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 skills add geoffjay/claude-plugins --skill gpui-patternsgit clone --depth 1 https://github.com/geoffjay/claude-pluginsWrote 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/geoffjay/claude-plugins/gpui-patterns)<a href="https://agentmods.dev/skills/geoffjay/claude-plugins/gpui-patterns"><img src="https://agentmods.dev/badge/skills/geoffjay/claude-plugins/gpui-patterns/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/geoffjay/claude-plugins/gpui-patterns"><img src="https://agentmods.dev/badge/skills/geoffjay/claude-plugins/gpui-patterns.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 | $0.00043 | $0.02972 |
| Opus 5.5 | $0.00017 | $0.01189 |
| Sonnet 5.5 | $0.00009 | $0.00594 |
| Haiku 4.5 | $0.00004 | $0.00297 |
Grade A, and why
gpui-patterns 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 2mo 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 Patterns
Metadata
This skill provides comprehensive guidance on common GPUI patterns and best practices for building maintainable, performant applications.
Instructions
Component Composition Patterns
Basic Component Structure
use gpui::*;
// View component with state
struct MyView {
state: Model<MyState>,
_subscription: Subscription,
}
impl MyView {
fn new(state: Model<MyState>, cx: &mut ViewContext<Self>) -> Self {
let _subscription = cx.observe(&state, |_, _, cx| cx.notify());
Self { state, _subscription }
}
}
impl Render for MyView {
fn render(&mut self, cx: &mut ViewContext<Self>) -> impl IntoElement {
let state = self.state.read(cx);
div()
.flex()
.flex_col()
.child(format!("Value: {}", state.value))
}
}
Container/Presenter Pattern
Container (manages state and logic):
struct Container {
model: Model<AppState>,
_subscription: Subscription,
}
impl Container {
fn new(model: Model<AppState>, cx: &mut ViewContext<Self>) -> Self {
let _subscription = cx.observe(&model, |_, _, cx| cx.notify());
Self { model, _subscription }
}
}
impl Render for Container {
fn render(&mut self, cx: &mut ViewContext<Self>) -> impl IntoElement {
let state = self.model.read(cx);
// Pass data to presenter
Presenter::new(state.data.clone())
}
}
Presenter (pure rendering):
struct Presenter {
data: String,
}
impl Presenter {
fn new(data: String) -> Self {
Self { data }
}
}
impl Render for Presenter {
fn render(&mut self, cx: &mut ViewContext<Self>) -> impl IntoElement {
div().child(self.data.as_str())
}
}
Compound Components
// Parent component with shared context
pub struct Tabs {
items: Vec<TabItem>,
active_index: usize,
}
pub struct TabItem {
label: String,
content: Box<dyn Fn() -> AnyElement>,
}
impl Tabs {
pub fn new() -> Self {
Self {
items: Vec::new(),
active_index: 0,
}
}
pub fn add_tab(
mut self,
label: impl Into<String>,
content: impl Fn() -> AnyElement + 'static,
) -> Self {
self.items.push(TabItem {
label: label.into(),
content: Box::new(content),
});
self
}
fn set_active(&mut self, index: usize, cx: &mut ViewContext<Self>) {
self.active_index = index;
cx.notify();
}
}
impl Render for Tabs {
fn render(&mut self, cx: &mut ViewContext<Self>) -> impl IntoElement {
div()
.flex()
.flex_col()
.child(
// Tab headers
div()
.flex()
.children(
self.items.iter().enumerate().map(|(i, item)| {
tab_header(&item.label, i == self.active_index, || {
self.set_active(i, cx)
})
})
)
)
.child(
// Active tab content
(self.items[self.active_index].content)()
)
}
}
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.
- 2mo ago First seen · 604 lines · 43 tokens per session scan A 597dcfc627d1
gpui-patterns is a skill published in the GitHub repository geoffjay/claude-plugins (8 stars, last pushed 1y ago), licensed MIT. It adds 43 tokens to every session and 2,972 once invoked, about $0.0002 per session on Opus 5.5. 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.
gpui-patterns compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| gpui-patternsgeoffjay/claude-plugins | Skill | 8 | 1y ago | MIT | A | 43 | Claude Code |
| cranposesamoylenkodmitry/Cranpose | Skill | 59 | yesterday | Apache-2.0 | A | 44 | Claude Code |
| cougr-game-startersalazarsebas/Cougr | Skill | 53 | 16d ago | MIT | A | 68 | Claude Code, Codex |
| rust-patternsaffaan-m/ECC | Skill | 298k | 4d ago | MIT | A | 28 | Claude Code, Kiro |
| update-v8-versionopeninterpreter/openinterpreter | Skill | 69k | 2d ago | Apache-2.0 | A | 86 | Codex |
| dd-code-generationDataDog/pup | Skill | 1.0k | yesterday | Apache-2.0 | A | 16 | Claude Code |
| omh-rustrlaope/oh-my-hermes | Skill | 5.2k | today | MIT | A | 74 | Claude Code, Codex |