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 LeahyCC/claude-skills --skill webgpugit clone --depth 1 https://github.com/LeahyCC/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/leahycc/claude-skills/webgpu)<a href="https://agentmods.dev/skills/leahycc/claude-skills/webgpu"><img src="https://agentmods.dev/badge/skills/leahycc/claude-skills/webgpu/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/leahycc/claude-skills/webgpu"><img src="https://agentmods.dev/badge/skills/leahycc/claude-skills/webgpu.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 | $0.00120 | $0.01629 |
| Opus 5.5 | $0.00048 | $0.00652 |
| Sonnet 5.5 | $0.00024 | $0.00326 |
| Haiku 4.5 | $0.00012 | $0.00163 |
Grade A, and why
webgpu 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 today.
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 — 96 lines — stays where its author put it; the contents beside it link to each section on GitHub.
WebGPU
Writing WebGPU that works on the browsers you ship to, and does not fail silently when it does not. Whether WebGPU is the right fix for a slow page belongs to the spa-performance skill.
WebGPU almost never throws. A bad call returns an invalid object and reports the error later, and a lost device turns every call into a no-op. Wire up error reporting and device loss before anything else, or a black canvas is all you get.
If an engine owns the device, use the engine. In three.js, Babylon.js, or a library like TypeGPU, follow that library's API and its docs. Do not mix raw WebGPU calls into its frame unless it documents a way to. This skill is for code that owns its own device.
Source checks and dates: SOURCES.md.
Procedure
- Read setup.md. Detect, request only the features and limits the adapter has, and decide the fallback.
- Add the
uncapturederrorlistener anddevice.losthandler from errors-and-device-loss.md. Label every object. - For multi-pass or compute work, write down each pass first: what it reads, what it writes, and which buffer holds the current data afterwards.
- Read the resource for the thing you are building.
- For any struct shared with the CPU, run
node scripts/wgsl-layout.mjs <file.wgsl>and use the offsets it prints. Add--uniformfor uniform buffers. - Check the resource's checklist, then report how far the code was checked, using the levels in debugging-and-testing.md.
navigator.gpu? -> adapter? -> device? --any no--> fallback, log why
|
error listener + device.lost
|
+------------------------+------------------------+
| | |
draw to canvas compute only both
canvas.md compute.md all three
render-basics.md |
| |
+--- buffers-and-textures.md, wgsl.md, pipelines.md ---+
|
check it: debugging-and-testing.md slow? profiling.md
What ships with it
13 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.
- README.md 3.3 KB
- resources/buffers-and-textures.md 6.7 KB
- resources/canvas.md 7.9 KB
- resources/compute.md 5.4 KB
- resources/debugging-and-testing.md 6.7 KB
- resources/errors-and-device-loss.md 6.1 KB
- resources/pipelines.md 4.8 KB
- resources/profiling.md 4.6 KB
- resources/render-basics.md 7.9 KB
- resources/setup.md 7.4 KB
- resources/wgsl.md 7.8 KB
- scripts/wgsl-layout.mjs 6.4 KB runs code
- SOURCES.md 7.8 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.
- today First seen · 96 lines · 120 tokens per session scan A 9bd7a54af687
webgpu is a skill published in the GitHub repository LeahyCC/claude-skills (3 stars, last pushed today), licensed MIT. It adds 120 tokens to every session and 1,629 once invoked, about $0.0005 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 2026-10-24.
Other skills, from other repositories
Accessibility Audit Helper
Reviews UI code and components for WCAG 2.1 accessibility violations and provides specific fixes.
a11y-ally
Use when running comprehensive WCAG accessibility audits with axe-core + pa11y + Lighthouse, generating context-aware remediation, or testing video accessibility. Supports 3-tier browser cascade with graceful degradation.
accessibility-testing
WCAG 2.2 compliance testing, screen reader validation, and inclusive design verification. Use when ensuring legal compliance (ADA, Section 508), testing for disabilities, or building accessible applications for 1 billion disabled users globally.
Accessibility Auditor
Comprehensive WCAG 2.1 AA compliance testing combining automated axe-core scans with manual keyboard navigation, screen reader compatibility, and focus management verification.
accessibility
Use when making a web UI conform to WCAG 2.2 Level AA — axe-core or Lighthouse a11y violations, keyboard operability, focus management, ARIA roles/names/live regions, contrast, tap-target size. NOT palette or visual intent (that is design), NOT test-runner setup (that is testing-web), NOT LCP/page-speed (that is…
Accessibility A11y Enhanced
Comprehensive WCAG compliance and accessibility testing covering ARIA, keyboard navigation, screen readers, color contrast, and automated a11y validation.