Borrowing it
Nothing to install: this file belongs to oframe/ogpu. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/oframe/ogpu/main/.claude/skills/webgpu-spec-lookup/SKILL.mdgit clone --depth 1 https://github.com/oframe/ogpuWrote 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/oframe/ogpu/webgpu-spec-lookup)<a href="https://agentmods.dev/skills/oframe/ogpu/webgpu-spec-lookup"><img src="https://agentmods.dev/badge/skills/oframe/ogpu/webgpu-spec-lookup/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/oframe/ogpu/webgpu-spec-lookup"><img src="https://agentmods.dev/badge/skills/oframe/ogpu/webgpu-spec-lookup.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Agent Snooping · line 41 Skill reads from agent configuration directories (.claude/, .codex/, .gemini/). These directories may contain API keys, personal settings, and other credentials that the skill has no legitimate need to access.Fix: Remove all code or instructions that access agent configuration directories (.claude/, .codex/, .gemini/). If configuration values are needed, pass them explicitly as parameters or environment variabl
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 | $0.00000 | $0.01253 |
| Opus 5.5 | $0.00000 | $0.00501 |
| Sonnet 5.5 | $0.00000 | $0.00251 |
| Haiku 4.5 | $0.00000 | $0.00125 |
Grade A, and why
webgpu-spec-lookup 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 1mo 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 — 88 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Answer WebGPU-platform questions from the live docs, not from memory
WebGPU is a moving target: features ship per Chrome milestone, limits get raised, things sit behind flags or origin trials, and the spec adds capabilities on a rolling basis. Whatever you recall about "is X supported" or "what's the default limit" is liable to be months stale, and a confident wrong answer about browser support or a feature name wastes the user's time. The cost of fetching is a few seconds. So for platform questions, check the sources before answering.
This skill is for questions about WebGPU the platform — support, features,
limits, spec behavior. It is NOT for questions about OGPU's own engine code
(that's the codebase) or the webgpu-utils library (that's the
webgpu-utils-lookup skill).
Sources
Two sources answer different things — query each its own way:
-
Chrome WebGPU docs / "What's New" — reality of what's shipped. (WebFetch) https://developer.chrome.com/docs/web-platform/webgpu This is the entry point; the per-release "What's New in WebGPU (Chrome NNN)" posts are where feature-shipping, flags, origin trials, and raised limits are announced. The landing page links to them — if the answer needs a specific milestone, follow the link (or WebSearch
What's New in WebGPU Chrometo find the most recent post). Use this for: "is it shipping / in which Chrome / behind a flag / in an origin trial", and browser-compat reality. -
W3C WebGPU spec — authoritative API surface. (local cache, grep — not WebFetch) The spec is one 4.5 MB page; WebFetch'ing it per question is slow and lossy. Instead query a preprocessed local copy:
# Prints the cache path; (re)downloads + strips to text only when the cached # copy's date != today. Run it first, then grep the path it prints. python3 .claude/skills/webgpu-spec-lookup/update_spec.py grep -n -i "maxStorageBufferBindingSize" .claude/skills/webgpu-spec-lookup/webgpu-spec.txt
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.
- 1mo ago First seen · 88 lines · 0 tokens per session scan A f5c6d8842090
webgpu-spec-lookup is a skill published in the GitHub repository oframe/ogpu (163 stars, last pushed 3d ago), licensed Unlicense. It costs nothing until one of its globs matches a file; then it loads 1,253 tokens. 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
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…