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 CesiumGS/cesiumjs-ai-starter-app --skill czml-modelgit clone --depth 1 https://github.com/CesiumGS/cesiumjs-ai-starter-appWrote 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/cesiumgs/cesiumjs-ai-starter-app/czml-model)<a href="https://agentmods.dev/skills/cesiumgs/cesiumjs-ai-starter-app/czml-model"><img src="https://agentmods.dev/badge/skills/cesiumgs/cesiumjs-ai-starter-app/czml-model/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/cesiumgs/cesiumjs-ai-starter-app/czml-model"><img src="https://agentmods.dev/badge/skills/cesiumgs/cesiumjs-ai-starter-app/czml-model.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 | $0.01118 |
| Opus 5 | $0.00042 | $0.00559 |
| Sonnet 5 | $0.00017 | $0.00224 |
| Haiku 4.5 | $0.00008 | $0.00112 |
Grade A, and why
czml-model 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 11d 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 — 79 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CZML Model
- "model":
{ "gltf": "<URI or data URI>", "scale": <number>, "minimumPixelSize": <number>, "maximumScale": <number>, "show": true|false }— a 3D glTF model positioned and oriented by the entity's "position"/"orientation". When the intent asks for a 3D model, always include this property; do not substitute a point, label, or geometric primitive. - "gltf" may be a URL or a complete data URI. Use a URL supplied by the intent when present.
Otherwise, select the closest trusted Cesium sample asset below. Do not invent a URL and do not
emit a truncated or placeholder data URI, because neither can load:
- humanoid, person:
https://raw.githubusercontent.com/CesiumGS/cesium/main/Apps/SampleData/models/CesiumMan/Cesium_Man.glb - aircraft, airplane:
https://raw.githubusercontent.com/CesiumGS/cesium/main/Apps/SampleData/models/CesiumAir/Cesium_Air.glb - vehicle, car, crane:
https://raw.githubusercontent.com/CesiumGS/cesium/main/Apps/SampleData/models/GroundVehicle/GroundVehicle.glb - rocket, launch vehicle:
https://cesium.com/public/SandcastleSampleData/launchvehicle.glb
- humanoid, person:
- "minimumPixelSize": keeps the model visible (at this minimum screen size) even when the camera is far away; "maximumScale" caps how large that minimum-size behavior can scale the model.
- "nodeTransformations":
{ "<nodeName>": { "translation": { "cartesian": [x, y, z] }, "rotation": { "unitQuaternion": [x, y, z, w] }, "scale": { "cartesian": [x, y, z] } } }— applies a translation/rotation/scale to one named node inside the model (e.g. a joint or moving part), keyed by the node's name in the glTF asset. - "articulations":
{ "<stage name> <articulation name>": <number> }— sets a named glTF Articulation stage to a numeric value (the key is the stage name, a single space, then the articulation name, e.g."turret spin"). For a value that animates over time, use the same "epoch" + interleaved-timestamp-and-value pattern as any other sampled property:{ "epoch": "<ISO8601>", "turret spin": [t0, v0, t1, v1, ...] }.
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.
- 11d ago First seen · 79 lines · 83 tokens per session scan A bc463f5c5506
czml-model is a skill published in the GitHub repository CesiumGS/cesiumjs-ai-starter-app (7 stars, last pushed 13d ago), licensed Apache-2.0. It adds 83 tokens to every session and 1,118 once invoked, about $0.0004 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 2026-08-31.
Other skills, from other repositories
latex-compile
Compile a LaTeX document and fix every error plus aesthetic issue (overfull/underfull boxes, widows, alignment, fonts) for a clean PDF and log. Use this instead of running pdflatex/latexmk manually — it avoids the latexmk stale-log trap and silent grep failures on binary log output, and it reformats rather than…
nb-to-wolfbook
Convert Mathematica .nb or .m files to Wolfbook .wb format so they open and run in VS Code. Use when bringing existing .nb/.m files into Wolfbook, or to make an existing .wb bridge-safe.
sync-wb-nb
Propagate a change made in a Wolfbook .wb notebook into the paired .nb notebook so the two stay identical. Use immediately after every .wb edit.
wolfram-headless
Run heavy Wolfram Language (wolframscript) computations from Claude Code reliably, and diagnose the misleading "The product exited because of a license error". Use whenever invoking wolframscript on a non-trivial computation, when a wolframscript job dies with a "license error" despite a valid license, or when Wolfram…
cross-validate
Format a result, derivation, or numerical value for independent verification by a second model. Use when you want a cross-check on an important or contested result.
verify-citation
Confirm a paper actually exists (arXiv / Semantic Scholar / OpenAlex) before citing it. Use before writing any new citation.