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.
git clone --depth 1 https://github.com/quinnjr/skia-rsWrote 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/rules/quinnjr/skia-rs/gpu)<a href="https://agentmods.dev/rules/quinnjr/skia-rs/gpu"><img src="https://agentmods.dev/badge/rules/quinnjr/skia-rs/gpu/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/rules/quinnjr/skia-rs/gpu"><img src="https://agentmods.dev/badge/rules/quinnjr/skia-rs/gpu.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 | $0.00000 | $0.00227 |
| Opus 5.5 | $0.00000 | $0.00091 |
| Sonnet 5.5 | $0.00000 | $0.00045 |
| Haiku 4.5 | $0.00000 | $0.00023 |
Grade A, and why
gpu 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.
What it actually says
GPU Backend Guidelines
Feature Flags
[features]
default = ["wgpu-backend"]
vulkan = ["dep:ash"]
opengl = ["dep:glow"]
wgpu-backend = ["dep:wgpu"]
Backend Abstraction
pub trait GpuBackend: Send + Sync {
fn create_surface(&self, info: &ImageInfo) -> Result<GpuSurface, GpuError>;
fn flush(&self);
}
Supported Backends
- wgpu: Cross-platform WebGPU abstraction (default)
- Vulkan: Low-level via
ashcrate - OpenGL: Via
glowcrate - Metal: macOS/iOS (planned)
Resource Management
- Use GPU resource pools for frequently allocated objects
- Implement proper cleanup in
Droptraits - Handle device lost scenarios gracefully
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 · 40 lines · 0 tokens per session scan A 40a71cdf9ba9
gpu is a cursor rule published in the GitHub repository quinnjr/skia-rs (36 stars, last pushed 1mo ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 227 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 2026-09-01.
Other cursor rules, from other repositories
rust-architect
PoolAI — Rust Architect workflow: runtime stack, MSYS2, target/ disk, pre-push checks, docs sync.
table-of-contents-standard
Standard section ordering and TOC format for Verus source files.
arc-deref-pattern
When implementing parallel (Mt) algorithms in Verus, do NOT assume.
core
Core STT/TTS abstraction layer documentation.
wrap-vs-specify
When to use externaltypespecification vs wrapper struct for Verus specs.
spec-fn-naming
Spec function naming conventions.