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 pierreaubert/gpui-toolkit --skill gpuigit clone --depth 1 https://github.com/pierreaubert/gpui-toolkitWrote 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/pierreaubert/gpui-toolkit/gpui)<a href="https://agentmods.dev/skills/pierreaubert/gpui-toolkit/gpui"><img src="https://agentmods.dev/badge/skills/pierreaubert/gpui-toolkit/gpui.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 5.1 | $0.00060 | $0.02009 |
| Opus 5 | $0.00030 | $0.01005 |
| Sonnet 5 | $0.00012 | $0.00402 |
| Haiku 4.5 | $0.00006 | $0.00201 |
Grade A, and why
gpui-toolkit 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 — 168 lines — stays where its author put it; the contents beside it link to each section on GitHub.
GPUI Toolkit Skill
Use this skill for GPUI app and component work in this workspace. The prime directive is: build with the toolkit first. Do not recreate buttons, forms, charts, layout solvers, theme systems, keyboard handling, audio widgets, or component review surfaces that already exist here.
Start Here
- Before reading files, query TokenSave for the feature area:
tokensave_contextwhen available, otherwisetokensave_search/tokensave_files. - Read README.md for the crate map and TUTORIAL.md for the intended app composition flow.
- For crate-specific rules, read the nearest
AGENTS.mdorREADME.mdundercrates/<crate>/. - Prefer examples, showcase includes, and component-lab stories over inventing API style from memory.
- Use
rgfor textual searches after TokenSave when the semantic graph is not enough.
Composition Defaults
For desktop apps, start with gpui-miniapp. It supplies the app shell, menus, theme globals, design-system globals, language switching, and platform backend setup.
Use gpui-ui-kit for ordinary app UI:
- Core:
Button,IconButton,Card,Dialog,ConfirmDialog,Popover,Tabs,Menu,ContextMenu,Toast. - Forms:
Input,NumberInput,Checkbox,Toggle,Select,ButtonSet,ColorPickerView,Slider,Wizard. - Data and feedback:
Table,Badge,Avatar,Progress,Spinner,QrCode,KeyboardShortcutLabel,EmptyState,Alert,SearchBar,Tooltip. - Layout and navigation:
VStack,HStack,Spacer,Divider,PaneDivider,SplitPane,Sidebar,StatusBar,Accordion,Breadcrumbs. - Advanced surfaces:
CommandPalette,Toolbar,TreeView,DragList,WorkflowCanvas.
Use gpui-audio-kit for audio and plugin UIs: Potentiometer, VerticalSlider, VolumeKnob, AudioDesignTokens, meters, spectrum elements, tick rows, and audio scale helpers. gpui-ui-kit intentionally does not re-export these.
Use gpui-builder when layout behavior needs a reusable or testable contract: responsive shells, split panes, collapsible panels, auto-axis behavior, display tiers, or draggable divider math. Keep the solver tree pure and render the solved result in GPUI.
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 · 168 lines · 60 tokens per session scan A ed9b149bb1be
gpui-toolkit is a skill published in the GitHub repository pierreaubert/gpui-toolkit (60 stars, last pushed 5d ago), licensed ISC. It adds 60 tokens to every session and 2,009 once invoked, about $0.0003 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 2026-09-03.
Other skills, from other repositories
wasm-expert
WebAssembly expert for WASI, component model, Rust/C compilation, and browser integration.
gpui
GPUI framework knowledge covering actions/keybindings, async/background tasks, context management (App/Window/Context /AsyncApp), custom elements (low-level Element trait), entity state management, event system, focus handling, global state, layout/styling (flexbox/CSS-like), and testing. Use when working with any…
frontend-htmx
Axum + Askama + HTMX stack for single-binary web apps. Use when: building server-rendered UI, lightweight frontends, single deployable binary. Triggers: "htmx", "askama", "templates", "server-rendered", "single binary frontend".
compiler-orchestrator
Orchestrate the Rust compiler port end-to-end. Discovers the current frontier, fixes failing passes, ports new passes, reviews, and commits in a loop.
popular-web-designs
54 real design systems (Stripe, Linear, Vercel) as HTML/CSS.
compiler-port
Port a compiler pass from TypeScript to Rust. Gathers context, plans the port, implements in a subagent with test-fix loop, then reviews.