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 linegel/threejs-complete-set-of-skill --skill threejs-sky-atmosphere-and-hazegit clone --depth 1 https://github.com/linegel/threejs-complete-set-of-skillWrote 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/linegel/threejs-complete-set-of-skill/threejs-sky-atmosphere-and-haze)<a href="https://agentmods.dev/skills/linegel/threejs-complete-set-of-skill/threejs-sky-atmosphere-and-haze"><img src="https://agentmods.dev/badge/skills/linegel/threejs-complete-set-of-skill/threejs-sky-atmosphere-and-haze/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/linegel/threejs-complete-set-of-skill/threejs-sky-atmosphere-and-haze"><img src="https://agentmods.dev/badge/skills/linegel/threejs-complete-set-of-skill/threejs-sky-atmosphere-and-haze.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 | $0.00050 | $0.01843 |
| Opus 5.5 | $0.00020 | $0.00737 |
| Sonnet 5.5 | $0.00010 | $0.00369 |
| Haiku 4.5 | $0.00005 | $0.00184 |
Grade A, and why
threejs-sky-atmosphere-and-haze 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 1mo 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 — 184 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Sky, Atmosphere, and Haze
Build every branch around one atmosphere model, one scene-linear HDR path, and one final-output owner.
Process
1. Select the transport claim
Choose the least expensive branch that supports the requested observable:
| Need | Branch | Valid claim |
|---|---|---|
| Regional authored sky, distance haze, or height haze | SkyMesh plus TSL fog/haze |
Authored appearance in a bounded local frame |
| Real-time planetary sky and aerial perspective | Compact Hillaire-style LUTs | Approximate higher-order transport within measured error |
| Fixed atmosphere with stricter spectral/angular accuracy | Bruneton-style scattering orders or an offline solve | Accuracy demonstrated against the chosen reference |
Use the compact branch for changing cameras and suns. Use the higher-order branch when its regeneration cost and higher-dimensional products fit the actual workload. Keep an offline integrator as reference evidence rather than visible-pixel runtime work.
Complete when: the implementation names one branch, its supported spatial domain, its physical-versus-authored claim, and the error or visual criterion that admits it.
2. Establish one model
Declare one length unit for radii, positions, and integration steps; store
extinction/scattering coefficients in its reciprocal unit so
beta * ds is dimensionless. Define the body or local frame, origin policy,
altitude model, sun direction convention, spectral/working basis, and whether
the solar source is normal irradiance or finite-disc radiance.
Initialize WebGPURenderer, await renderer.init(), and confirm the native
WebGPU backend before allocating compute/storage products. Use
NoColorSpace for transport data and keep radiance scene-linear until the
host output stage.
For physically dimensioned extinction, LUT radiometry, mapping equations, phase conventions, product dependencies, imported LUT/product compatibility, or the single unit-equivalence fixture, read references/atmosphere-transport.md.
What ships with it
4 files 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.
- 1mo ago Changed · +1 lines 64502345f515
- 2mo ago First seen · 183 lines · 50 tokens per session scan A 4e5c038f2039
threejs-sky-atmosphere-and-haze is a skill published in the GitHub repository linegel/threejs-complete-set-of-skill (11 stars, last pushed 1mo ago), licensed ISC. It adds 50 tokens to every session and 1,843 once invoked, about $0.0002 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 2026-08-31.
Other skills, from other repositories
pixel-art
Pixel art w/ era palettes (NES, Game Boy, PICO-8).
dream-loop
Build stunning 3D scenes via a concept-art fidelity loop.
pokemon-player
Play Pokemon via headless emulator + RAM reads.
minecraft-modpack-server
Host modded Minecraft servers (CurseForge, Modrinth).
cli-anything-renderdoc
CLI harness for RenderDoc graphics debugger capture analysis.
cli-anything-nsight-graphics
Windows-first CLI harness for Nsight Graphics capture, GPU Trace summary, and ngfx-replay analysis.