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/generous-corp/pulp/skia-gpu-buildnpx skills add Generous-Corp/pulp --skill skia-gpu-buildgit clone --depth 1 https://github.com/Generous-Corp/pulpWrote 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/generous-corp/pulp/skia-gpu-build)<a href="https://agentmods.dev/skills/generous-corp/pulp/skia-gpu-build"><img src="https://agentmods.dev/badge/skills/generous-corp/pulp/skia-gpu-build.svg" alt="Measured on agentmods" 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 | $0.00105 | $0.09081 |
| Opus 5 | $0.00053 | $0.04541 |
| Sonnet 5 | $0.00021 | $0.01816 |
| Haiku 4.5 | $0.00011 | $0.00908 |
Grade A, and why
skia-gpu-build 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 — 606 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Building Pulp with Skia + GPU
Pulp's GPU path is Skia Graphite over Dawn (WebGPU). PULP_ENABLE_GPU is
ON by default, but GPU only actually turns on when CMake can find the
prebuilt Skia libraries. If it can't, the build silently comes up CPU-only
(CoreGraphics raster, MacWindowHost) with no hard error — that's the #1
"GPU doesn't work" cause.
Start with installed GPU health evidence
Before inspecting libraries or opening a window, run:
pulp doctor gpu --json
This performs bounded render/readback and compute/map work through the installed
Pulp paths. Exit 0 means all required real-work proofs passed and at least one
required probe has authentic identity; exit 1 is a completed measured failure, and
exit 2 means requested evidence is unavailable or unverified. Use
pulp doctor gpu --no-render --json for inventory/preflight without acquiring
a GPU device; it returns unverified, never passed. The pulp_gpu_doctor MCP tool
returns the same typed evidence and both installed surfaces work independently
of the current directory.
Record adapter identity exactly as Dawn reports it. A backend label such as Metal, D3D12, or Vulkan does not prove that the adapter is hardware or discrete, and null/software adapters are never hardware passes. Probe identities are independent; do not infer that separately acquired Renderer3D, HeadlessSurface, and GpuCompute devices are the same device. Continue with the manual bundle and symbol checks below when the result is unavailable/unverified or when a completed probe fails.
The fresh-worktree trap (most common)
external/skia-build/ in a fresh worktree often contains only headers —
include/, modules/, VERSION.md — and no compiled libs. FindSkia needs
external/skia-build/build/<platform>-gpu/lib/Release/*.a (e.g.
libskia.a, libdawn_combined.a, libskparagraph.a, libskunicode_icu.a).
Headers-only ⇒ -- Skia: SKIA_DIR not set — Skia rendering disabled (or "not
found") ⇒ PULP_HAS_SKIA undefined ⇒ CPU-only build.
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 · 606 lines · 105 tokens per session scan A 1f1ad5befc1a
skia-gpu-build is a skill published in the GitHub repository Generous-Corp/pulp (16 stars, last pushed today), licensed MIT. It adds 105 tokens to every session and 9,081 once invoked, about $0.0005 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 2026-09-04.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
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…
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…