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/oframe/ogpu/webgpu-utils-lookupnpx skills add oframe/ogpu --skill webgpu-utils-lookupgit clone --depth 1 https://github.com/oframe/ogpuWhat 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 | $0.00178 | $0.01323 |
| Opus 5 | $0.00089 | $0.00661 |
| Sonnet 5 | $0.00036 | $0.00265 |
| Haiku 4.5 | $0.00018 | $0.00132 |
Grade A, and why
webgpu-utils-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 3d 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 — 97 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Answer webgpu-utils questions from the source, not from memory
webgpu-utils is small but full of non-obvious behavior: functions that mutate a
passed-in view in place, reflection that keys uniforms by declared name, helpers
that silently pick a texture view dimension for you, options whose defaults
matter (mips, usage, viewDimension). Memory of "roughly how it works" is
exactly where wrong answers come from — a misremembered option name or a stale
signature compiles fine and then breaks at runtime with no error. The cost of
checking is a few seconds; the cost of guessing is a silent garbage texture or a
buffer written to the wrong offset. So check first.
This codebase pins webgpu-utils 1.11.0 (dist/1.x). The installed copy is
the ground truth for this project — prefer it over anything you recall or find
online, because online docs track latest and may have drifted.
Lookup order
-
Local types — authoritative for the installed version. The
.d.tsfiles carry full signatures, option-object shapes, defaults, and the doc-comments (often with usage examples). Read these first:node_modules/webgpu-utils/dist/1.x/<module>.d.tsreferences/api-map.mdmaps every exported symbol to its.d.tsmodule so you can jump straight to the right file. -
Local implementation — when behavior isn't clear from the type alone. Questions like "does it mutate the argument or return a copy?", "what does it default the format to?", "how does it decide cube vs 2d-array?" are answered by reading the compiled source:
node_modules/webgpu-utils/dist/1.x/webgpu-utils.module.jsIt's readable ES —
grep -n 'function <name>'to find the definition. -
GitHub repo — for rationale, latest source, history, issues. Use when the local copy doesn't settle it, when the user asks about a version newer than 1.11.0, or when "why does it do this" needs the original TypeScript / commit context: https://github.com/greggman/webgpu-utils (source under
src/, one file per module mirroring the.d.tsnames). Fetch with WebFetch.
What ships with it
2 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.
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.
- 3d ago First seen · 97 lines · 178 tokens per session scan A 35d1259b52dc
webgpu-utils-lookup is a skill published in the GitHub repository oframe/ogpu (139 stars, last pushed 22d ago), licensed Unlicense. It adds 178 tokens to every session and 1,323 once invoked, about $0.0009 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
auto-perf-optimize
Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.
chat-perf
Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.
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…