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 calesthio/generative-media-skills --skill world-labs-marblegit clone --depth 1 https://github.com/calesthio/generative-media-skillsWrote 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/calesthio/generative-media-skills/world-labs-marble)<a href="https://agentmods.dev/skills/calesthio/generative-media-skills/world-labs-marble"><img src="https://agentmods.dev/badge/skills/calesthio/generative-media-skills/world-labs-marble/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/calesthio/generative-media-skills/world-labs-marble"><img src="https://agentmods.dev/badge/skills/calesthio/generative-media-skills/world-labs-marble.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00204 | $0.05345 |
| Opus 5 | $0.00102 | $0.02672 |
| Sonnet 5 | $0.00041 | $0.01069 |
| Haiku 4.5 | $0.00020 | $0.00534 |
Grade A, and why
world-labs-marble 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 9d 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 — 392 lines — stays where its author put it; the contents beside it link to each section on GitHub.
World Labs Marble
Marble is World Labs' commercial multimodal world model: it lifts a text prompt, image(s), video, panorama, or coarse 3D blocking into a persistent, downloadable 3D environment you can navigate, edit, expand, and export. World Labs was co-founded by Fei-Fei Li; Marble reached general availability on 2025-11-12 and a programmatic World API was announced 2026-01-21. (Documented; verified 2026-07-10.)
The defining property, and the thing that separates Marble from most "generative video" or interactive world models: the world is materialized as persistent 3D geometry (Gaussian splats and/or meshes) that you own as a file, rather than hallucinated frame-by-frame as you walk. That makes it usable as a production asset, not just a demo you watch. (Documented — worldlabs.ai blog; verified 2026-07-10.)
When to use this skill
Use it when the deliverable is a 3D space:
- An explorable environment for VR (Quest 3, Vision Pro), a web viewer, or a game engine.
- A virtual-production / previz backdrop, a set blockout, or an environment concept that must hold up from multiple camera angles.
- A programmatic pipeline that needs many worlds generated on demand (World API).
- Turning a single photo, concept art, or a location video into a navigable set.
Do not reach for Marble when the user wants a flat image (use an image model), a short talking/action video clip (use a video model), or a real-time game engine that streams infinite world on the fly. Marble worlds are bounded, static environments — extremely detailed, but not simulations with moving actors or physics baked in.
Access routes (verify — these are volatile)
As of 2026-07-10 there are two first-party routes; both are live:
| Route | Where | Auth | Billing | Best for |
|---|---|---|---|---|
| Marble web app | marble.worldlabs.ai |
Account login | Monthly subscription (Free/Standard/Pro/Max) | Hands-on authoring, Chisel, Studio (Compose/Record), interactive editing |
| World API | platform.worldlabs.ai, endpoint base api.worldlabs.ai/marble/v1 |
WLT-Api-Key header |
Prepaid credits (separate wallet) | Automated/batch generation, product integrations |
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 9d ago First seen · 392 lines · 204 tokens per session scan A 2bc175079905
world-labs-marble is a skill published in the GitHub repository calesthio/generative-media-skills (170 stars, last pushed 2mo ago), licensed MIT. It adds 204 tokens to every session and 5,345 once invoked, about $0.0010 per session on Opus 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 2026-09-03.
Other skills, from other repositories
threejs-animation
Three.js animation - keyframe animation, skeletal animation, morph targets, animation mixing. Use when animating objects, playing GLTF animations, creating procedural motion, or blending animations.
threejs-geometry
Three.js geometry creation - built-in shapes, BufferGeometry, custom geometry, instancing. Use when creating 3D shapes, working with vertices, building custom meshes, or optimizing with instanced rendering.
threejs-fundamentals
Three.js scene setup, cameras, renderer, Object3D hierarchy, coordinate systems. Use when setting up 3D scenes, creating cameras, configuring renderers, managing object hierarchies, or working with transforms.
threejs-world-generation
Build deterministic, editable, free-viewpoint Three.js worlds from text or structured briefs. Use for cinematic 3D terrain, semantic regions, procedural biomes, explicit landmarks, environmental scattering, camera fly-throughs, world diagnostics, or requests for a real 3D environment rather than generated 2D footage.…
3d-asset-generation
Generate, reconstruct, inspect, and route production 3D assets for OpenMontage worlds using Atlas Cloud, fal.ai, licensed catalogs, and Blender.
sound-effects
Generate sound effects from text descriptions using ElevenLabs. Use when creating sound effects, generating audio textures, producing ambient sounds, cinematic impacts, UI sounds, or any audio that isn't speech. Supports looping, duration control, and prompt influence tuning.