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 oaustegard/claude-skills --skill compiling-wgslgit clone --depth 1 https://github.com/oaustegard/claude-skillsWrote 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/oaustegard/claude-skills/compiling-wgsl)<a href="https://agentmods.dev/skills/oaustegard/claude-skills/compiling-wgsl"><img src="https://agentmods.dev/badge/skills/oaustegard/claude-skills/compiling-wgsl/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/oaustegard/claude-skills/compiling-wgsl"><img src="https://agentmods.dev/badge/skills/oaustegard/claude-skills/compiling-wgsl.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 | $0.00206 | $0.05234 |
| Opus 5.5 | $0.00082 | $0.02094 |
| Sonnet 5.5 | $0.00041 | $0.01047 |
| Haiku 4.5 | $0.00021 | $0.00523 |
Grade A, and why
compiling-wgsl scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 5d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 313 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Compiling WGSL
scripts/forge is a pure-Python WGSL toolchain (numpy is the only dependency): a parser
that follows the spec's template-list rules, a minifier, a shape compiler, and a GLSL
front end that rewrites WebGL and Shadertoy GLSL for naga (and glslang) to translate. It came
from oaustegard/experiments/wgsl-forge, whose RESULTS.md holds the measurements quoted
here. Set SKILL=/mnt/skills/user/compiling-wgsl (or this directory) and run every
command with PYTHONPATH=$SKILL/scripts.
When NOT to use this skill
| Situation | Use instead |
|---|---|
| A raster image (photo, PNG) should become vector shapes | image-to-svg, then this skill on its SVG |
| The output is a PNG, PDF or SVG file rather than a shader | drawing-with-pycairo |
| Charts or dashboards | charting, charting-vega-lite |
| HLSL or Metal | not covered; naga reads SPIR-V (naga in.spv out.wgsl), so HLSL can go through DXC to SPIR-V first |
GLSL for desktop OpenGL with #version 330 or older, or code using iChannel buffers (multi-pass Shadertoy) |
converts, but the multi-pass plumbing (render targets, feedback) is host code you write |
| A shader whose host reads names back by reflection (a binding library that matches struct member or function names) | run with --keep name1,name2, or do not rename |
Setup
export SKILL=/mnt/skills/user/compiling-wgsl
pip install --break-system-packages numpy pillow # pillow only for --png
command -v naga || cargo install naga-cli # validator; required for GLSL, ~3 min
command -v glslangValidator || apt-get install -y glslang-tools # GLSL fallback route
node -e "require('playwright')" && echo playwright-ok # GPU checks need it
python3 $SKILL/scripts/selftest.py # ~20 s: every route on bundled fixtures
selftest.py prints missing tools: first if naga, glslang or node is absent. Every
other line must read ok.
The GPU checks run headless Chromium on SwiftShader. On claude.ai and Claude Code on
the web, Playwright's Chromium is already installed. Elsewhere, point CHROME_PATH at a
Chromium binary.
What ships with it
34 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.
- CHANGELOG.md 604 B
- references/example_scene.py 1.4 KB runs code
- references/scene-api.md 3.1 KB
- scripts/forge/__init__.py 68 B runs code
- scripts/forge/__main__.py 9.6 KB runs code
- scripts/forge/ast.py 3.3 KB runs code
- scripts/forge/codegen.py 32 KB runs code
- scripts/forge/color.py 4.4 KB runs code
- scripts/forge/geom.py 16 KB runs code
- scripts/forge/glsl.py 14 KB runs code
- scripts/forge/gpu.py 1.6 KB runs code
- scripts/forge/minify.py 23 KB runs code
- scripts/forge/names.py 5.6 KB runs code
- scripts/forge/printer.py 15 KB runs code
- scripts/forge/reflect.py 6.2 KB runs code
- scripts/forge/scene.py 18 KB runs code
- scripts/forge/scope.py 8.1 KB runs code
- scripts/forge/svg.py 14 KB runs code
- scripts/forge/types.py 9.6 KB runs code
- scripts/forge/wgsl.py 20 KB runs code
- scripts/harness/gpu.mjs 11 KB runs code
- scripts/selftest.py 2.0 KB runs code
- scripts/selftest/blur.comp 616 B
- scripts/selftest/collatz.wgsl 971 B
- scripts/selftest/es100.frag 266 B
- scripts/selftest/es300.frag 430 B
- scripts/selftest/es300.vert 239 B
- scripts/selftest/paths.svg 878 B
- scripts/selftest/rev.comp 272 B
- scripts/selftest/st_fbm.glsl 876 B
- scripts/selftest/st_misc.glsl 1019 B
- scripts/selftest/st_plasma.glsl 368 B
- scripts/selftest/st_raymarch.glsl 1.7 KB
- scripts/verify.py 15 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.
- 5d ago Changed · +23 lines 670b26af11ef
- 6d ago First seen · 290 lines · 206 tokens per session scan A 8e28d84cb356
compiling-wgsl is a skill published in the GitHub repository oaustegard/claude-skills (158 stars, last pushed yesterday), licensed MIT. It adds 206 tokens to every session and 5,234 once invoked, about $0.0008 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 2026-11-02.
compiling-wgsl compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| compiling-wgsloaustegard/claude-skills | Skill | 158 | yesterday | MIT | A | 206 | Claude Code, Codex |
| superdesignsuperdesigndev/superdesign-skill | Skill | 956 | 2mo ago | MIT | A | 115 | Claude Code, Codex |
| figma-to-codescoobynko/claude-code-design-skills | Skill | 40 | 1mo ago | MIT | A | 0 | Claude Code, Codex |
| Linearwrsmith108/linear-claude-skill | Skill | 140 | 3mo ago | MIT | A | 32 | Claude Code |
| bpmn-xml-generatorstateway-io/bpmn-xml-generator | Skill | 4 | 12d ago | Apache-2.0 | A | 177 | Claude Code |
| smb-sales-boostTomsonx232/smb-sales-boost-skill | Skill | 5 | 24d ago | MIT | A | 200 | Claude Code, Codex |
| free-public-rest-apisaisenseapi/aisense-free-public-rest-apis | Skill | 1 | today | MIT | A | 366 | Claude Code, Codex |