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/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/commands/geoffjay/claude-plugins/gpui-component)<a href="https://agentmods.dev/commands/geoffjay/claude-plugins/gpui-component"><img src="https://agentmods.dev/badge/commands/geoffjay/claude-plugins/gpui-component/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/commands/geoffjay/claude-plugins/gpui-component"><img src="https://agentmods.dev/badge/commands/geoffjay/claude-plugins/gpui-component.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 | $0.00020 | $0.03088 |
| Opus 5.5 | $0.00008 | $0.01235 |
| Sonnet 5.5 | $0.00004 | $0.00618 |
| Haiku 4.5 | $0.00002 | $0.00309 |
Grade A, and why
gpui-component 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.
How it starts
The opening of the file, as written. The whole thing — 594 lines — stays where its author put it; the contents beside it link to each section on GitHub.
GPUI Component Generator
Generate reusable, well-structured GPUI components with proper typing, state management, styling, and comprehensive documentation.
Arguments
$1: Component name (required) - Name of the component in PascalCase (e.g., "Button", "DataTable", "SearchInput")$2: Component type (optional) - Either "stateless" (default) or "stateful"
Workflow
1. Gather Component Requirements
Ask user for:
- Component purpose and description
- Props/configuration needed
- Whether component needs internal state
- Event handlers required
- Styling requirements
- Accessibility needs
2. Generate Component Struct
Create component struct based on type:
Stateless Component
use gpui::*;
/// A reusable button component
///
/// # Examples
///
/// ```
/// Button::new("Click me")
/// .on_click(|cx| {
/// println!("Clicked!");
/// })
/// ```
pub struct Button {
label: String,
variant: ButtonVariant,
disabled: bool,
on_click: Option<Box<dyn Fn(&mut WindowContext)>>,
}
#[derive(Clone, Copy, PartialEq)]
pub enum ButtonVariant {
Primary,
Secondary,
Destructive,
Ghost,
}
impl Button {
pub fn new(label: impl Into<String>) -> Self {
Self {
label: label.into(),
variant: ButtonVariant::Primary,
disabled: false,
on_click: None,
}
}
pub fn variant(mut self, variant: ButtonVariant) -> Self {
self.variant = variant;
self
}
pub fn disabled(mut self, disabled: bool) -> Self {
self.disabled = disabled;
self
}
pub fn on_click(mut self, handler: impl Fn(&mut WindowContext) + 'static) -> Self {
self.on_click = Some(Box::new(handler));
self
}
}
Stateful Component
use gpui::*;
/// A search input with autocomplete
pub struct SearchInput {
query: String,
suggestions: Vec<String>,
selected_index: Option<usize>,
on_search: Option<Box<dyn Fn(&str, &mut WindowContext)>>,
}
impl SearchInput {
pub fn new() -> Self {
Self {
query: String::new(),
suggestions: Vec::new(),
selected_index: None,
on_search: None,
}
}
pub fn on_search(mut self, handler: impl Fn(&str, &mut WindowContext) + 'static) -> Self {
self.on_search = Some(Box::new(handler));
self
}
fn handle_input(&mut self, value: String, cx: &mut ViewContext<Self>) {
self.query = value;
self.update_suggestions(cx);
cx.notify();
}
fn update_suggestions(&mut self, cx: &mut ViewContext<Self>) {
// Update suggestions based on query
if let Some(handler) = &self.on_search {
handler(&self.query, cx);
}
}
fn handle_key_down(&mut self, event: &KeyDownEvent, cx: &mut ViewContext<Self>) {
match event.key.as_str() {
"ArrowDown" => {
self.selected_index = Some(
self.selected_index
.map(|i| (i + 1).min(self.suggestions.len() - 1))
.unwrap_or(0)
);
cx.notify();
}
"ArrowUp" => {
self.selected_index = self.selected_index
.and_then(|i| i.checked_sub(1));
cx.notify();
}
"Enter" => {
if let Some(index) = self.selected_index {
self.query = self.suggestions[index].clone();
self.suggestions.clear();
cx.notify();
}
}
_ => {}
}
}
}
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 · 594 lines · 20 tokens per session scan A bcc347437faa
gpui-component is a command published in the GitHub repository geoffjay/claude-plugins (8 stars, last pushed 11mo ago), licensed MIT. It adds 20 tokens to every session and 3,088 once invoked, about $0.0001 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.
Other commands, from other repositories
cargo-metadata
Command "cargo-metadata" from olorehq/olore, covering cargo-metadata(1), name, synopsis, description and output format.
mutation-test
Uses cargo-mutants to run mutation tests and verify test quality.
cargo-bench
Command "cargo-bench" from olorehq/olore, covering cargo-bench(1), name, synopsis, description and working directory of benchmarks.
cargo-build
Command "cargo-build" from olorehq/olore, covering cargo-build(1), name, synopsis, description and options.
cargo-check
Command "cargo-check" from olorehq/olore, covering cargo-check(1), name, synopsis, description and options.
cargo
Command "cargo" from olorehq/olore, covering cargo(1), name, synopsis, description and commands.