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-procedural-vegetationgit 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-procedural-vegetation)<a href="https://agentmods.dev/skills/linegel/threejs-complete-set-of-skill/threejs-procedural-vegetation"><img src="https://agentmods.dev/badge/skills/linegel/threejs-complete-set-of-skill/threejs-procedural-vegetation/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-procedural-vegetation"><img src="https://agentmods.dev/badge/skills/linegel/threejs-complete-set-of-skill/threejs-procedural-vegetation.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 | $0.00043 | $0.02243 |
| Opus 5.5 | $0.00017 | $0.00897 |
| Sonnet 5.5 | $0.00009 | $0.00449 |
| Haiku 4.5 | $0.00004 | $0.00224 |
Grade A, and why
threejs-procedural-vegetation 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 — 209 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Procedural Vegetation
Build vegetation as a compiler: stable environmental causes become immutable
placement/topology records, while wind and interaction remain separately owned
dynamic state. The canonical path uses Three.js r185 WebGPURenderer, TSL,
NodeMaterial, and workload-selected compute/storage.
1. Define the observable and owners
Classify every requested result before selecting APIs:
| Branch | Requested observable | Vegetation owns |
|---|---|---|
| dense population | grass, flowers, ground cover, repeated shrubs/trees | placement identity, pages, representations, deformation bindings |
| tree growth | trunks, roots, branches, foliage, rooted wind | growth hierarchy, geometry, structural response, LOD |
| terrain ecology | populations caused by terrain or site fields | species response, candidate conflicts, stable acceptance |
Name the coordinate frame, world unit, characteristic plant scale, target cameras/extents, update frequency, output owner, and external field owners. Terrain, weather, water, contact, and lighting remain with their routed owners; vegetation consumes versioned samples from them.
This step is complete when every requested observable has one owner and every external input names its producer, units, frame/chart, support/filter, revision, validity, error, and update cadence.
2. Select representations by population and projected error
| Workload | Default representation |
|---|---|
| one or a few close trees | CPU/worker growth compile into indexed buffers |
| repeated trees or shrubs | compatible species variants instanced in spatial pages, then geometry LOD and impostors |
| dense grass or ground cover | shared strip/clump geometry with implicit, compact CPU, or storage-backed placement |
| changing placement or topology | compute only the changing records, followed by bounded compaction |
Choose compute from measured changed-data volume, dispatch cost, traffic, and residency. Static CPU-generated vegetation can be the lowest-cost GPU result. For every near/mid/far range, record the representation, transition error, expanded bound, shadow proxy, static bytes, dynamic bytes, and submitted work.
What ships with it
5 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 · +7 lines fa39f6aa2515
- 2mo ago First seen · 202 lines · 43 tokens per session scan A d1614e13c8b2
threejs-procedural-vegetation is a skill published in the GitHub repository linegel/threejs-complete-set-of-skill (11 stars, last pushed 1mo ago), licensed ISC. It adds 43 tokens to every session and 2,243 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.