Estella is a 2D and 3D game engine with a TypeScript interface, a C++/WebAssembly core, and a visual editor that also acts as an MCP server. It helps developers create, test, and export games for the web, desktop, mini-game platforms, playable ads, and native mobile devices. Its catalogue add-ons let coding agents operate the editor through the same tool surface used by its interface.
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 esengine/estella --skill estella-multiplayergit clone --depth 1 https://github.com/esengine/estellaWrote 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/esengine/estella/estella-multiplayer)<a href="https://agentmods.dev/skills/esengine/estella/estella-multiplayer"><img src="https://agentmods.dev/badge/skills/esengine/estella/estella-multiplayer/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/esengine/estella/estella-multiplayer"><img src="https://agentmods.dev/badge/skills/esengine/estella/estella-multiplayer.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 | $0.00074 | $0.01189 |
| Opus 5.5 | $0.00030 | $0.00476 |
| Sonnet 5.5 | $0.00015 | $0.00238 |
| Haiku 4.5 | $0.00007 | $0.00119 |
Grade A, and why
estella-multiplayer 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 today.
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 — 69 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Multiplayer
Start from the online-3d template (list_project_templates): a server-authoritative world where each player steers a
pawn, the server decides where it is, and your own pawn answers the key at once. Its README says where everything lives.
Build on it rather than wiring replication from nothing.
Everything networked is imported from esengine/replication (and esengine/persist, esengine/zones,
esengine/metrics), never from esengine: the root entry does not export it, and a wrong import fails at build time.
The shape: one set of rules, two ends
- A component is replicated by naming its fields:
defineComponent('Hp', { hp: 100 }, { replicatedFields: ['hp'] }). An entity is sent to clients when it hasReplicated({ owner: connectionId }makes it that player's). - Movement and anything a server must be able to refuse lives in one function both ends run: the server applies each
connection's input with it, the client predicts with it (
net.client.enablePrediction({ apply, smoothing })). Keep it free of the keyboard and the clock; it gets the actions anddt. - How a replicated entity is built on a client (mesh, material) is
registerReplicationArchetype(key, build), so the server sends a key and not a scene. - The server:
app.getResource(Net).startServer(options), thenserver.attachConnection(transport)for each socket andserver.detachConnection(id)when it closes. The template'sserver/main.tsdoes this overws. A browser client connects withNet.connect(new GameSocket({ url }), options). - Game messages that are not state (a chat line, "open the shop") are
server.message(id, type, data)/server.onMessage(type, handler)andclient.message/client.onMessage.
Who a player is
Anonymous by default: a player who reconnects is a stranger. Pass authenticate: (credentials) => ({ playerId }) to
startServer (throw to refuse) and credentials plus reconnect: true to connect; a player who drops keeps their
connection id, and their pawn, for reconnectGraceMs. Spawn and retire pawns from server.presentIds, not from the
live sockets, or a reconnect finds its pawn gone. What the credentials are and who checks them is the game's.
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.
- today First seen · 69 lines · 74 tokens per session scan A 60832224ea8a
estella-multiplayer is a skill published in the GitHub repository esengine/estella (1,174 stars, last pushed today), licensed Apache-2.0. It adds 74 tokens to every session and 1,189 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 2026-11-19.
estella-multiplayer compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| estella-multiplayeresengine/estella | Skill | 1.2k | today | Apache-2.0 | A | 74 | Claude Code, Codex |
| cougr-game-startersalazarsebas/Cougr | Skill | 53 | 28d ago | MIT | A | 68 | Claude Code, Codex |
| hearth-artechoo19/hearth | Skill | 43 | 1mo ago | MIT | A | 89 | Claude Code |
| hearth-feelechoo19/hearth | Skill | 43 | 1mo ago | MIT | A | 97 | Claude Code |
| hearth-buildechoo19/hearth | Skill | 43 | 1mo ago | MIT | A | 75 | Claude Code |
| hearth-codeechoo19/hearth | Skill | 43 | 1mo ago | MIT | A | 88 | Claude Code |
| hearth-designechoo19/hearth | Skill | 43 | 1mo ago | MIT | A | 109 | Claude Code |