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 agentmods add skills/manhvann/codexkit/threejsnpx skills add manhvann/codexkit --skill threejsgit clone --depth 1 https://github.com/manhvann/codexkitWhat 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 | $0.00093 | $0.01290 |
| Opus 5 | $0.00046 | $0.00645 |
| Sonnet 5 | $0.00019 | $0.00258 |
| Haiku 4.5 | $0.00009 | $0.00129 |
Grade A, and why
ck:threejs 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 2d 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 — 143 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Three.js Development
Build high-performance 3D web applications using Three.js. Contains 556 searchable examples across 13 categories, 60 API classes, and 20 use-case templates.
When to Use
- Building 3D scenes, games, or visualizations
- Loading 3D models (GLTF, FBX, OBJ)
- Implementing animations, physics, or VR/XR
- Creating particle effects or custom shaders
- Optimizing rendering performance
Search Examples & API
Use the search CLI to find relevant examples and API references:
python3 .agents/skills/threejs/scripts/search.py "<query>" [--domain <domain>] [-n <max_results>]
Search Domains
| Domain | Use For | Example Query |
|---|---|---|
examples |
Find code examples | "particle effects gpu" |
api |
Class/method reference | "PerspectiveCamera" |
use-cases |
Project recommendations | "product configurator" |
categories |
Browse categories | "webgpu" |
Quick Examples
# Find particle/compute examples
python3 .agents/skills/threejs/scripts/search.py "particle compute webgpu"
# Search API for camera classes
python3 .agents/skills/threejs/scripts/search.py "camera" --domain api
# Get examples for a use case
python3 .agents/skills/threejs/scripts/search.py "product configurator" --use-case
# Filter by category
python3 .agents/skills/threejs/scripts/search.py --category webgpu -n 10
# Filter by complexity
python3 .agents/skills/threejs/scripts/search.py --complexity high -n 5
Example Categories
| Category | Count | Description |
|---|---|---|
webgl |
216 | Standard WebGL rendering |
webgpu (wip) |
190 | Modern WebGPU + compute shaders |
webgl / advanced |
48 | Low-level GPU, custom shaders |
webgl / postprocessing |
27 | Bloom, SSAO, SSR, DOF |
webxr |
26 | VR/AR experiences |
physics |
13 | Physics simulation |
Common Use Cases
| Use Case | Recommended | Complexity |
|---|---|---|
| Product Configurator | GLTF, PBR, EnvMaps | Medium |
| Game Development | Animation, Physics, Controls | High |
| Data Visualization | BufferGeometry, Points | Medium |
| 360 Panorama | Equirectangular, WebXR | Low |
| Architectural Viz | GLTF, HDR, CSM Shadows | High |
What ships with it
28 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.
- data/api-reference.csv 8.3 KB
- data/categories.csv 1.9 KB
- data/examples-all.csv 129 KB
- data/use-cases.csv 4.2 KB
- references/00-fundamentals.md 11 KB
- references/01-getting-started.md 3.7 KB
- references/02-loaders.md 4.0 KB
- references/03-textures.md 4.1 KB
- references/04-cameras.md 4.8 KB
- references/05-lights.md 4.3 KB
- references/06-animations.md 4.7 KB
- references/07-math.md 5.1 KB
- references/08-interaction.md 6.6 KB
- references/09-postprocessing.md 5.3 KB
- references/10-controls.md 5.8 KB
- references/11-materials-advanced.md 5.9 KB
- references/11-materials.md 13 KB
- references/12-performance.md 6.5 KB
- references/13-node-materials.md 6.7 KB
- references/14-physics-vr.md 6.7 KB
- references/15-specialized-loaders.md 7.4 KB
- references/16-webgpu.md 7.0 KB
- references/17-shader.md 14 KB
- references/18-geometry.md 13 KB
- scripts/core.py 7.7 KB runs code
- scripts/extract_examples.py 41 KB runs code
- scripts/generate_csv_from_json.py 4.7 KB runs code
- scripts/search.py 2.7 KB runs code
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.
- 2d ago First seen · 143 lines · 93 tokens per session scan A 9b9d695c38d0
ck:threejs is a skill published in the GitHub repository manhvann/codexkit (88 stars, last pushed 3d ago), licensed MIT. It adds 93 tokens to every session and 1,290 once invoked, about $0.0005 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 2026-08-30.
Other skills, from other repositories
general-video
Author or edit a custom HyperFrames composition when no specialized workflow fits, or when BRIEF.md sets flow: companion. Use for longer or multi-scene pieces, brand and sizzle reels, montages, static loops, static title cards, footage remixes, and freeform builds. Use motion-graphics instead for a short unnarrated…
media-ingest
Ingest video, audio, PDF, book, screenshot, and GitHub repo content into the brain. Multi-format handling with entity extraction and backlink propagation. Covers video-ingest, youtube-ingest, and book-ingest subtypes.
diagnostic-stem-delivery
Audio production with diagnostic analysis, timecode parsing from documents, and verified export workflow.
vox-director
Turn ONE topic into a finished Vox-style paper-collage explainer / ad video, end to end on the Atlas Cloud API + local ffmpeg — script, collage keyframes, motion, voice-over, music, captions, all automated. Use this whenever the user wants a "Vox style" video, a paper/torn-paper collage animation, a "motion collage"…
seedance-vocab-ja
This skill should be used when the user asks for Japanese Seedance 2.0 prompt wording, Japanese cinematic vocabulary, or translation of camera, lighting, action, VFX, audio, and production terms into Japanese.
model-compatibility
Model family compatibility matrix covering loaders, resolutions, samplers, CFG, VAE, ControlNet, and LoRA compatibility for SD 1.5, SDXL, Flux, SD3, and video models.