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-3d-gameplaygit 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-3d-gameplay)<a href="https://agentmods.dev/skills/esengine/estella/estella-3d-gameplay"><img src="https://agentmods.dev/badge/skills/esengine/estella/estella-3d-gameplay/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-3d-gameplay"><img src="https://agentmods.dev/badge/skills/esengine/estella/estella-3d-gameplay.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 | $0.00085 | $0.01335 |
| Opus 5.5 | $0.00034 | $0.00534 |
| Sonnet 5.5 | $0.00017 | $0.00267 |
| Haiku 4.5 | $0.00009 | $0.00134 |
Grade A, and why
estella-3d-gameplay 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 — 75 lines — stays where its author put it; the contents beside it link to each section on GitHub.
3D gameplay
Start from the 3d-starter template (list_project_templates): a lit world with ground, props, a Sun and a sky light,
a capsule Hero you walk with WASD and Space, and a camera that follows it. Change what the task asks for rather than
rebuilding what is there. A world unit is a centimetre (100 to the metre) unless the project says otherwise: a person
is about 160 tall, a walk about 340 a second.
A character that walks and jumps
CharacterController3D is a kinematic mover swept against the world. Each fixed step a system writes velocity.x and
velocity.z (normalise the diagonal) and reads isOnFloor; it leaves velocity.y alone, because the controller carries
gravity there, and sets it only to jump. radius and halfHeight are its capsule, stepHeight what it climbs,
maxSlope (radians) the steepest ground it stands on. The template's src/systems/walk.ts is the pattern: it runs in
Schedule.FixedPreUpdate, where the controller reads it. Movement that turns the body to face where it walks writes
the Transform rotation in the same system.
Physics and triggers
- A solid thing is a
RigidBody3Dand a collider together (BoxCollider3D,SphereCollider3D,CapsuleCollider3D,MeshCollider3Dfor static level geometry).bodyTypeis 0 static (ground, walls), 1 kinematic (moved by code), 2 dynamic (falls and is pushed). A body with no collider falls through the world.configure_physics_bodyis 2D only: add the 3D components withadd_componentorapply_scene_ops. - A trigger (a pickup, a door zone) is a collider with
isSensor: true. A script readsRes(Physics3DEvents):sensorEnterslists{ sensorEntity, visitorEntity },contactEntersthe solid hits. - Collider sizes are half extents and radii in world units, measured from the entity's centre: a 100-unit cube has
halfExtents50, 50, 50.
Camera
The template's src/systems/camera.ts eases the camera toward the character plus an offset, in Schedule.PostUpdate
so it is smooth at the display's rate. A FollowTarget on the camera (target, offsetX/offsetY/offsetZ,
damping, deadzone) does the same without code, but only with followZ on: it is off by default, for flat scenes,
and a 3D camera without it never moves forward or back with the character.
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 · 75 lines · 85 tokens per session scan A 263f20ec09e3
estella-3d-gameplay is a skill published in the GitHub repository esengine/estella (1,174 stars, last pushed today), licensed Apache-2.0. It adds 85 tokens to every session and 1,335 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-3d-gameplay compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| estella-3d-gameplayesengine/estella | Skill | 1.2k | today | Apache-2.0 | A | 85 | Claude Code, Codex |
| arxiv-searchlangchain-ai/deepagents | Skill | 31k | today | MIT | A | 62 | Claude Code, Codex |
| cougr-game-startersalazarsebas/Cougr | Skill | 53 | 28d ago | MIT | A | 68 | Claude Code, Codex |
| petrinauthashintel/hash | Skill | 1.7k | today | none | A | 61 | Claude Code, Codex |
| modellinghashintel/hash | Skill | 1.7k | today | none | A | 46 | 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 |