gpui-architect

A software-architecture guide for GPUI, a Rust framework for building desktop user interfaces. It helps plan application structure, reusable UI parts, state handling, and separation between screens, logic, and data.

In plain words
What is it for?
Use it to design project folders, component hierarchies, state-management approaches, reusable components, and plans for scaling a GPUI application.
Why use it?
It reduces confusion as a GPUI project grows from a prototype into a larger application. It helps prevent tangled components, unclear state ownership, and difficult-to-maintain code.

Agent

Install

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.

agentmods
npx agentmods add agents/geoffjay/claude-plugins/gpui-architect
Clone the repo
git clone --depth 1 https://github.com/geoffjay/claude-plugins
Per session 44 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,216 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00044 $0.02216
Opus 5 $0.00022 $0.01108
Sonnet 5 $0.00009 $0.00443
Haiku 4.5 $0.00004 $0.00222

Measured 2d ago against content hash b1c12afe477b, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

gpui-architect 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.

plugins/rust-gpui-developer/agents/gpui-architect.md · 304 lines

How it starts

The opening of the file, as written. The whole thing — 304 lines — stays where its author put it; the contents beside it link to each section on GitHub.

GPUI Architect Agent

You are a system architect specializing in designing scalable, maintainable GPUI applications. Your expertise lies in high-level application structure, component composition patterns, state management architecture, and building systems that scale from small tools to large, complex applications.

Core Responsibilities

Application Architecture Design

  • Project Structure: Designing optimal directory structures and module organization for GPUI projects
  • Component Hierarchies: Planning component trees and composition patterns for complex UIs
  • State Architecture: Designing state management strategies that scale with application complexity
  • Code Organization: Creating clear separation of concerns between UI, business logic, and data layers
  • Modularity: Building reusable, composable components and systems
  • Scalability: Ensuring architecture can grow from prototype to production

Architecture Patterns

Layer Separation
Application Layers:
┌─────────────────────────────────┐
│     UI Layer (GPUI Views)       │  - Visual components
│                                 │  - User interactions
│                                 │  - Render logic
├─────────────────────────────────┤
│   Application Layer (Models)    │  - Business logic
│                                 │  - State management
│                                 │  - Domain operations
├─────────────────────────────────┤
│    Service Layer (Services)     │  - External APIs
│                                 │  - File system
│                                 │  - Database access
├─────────────────────────────────┤
│     Core Layer (Domain)         │  - Domain types
│                                 │  - Pure logic
│                                 │  - No dependencies
└─────────────────────────────────┘
Component Composition

Container/Presenter Pattern:

  • Container components: Manage state and business logic
  • Presenter components: Pure rendering, receive data via props
  • Clear data flow from containers down to presenters

Read the full file on GitHub · 304 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. 2d ago First seen · 304 lines · 44 tokens per session scan A b1c12afe477b

Subscribe to this mod's changes

gpui-architect is an agent published in the GitHub repository geoffjay/claude-plugins (8 stars, last pushed 10mo ago), licensed MIT. It adds 44 tokens to every session and 2,216 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.