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/geoffjay/claude-plugins/gpui-performancenpx skills add geoffjay/claude-plugins --skill gpui-performancegit clone --depth 1 https://github.com/geoffjay/claude-pluginsWhat 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 | $0.00039 | $0.03325 |
| Opus 5 | $0.00019 | $0.01663 |
| Sonnet 5 | $0.00008 | $0.00665 |
| Haiku 4.5 | $0.00004 | $0.00332 |
Grade A, and why
gpui-performance 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 2d 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 — 604 lines — stays where its author put it; the contents beside it link to each section on GitHub.
GPUI Performance Optimization
Metadata
This skill provides comprehensive guidance on optimizing GPUI applications for rendering performance, memory efficiency, and overall runtime speed.
Instructions
Rendering Optimization
Understanding the Render Cycle
State Change → cx.notify() → Render → Layout → Paint → Display
Key Points:
- Only call
cx.notify()when state actually changes - Minimize work in
render()method - Cache expensive computations
- Reduce element count and nesting
Avoiding Unnecessary Renders
// BAD: Renders on every frame
impl MyComponent {
fn start_animation(&mut self, cx: &mut ViewContext<Self>) {
cx.spawn(|this, mut cx| async move {
loop {
cx.update(|_, cx| cx.notify()).ok(); // Forces rerender!
Timer::after(Duration::from_millis(16)).await;
}
}).detach();
}
}
// GOOD: Only render when state changes
impl MyComponent {
fn update_value(&mut self, new_value: i32, cx: &mut ViewContext<Self>) {
if self.value != new_value {
self.value = new_value;
cx.notify(); // Only notify on actual change
}
}
}
Optimize Subscription Updates
// BAD: Always rerenders on model change
let _subscription = cx.observe(&model, |_, _, cx| {
cx.notify(); // Rerenders even if nothing relevant changed
});
// GOOD: Selective updates
let _subscription = cx.observe(&model, |this, model, cx| {
let data = model.read(cx);
// Only rerender if relevant field changed
if data.relevant_field != this.cached_field {
this.cached_field = data.relevant_field.clone();
cx.notify();
}
});
Memoization Pattern
use std::cell::RefCell;
use std::collections::hash_map::DefaultHasher;
use std::hash::{Hash, Hasher};
struct MemoizedComponent {
model: Model<Data>,
cached_result: RefCell<Option<(u64, String)>>, // (hash, result)
}
impl MemoizedComponent {
fn expensive_computation(&self, cx: &ViewContext<Self>) -> String {
let data = self.model.read(cx);
// Calculate hash of input
let mut hasher = DefaultHasher::new();
data.relevant_fields.hash(&mut hasher);
let hash = hasher.finish();
// Return cached if unchanged
if let Some((cached_hash, cached_result)) = &*self.cached_result.borrow() {
if *cached_hash == hash {
return cached_result.clone();
}
}
// Compute and cache
let result = perform_expensive_computation(&data);
*self.cached_result.borrow_mut() = Some((hash, result.clone()));
result
}
}
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.
- 2d ago First seen · 604 lines · 39 tokens per session scan A d53db89b8f49
gpui-performance is a skill published in the GitHub repository geoffjay/claude-plugins (8 stars, last pushed 10mo ago), licensed MIT. It adds 39 tokens to every session and 3,325 once invoked, about $0.0002 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 2026-08-31.
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…