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/shadernpx skills add manhvann/codexkit --skill shadergit 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 | $0.00065 | $0.01133 |
| Opus 5 | $0.00032 | $0.00566 |
| Sonnet 5 | $0.00013 | $0.00227 |
| Haiku 4.5 | $0.00006 | $0.00113 |
Grade A, and why
ck:shader 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 — 114 lines — stays where its author put it; the contents beside it link to each section on GitHub.
GLSL Fragment Shaders
Write GPU-accelerated fragment shaders for procedural graphics, textures, and visual effects.
When to Use
- Creating procedural textures (wood, marble, clouds, terrain)
- Drawing shapes with distance fields (SDF)
- Generating patterns, noise, gradients
- Building visual effects and animations
- Writing custom shaders for Three.js, WebGL, Processing
Core Concepts
Fragment shaders execute simultaneously on every pixel. Each thread:
- Receives pixel position via
gl_FragCoord - Returns color via
gl_FragColor(vec4: RGBA 0.0-1.0) - Cannot communicate with other threads (stateless)
Standard Uniforms
uniform float u_time; // Elapsed seconds
uniform vec2 u_resolution; // Canvas size (width, height)
uniform vec2 u_mouse; // Mouse position in pixels
Normalize coordinates: vec2 st = gl_FragCoord.xy / u_resolution;
Essential Functions
| Function | Purpose | Example |
|---|---|---|
mix(a,b,t) |
Linear interpolate | mix(red, blue, 0.5) |
step(edge,x) |
Hard threshold | step(0.5, st.x) |
smoothstep(e0,e1,x) |
Smooth threshold | smoothstep(0.2, 0.8, st.x) |
fract(x) |
Fractional part | fract(st * 3.0) for tiling |
mod(x,y) |
Modulo | mod(st.x, 0.25) |
clamp(x,min,max) |
Constrain value | clamp(col, 0.0, 1.0) |
length(v) |
Vector magnitude | length(st - 0.5) |
distance(a,b) |
Euclidean distance | distance(st, center) |
dot(a,b) |
Dot product | dot(normal, lightDir) |
normalize(v) |
Unit vector | normalize(direction) |
atan(y,x) |
Angle (radians) | atan(st.y-0.5, st.x-0.5) |
sin/cos/pow/abs |
Math | Hardware-accelerated |
Quick Patterns
Circle:
float d = distance(st, vec2(0.5));
float circle = 1.0 - smoothstep(0.2, 0.21, d);
Rectangle:
vec2 bl = step(vec2(0.1), st);
vec2 tr = step(vec2(0.1), 1.0 - st);
float rect = bl.x * bl.y * tr.x * tr.y;
Tiling:
st = fract(st * 4.0); // 4x4 grid
What ships with it
12 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.
- references/glsl-cellular-voronoi-worley-noise-patterns.md 3.3 KB
- references/glsl-colors-rgb-hsb-gradients-mixing-color-spaces.md 3.1 KB
- references/glsl-fbm-fractional-brownian-motion-turbulence-octaves.md 3.0 KB
- references/glsl-fundamentals-data-types-vectors-precision-coordinates.md 2.4 KB
- references/glsl-noise-random-perlin-simplex-cellular-voronoi.md 2.8 KB
- references/glsl-pattern-symmetry-truchet-domain-warping.md 2.8 KB
- references/glsl-patterns-tiling-fract-matrices-transformations.md 2.4 KB
- references/glsl-procedural-textures-clouds-marble-wood-terrain.md 3.0 KB
- references/glsl-shader-builtin-functions-complete-api-reference.md 2.9 KB
- references/glsl-shapes-polygon-star-polar-sdf-combinations.md 2.9 KB
- references/glsl-shapes-sdf-circles-rectangles-polar-distance-fields.md 2.4 KB
- references/glsl-shaping-functions-step-smoothstep-curves-interpolation.md 2.8 KB
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 · 114 lines · 65 tokens per session scan A 5cd90f8c61f4
ck:shader is a skill published in the GitHub repository manhvann/codexkit (88 stars, last pushed 4d ago), licensed MIT. It adds 65 tokens to every session and 1,133 once invoked, about $0.0003 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
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.
comfyui-topology-viz
Turn a network topology into one stylized, AI-generated still image via a self-hosted ComfyUI instance — reuses the same topology model as threejs-network-viz (any of 8 topology-source integrations, or a freeform description). Use when the operator asks for a stylized, flashy, or AI-generated…