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-shippinggit 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-shipping)<a href="https://agentmods.dev/skills/esengine/estella/estella-shipping"><img src="https://agentmods.dev/badge/skills/esengine/estella/estella-shipping/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-shipping"><img src="https://agentmods.dev/badge/skills/esengine/estella/estella-shipping.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 | $0.00079 | $0.01109 |
| Opus 5.5 | $0.00032 | $0.00444 |
| Sonnet 5.5 | $0.00016 | $0.00222 |
| Haiku 4.5 | $0.00008 | $0.00111 |
Grade A, and why
estella-shipping 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.
Shipping
A game is shipped when it runs on the target, not when the export says ok. The order: check, export, read the report, then see it run there.
Before exporting
save_scene: an export reads what is on disk, and unsaved changes are a blocker.get_project_health { target }is the Build dialog's own preflight. Ablockerstops the export; awarningships and is worth reading (an empty required field is one).unavailablelists checks that did not run, not checks that passed.- Every scene in the scenes folder ships unless it was unticked in the Build dialog; the startup scene always does. A playable ships the startup scene only.
Export
export_game { platform } with platform one of web, desktop, wechat and the other mini-game targets the
Build dialog lists, playable, android, ios. It writes dist-<platform>/ unless outDir says otherwise.
- A content blocker (a dead reference, unsaved changes, no entry scene) can be passed with
acknowledgeBlockers: trueonly when you can say why it does not matter; a missing toolchain cannot be passed. - Compression is off unless the call or the chosen
profileasks for it:compressTextures(KTX2),compressAudio(WAV to MP3) andatlasTexturesfollow each asset's Import Settings. Turn them on for a release, not for a quick check. A texture whose width or height is not a multiple of 4 ships raw, and the warning names it. profilepicks one of the project's saved export profiles;debugChannel: truemakes a development build that connects back to this editor (below).
Size
The result weighs the package: initial (downloaded before the game plays), on demand (subpackages) and CDN (remote asset groups, outside the package). Limits are reported, not enforced:
- WeChat: 4 MB main package, 30 MB with all subpackages. Move levels behind subpackages or remote groups; a game that never uses particles, post-processing or tilemaps gets the smaller engine on its own.
- Playable: one
index.htmlwith everything inlined, at most what the chosen ad network accepts (often 5 MB).webpImages("lossless", 90, 80) shrinks its images; the game callsplayableCta()where the player is sent to the store and never names a network. - Web, desktop, Android, iOS: no published limit; read the largest files the report lists anyway.
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 · 79 tokens per session scan A be0c769c1fa5
estella-shipping is a skill published in the GitHub repository esengine/estella (1,174 stars, last pushed today), licensed Apache-2.0. It adds 79 tokens to every session and 1,109 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-shipping compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| estella-shippingesengine/estella | Skill | 1.2k | today | Apache-2.0 | A | 79 | Claude Code, Codex |
| scaffold-projectMarve10s/Better-Fullstack | Skill | 824 | today | MIT | A | 80 | Claude Code |
| init-projectwataru-maeda/react-native-boilerplate | Skill | 525 | 3d ago | MIT | A | 50 | Claude Code, Codex |
| expo-moduleopenai/plugins | Skill | 8.0k | today | none | A | 59 | Codex |
| capacitor-plugin-developmentcapawesome-team/skills | Skill | 56 | 4d ago | MIT | A | 117 | Claude Code, Codex |
| build-swiftui-interfacememi-design/memi | Skill | 51 | 5d ago | MIT | A | 45 | Claude Code |
| unistyles-v2-to-v3-migrationjpudysz/react-native-unistyles | Skill | 3.0k | 2d ago | none | A | 104 | Claude Code |