gpui-toolkit: Instructions file for Codex

AGENTS.md

gpui-toolkit AGENTS.md is an instructions file for Codex, OpenCode from pierreaubert/gpui-toolkit. It costs 3,199 tokens per session, scanned A, original, ISC.

A set of instructions for using the GPUI toolkit, a collection of Rust libraries for building graphical applications. It summarizes the toolkit’s components, including layout, design, audio, web, and data-visualization packages.

In plain words
What is it for?
Use it when working on GPUI layouts, forms, keyboard or mouse handling, platform backends, web builds, charts, or shared design components.
Why use it?
It gives an AI assistant a map of the available packages and their purposes before it changes or extends a GPUI application.

Instructions file for CodexOpenCode

Written for Codex and OpenCode: the file is AGENTS.md. Also seen: mentions AGENTS.md.

This is pierreaubert/gpui-toolkit's own configuration. It tells Codex and OpenCode how to work on gpui-toolkit itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything gpui-toolkit configures →

Reuse

Borrowing it

Nothing to install: this file belongs to pierreaubert/gpui-toolkit. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/pierreaubert/gpui-toolkit/main/AGENTS.md
Clone the repo
git clone --depth 1 https://github.com/pierreaubert/gpui-toolkit

Made for: Codex, OpenCode.

Wrote 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.

agentmods badge for gpui-toolkit AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/pierreaubert/gpui-toolkit/agents-md/github.svg)](https://agentmods.dev/instructions/pierreaubert/gpui-toolkit/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/pierreaubert/gpui-toolkit/agents-md"><img src="https://agentmods.dev/badge/instructions/pierreaubert/gpui-toolkit/agents-md/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.

agentmods 80×15 button for gpui-toolkit AGENTS.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/pierreaubert/gpui-toolkit/agents-md"><img src="https://agentmods.dev/badge/instructions/pierreaubert/gpui-toolkit/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 3,199 This file is loaded in full into every session.
When invoked 3,199 The same file — it is already loaded in full.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.03199 $0.03199
Opus 5.5 $0.01280 $0.01280
Sonnet 5.5 $0.00640 $0.00640
Haiku 4.5 $0.00320 $0.00320

Measured yesterday against content hash efc04f16e738, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

gpui-toolkit AGENTS.md 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 yesterday.

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.

AGENTS.md · 231 lines

How it starts

The opening of the file, as written. The whole thing — 231 lines — stays where its author put it; the contents beside it link to each section on GitHub.

GPUI Toolkit - Agent's Guide

Quick reference for AI agents working with the GPUI toolkit libraries.

Overview

The gpui-toolkit workspace contains several related crates for building GPUI applications:

