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/owenob1/web-shaders-agent-kit/web-shadersnpx skills add owenob1/web-shaders-agent-kit --skill web-shadersgit clone --depth 1 https://github.com/owenob1/web-shaders-agent-kitWhat 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 | $0.00083 | $0.02062 |
| Opus 5 | $0.00042 | $0.01031 |
| Sonnet 5 | $0.00017 | $0.00412 |
| Haiku 4.5 | $0.00008 | $0.00206 |
Grade A, and why
web-shaders 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 — 117 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Web Shaders
You are writing shaders that run in a browser. Get the platform and language right first, then the technique, then verify visually.
1. Establish the target before writing a line
Ask (or infer from the codebase) which of these you are in — the boilerplate and language differ:
| Target | Language | Notes |
|---|---|---|
| Raw WebGL 2 | GLSL ES 3.00 (#version 300 es) |
You declare everything. in/out, texture(), custom out vec4. |
| Raw WebGL 1 | GLSL ES 1.00 | attribute/varying, texture2D(), gl_FragColor. Legacy — avoid for new work. |
| WebGPU (raw) | WGSL | @vertex/@fragment, bind groups, uniform buffers with strict alignment. |
Three.js ShaderMaterial |
GLSL ES 1.00 by default | Three injects camera/model matrices and attributes (see §2). Set glslVersion: THREE.GLSL3 for GLSL 3. |
Three.js RawShaderMaterial |
whatever you declare | No injected uniforms/attributes or precision. You write the full header. |
| Three.js TSL (WebGPURenderer) | JavaScript nodes | Author with tslFn/node ops; compiles to both WGSL and GLSL. No raw shader strings. |
| React Three Fiber | GLSL via drei shaderMaterial |
Wraps ShaderMaterial; uniforms become material props. |
If the project uses WebGPURenderer, prefer TSL over raw WGSL strings — it is the supported path and cross-compiles.
2. Three.js ShaderMaterial: what is already provided
ShaderMaterial (not RawShaderMaterial) auto-injects, so do not redeclare them:
- Vertex attributes:
position,normal,uv. - Uniforms:
modelMatrix,modelViewMatrix,projectionMatrix,viewMatrix,normalMatrix,cameraPosition. precisionis set for you.
A minimal correct pair:
// vertex
varying vec2 vUv;
void main() {
vUv = uv;
gl_Position = projectionMatrix * modelViewMatrix * vec4(position, 1.0);
}
// fragment
varying vec2 vUv;
uniform float uTime;
void main() {
gl_FragColor = vec4(vUv, 0.5 + 0.5 * sin(uTime), 1.0);
}
For GLSL 3 (glslVersion: THREE.GLSL3): replace varying→in/out, texture2D→texture, and declare out vec4 fragColor; instead of gl_FragColor.
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 · 117 lines · 83 tokens per session scan A fbae1884a679
web-shaders is a skill published in the GitHub repository owenob1/web-shaders-agent-kit (2 stars, last pushed 1mo ago), licensed MIT. It adds 83 tokens to every session and 2,062 once invoked, about $0.0004 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
honey-superpowers
Inject Honey levers into dispatched subagent prompts.
honey-px
Read huge read-only text as PNG pages; big input cut.
honey-ccr
Compress-cache-retrieve huge array tool output.
honey-eco
Report session token and CO2 savings vs no-Honey baseline.
honey-design
Same pixels, fewer tokens: dense CSS for user-facing UI.
honey-memory
Per-project persistent memory files indexed in MEMORY.md.