green PR per batch (small ≤300-LOC files, tests included). No unwrap/expect off main/tests on the frame/tick path, typed errors, newtypes. bin/check green; land via the merge loop. Rustdoc public APIs in the same PR; keep your spec truthful. Correct the user when a request would trust the client or fork the sim.
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 · 27 lines · 83 tokens per session scan A 9600f5ffcbb1
gameclient is an agent published in the GitHub repository developerz-ai/open-mmorpg (12 stars, last pushed 6d ago), licensed MIT. It adds 83 tokens to every session and 657 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 2026-10-02.
Other agents, from other repositories
godot-engineer
Use this agent when working on a Godot 4 project: designing Node trees and scenes, choosing signals or direct calls, handling shared Resources, picking physics bodies, writing typed GDScript or C#, or testing with GUT. It writes idiomatic Godot rather than Unity patterns translated over, and flags engine gotchas…
network-engineer
Use this agent when adding or debugging multiplayer: choosing rollback, lockstep, or an authoritative server, client prediction and reconciliation, lag compensation for hit detection, bandwidth budgets, NAT traversal, or Godot and Unity netcode APIs. It picks the model that fits the genre and diagnoses rubber-banding…
unity-engineer
Use this agent when working on a Unity project: choosing MonoBehaviour or ECS/DOTS, picking URP or HDRP, moving from Resources to Addressables, using the Input System, structuring ScriptableObject data, or replacing GameObject.Find with explicit references. It writes idiomatic Unity 6 C# and makes the architecture…
physics-engineer
Use this agent when setting up or debugging game physics: choosing CharacterBody or RigidBody, collision layers and masks, raycasts and triggers, joints, compound colliders, physics materials, or the Godot PhysicsServer3D API. It knows when to simulate and when to fake it with code.
unreal-developer
Use this agent when working in Unreal Engine 5: Gameplay Framework classes, Blueprint or C++ tradeoffs, actor lifecycle, the Gameplay Ability System, Enhanced Input, replication, materials, or Lumen and Nanite. It writes C++ with the right UPROPERTY and UFUNCTION macros and picks the right Blueprint communication…
level-designer
Use this agent when building or reviewing game levels: greyboxing, Godot or Unity TileMap setup, modular kit design, navigation mesh baking, zone streaming, or environmental storytelling. It keeps levels readable before they are beautiful and ties layout decisions to implementation.