Crate Purpose Documentation
gpui-au macOS Audio Unit platform backend — embeds GPUI inside AUv3 ViewControllers via Metal/wgpu lib.rs
gpui-hello-web Minimal wasm/browser spike app (gpui_web + gpui_wgpu canvas) this repo, just wasm-serve-hello
gpui-showcase Component showcase with a wasm/browser entry point (gpui_web + gpui_wgpu canvas) just wasm-serve-showcase
gpui-px (px-showcase) Chart showcase with a wasm/browser entry point just wasm-serve-px
gpui-builder Generic constraint-based layout solver — priority collapse, auto-axis, display tiers, dividers README
gpui-d3rs Low-level D3.js-inspired visualization primitives, incl. vello-backed 2D rasterization (vello2d module, zero-copy via WgpuCustomDraw, vello_cpu fallback); d3rs-showcase example doubles as the wasm demo (route /d3rs/) README
gpui-design Platform-adaptive design system (Apple HIG, Material 3, Fluent, Neutral) — spacing, corners, typography, animation README
gpui-foreign-parent Platform-neutral core for foreign-parent editor embedding (registry, frame throttle, resize debounce, callback slots, FFI helpers) contract
gpui-web-foreign Browser binding: page-owned canvas host shell (observers, rAF pump, listeners) plus DOM input tables; renderer provider needs the §16 fork change contract
gpui-win-foreign Windows binding: GPUI editors in host-owned HWNDs (VST3); WS_CHILD creation hook in the gpui_windows fork contract
gpui-linux-foreign Linux binding: X11 child windows (VST3/CLAP-x11) and Wayland subsurfaces (CLAP-wayland); creation hooks in the gpui_linux fork contract
gpui-ios iOS platform backend (Metal rendering, touch, text) README, AGENTS.md
gpui-pretext High-performance text measurement and multiline layout (Rust port of chenglou/pretext) README
gpui-profiler Lightweight allocation profiling utilities for interactive UI hot paths README
gpui-px High-level Plotly Express-style charting API, including unstructured MeshPlot README
gpui-mesh Mesh data model only: VTK-style cells (tet/hex/wedge/pyramid), scalar/vector/tensor/complex fields, boundary extraction, bounded surface chunking for large datasets; no GPUI/wgpu/IO, wasm-safe README
gpui-dataset-transformation Pure DataSet -> DataSet filters: plane slice/clip, threshold, marching-tet isosurface, calculators, flow diagnostics (vorticity/Q/divergence, optional wgpu compute via gpu feature), warp, glyphs, streamlines, probe, VTK/VTU/XDMF I/O; wasm-safe by default README
gpui-scene3d Scene rendering only: orbit camera, transfer functions, WGSL clipping-plane shaders, chunked GPU-ready buffers, software rasterizer (clipping + sorted transparency), volume raycasting, time playback, PNG sequences and MP4 muxing (mp4 feature, native ffmpeg), optional GPUI element (gpui feature); wasm-safe by default; mesh browser demo via just wasm-serve-mesh README
gpui-spinorama Spinorama-style speaker measurement showcase (CEA-2034 + dispersion, wasm route /spinorama/) this repo, just wasm-serve-spinorama
gpui-themes Theme editor and management infrastructure AGENTS.md
gpui-ui-kit Reusable UI components (buttons, forms, layout) with ARIA accessibility support lib.rs, AGENTS.md
gpui-ui-kit-macros Procedural macros for theme derivation and the layout! DSL README
gpui-toolkit-cli Unified gpui-toolkit binary: catalog, templates, themes, doctor, upgrade, layout tools README, TUTORIAL §15
gpui-layout-expr Layout-expression AST, parser, validation, custom aliases (no GPUI deps) layout spec
figma/ Figma-to-GPUI design system rules and Code Connect mappings DESIGN_SYSTEM_RULES.md, CODE_CONNECT_MAPPINGS.md

Read the full file on GitHub · 231 lines

Changes

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.

  1. yesterday Changed · +10 lines · +112 tokens per session efc04f16e738
  2. 6d ago Changed · +13 tokens per session c6598a53e66a
  3. 7d ago Changed · +3 lines · +269 tokens per session 2a47c066a6f1
  4. 8d ago Changed · +4 lines · +210 tokens per session f7c66304d233
  5. 9d ago Changed · +3 lines · +106 tokens per session 59721b3e2d6c
  6. 14d ago Changed · +16 lines · +307 tokens per session 20b11f1fa813
  7. 1mo ago First seen · 195 lines · 2,182 tokens per session scan A e239e4965987

Subscribe to this mod's changes

gpui-toolkit AGENTS.md is an instructions file published in the GitHub repository pierreaubert/gpui-toolkit (86 stars, last pushed today), licensed ISC. It adds 3,199 tokens to every session, about $0.0128 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 2026-08-30.

Related

Other instructions, from other repositories

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 9,649 tokens

next.js AGENTS.md

AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,549 tokens

vscode oss-third-party-notices.instructions.md

Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).

microsoft/vscode · 5,262 tokens

langchain AGENTS.md

AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.

langchain-ai/langchain · 4,680 tokens

vscode copilot-instructions.md

Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).

microsoft/vscode · 2,731 tokens

deno copilot-instructions.md

Copilot instructions for denoland/deno, covering deno development guide for github copilot, network access, high level overview, key directories and key files to understand first.

denoland/deno · 3,077 tokens