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/sacredvoid/skillkit/creative-code-labnpx skills add sacredvoid/skillkit --skill creative-code-labgit clone --depth 1 https://github.com/sacredvoid/skillkitWhat 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 | $0.00113 | $0.05697 |
| Opus 5 | $0.00056 | $0.02848 |
| Sonnet 5 | $0.00023 | $0.01139 |
| Haiku 4.5 | $0.00011 | $0.00570 |
Grade A, and why
creative-code-lab 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 yesterday.
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 — 597 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Creative Code Lab
Generate interactive generative art and creative coding sketches. Inspired by Leisure Lab (43 sketches by KainXu).
Overview
Creative coding = algorithms made visible. Every sketch transforms math into something you can see, touch, and feel.
The output format is flexible: single self-contained HTML file, React component, Next.js page, p5.js sketch, or raw Canvas/WebGL - whatever fits the user's project.
When to Use
- User wants generative/procedural art
- Building animated backgrounds or hero sections
- Creating interactive visual experiments
- Implementing particle systems, flow fields, shaders, fractals
- "Make something cool/beautiful with code"
- Image-to-art transformations
- Creative 404 pages, loading screens, visual flourishes
Technique Catalog
Pick the right approach for the visual:
What visual are you building?
|
+-- Flowing, organic motion?
| +-- Particles following forces --> Flow Field (Perlin noise)
| +-- Smooth color blending --> Fluid Shader (WebGL fragment)
| +-- Swirling paint effect --> Fluid Swirl (iterative sine + spiral distortion)
|
+-- Nature / biology?
| +-- Trees, plants, corals --> L-System (recursive branching)
| +-- Cell division, growth --> Cellular Automata (neighbor rules)
| +-- Veins, rivers, cracks --> Diffusion-Limited Aggregation
|
+-- Geometric / mathematical?
| +-- Mondrian, grids --> Recursive Subdivision
| +-- Space-filling patterns --> Hilbert/Peano Curves
| +-- Spirals, roses --> Polar Coordinate Math
| +-- Vortex patterns --> Parametric equations in (r, theta)
|
+-- Text effects?
| +-- Text from particles --> Canvas pixel sampling + particle system
| +-- Neon glow --> CSS text-shadow stacking or shader
| +-- Glitch effect --> Random clip-path + color channel offset
| +-- Blur/reveal --> CSS filter animation or shader blur
|
+-- Interactive / mouse-driven?
| +-- Particles scatter from cursor --> Distance-based force repulsion
| +-- Drawing / painting --> Canvas stroke with velocity-based width
| +-- Cursor trail effects --> Ring buffer of positions + fade
|
+-- 3D scenes?
| +-- Product showcase --> Three.js + GLTF + orbit controls
| +-- Abstract geometry --> Three.js + custom shaders
| +-- Camera depth blur --> Three.js postprocessing (DOF)
|
+-- Image transformation?
+-- Photo to painting --> Algorithmic brush strokes on canvas
+-- Pointillism / dots --> Pixel sampling + circle rendering
+-- Pixel decomposition --> Grid sampling + animated scatter
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.
- yesterday First seen · 597 lines · 113 tokens per session scan A 29fd733be936
creative-code-lab is a skill published in the GitHub repository sacredvoid/skillkit (10 stars, last pushed 5mo ago), licensed MIT. It adds 113 tokens to every session and 5,697 once invoked, about $0.0006 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
image-fetcher
Fetch relevant, high-quality, free-to-use images from the web. Accepts a description/query, or scans the current directory for context. Sources from Unsplash, Pexels, and Pixabay APIs (if keys configured) with a zero-config WebSearch fallback.
self-improvement
Captures lessons and promotes recurring patterns.
building-mcp-servers
Authors an MCP server with the official SDK and gates.
requirements-elicitation
Turns vague intent into testable requirements.
using-superpowers
Activates the dojo framework at the start of a session.
codebase-onboarding
Maps an unfamiliar repo before touching its code.