gpui-review

gpui-review is a command for coding agents from geoffjay/claude-plugins. It costs 24 tokens per session (2,053 once invoked), scanned A, original, MIT.

A code-review command for GPUI projects, where GPUI is a Rust framework for desktop user interfaces. It examines GPUI source files for code structure, performance, state handling, and framework conventions.

In plain words
What is it for?
Use it to review a selected Rust file or directory, or to inspect an entire project for view and model organization, component design, naming, and GPUI usage.
Why use it?
It helps find unclear responsibilities, tightly connected components, incorrect state ownership, missing error handling, and avoidable performance problems before they become harder to fix.

Command

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 commands/geoffjay/claude-plugins/gpui-review
Clone the repo
git clone --depth 1 https://github.com/geoffjay/claude-plugins

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-review

README.md
[![agentmods](https://agentmods.dev/badge/commands/geoffjay/claude-plugins/gpui-review.svg)](https://agentmods.dev/commands/geoffjay/claude-plugins/gpui-review)
Your own site
<a href="https://agentmods.dev/commands/geoffjay/claude-plugins/gpui-review"><img src="https://agentmods.dev/badge/commands/geoffjay/claude-plugins/gpui-review.svg" alt="Measured on agentmods" height="20"></a>
Per session 24 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,053 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 $0.00024 $0.02053
Opus 5 $0.00012 $0.01026
Sonnet 5 $0.00005 $0.00411
Haiku 4.5 $0.00002 $0.00205

Measured 4d ago against content hash ba5b9969cd19, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

gpui-review 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 4d 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/commands/gpui-review.md · 362 lines

How it starts

The opening of the file, as written. The whole thing — 362 lines — stays where its author put it; the contents beside it link to each section on GitHub.

GPUI Code Review

Perform comprehensive code review of GPUI applications, identifying issues with patterns, performance, state management, and suggesting improvements.

Arguments

  • $1: Path (optional) - Specific file or directory to review. If not provided, reviews entire project.

Workflow

1. Search for GPUI Code

  • Locate all .rs files in the project or specified path
  • Identify files using GPUI (imports gpui::* or specific GPUI types)
  • Categorize files by type:
    • View components (impl Render)
    • Models (application state)
    • Main entry points
    • Utility code

2. Analyze Component Patterns

Review each component for:

Component Structure
  • Proper use of View vs Model types
  • Clear separation of concerns
  • Component has single responsibility
  • Props/dependencies passed explicitly
  • Proper lifetime management
Anti-patterns
  • God components (doing too much)
  • Tight coupling between components
  • Improper state ownership
  • Missing error handling
  • Inconsistent naming conventions

Example issues to flag:

// BAD: Component doing too much
impl Render for GodComponent {
    fn render(&mut self, cx: &mut ViewContext<Self>) -> impl IntoElement {
        // Fetching data
        // Computing business logic
        // Rendering UI
        // Handling all events
        // Managing multiple concerns
    }
}

// GOOD: Focused component
impl Render for FocusedComponent {
    fn render(&mut self, cx: &mut ViewContext<Self>) -> impl IntoElement {
        let state = self.model.read(cx);
        div().child(format!("Count: {}", state.count))
    }
}

3. Check State Management

Review state management for:

Model Usage
  • State properly encapsulated in Model types
  • Appropriate use of cx.new_model()
  • State updates use model.update()
  • No direct state mutation outside updates
  • Proper state ownership hierarchy
Subscription Management
  • Subscriptions created during initialization, not render
  • Subscriptions stored to prevent cleanup
  • cx.observe() used for model changes
  • No subscription leaks
  • Proper cleanup in Drop if needed

Read the full file on GitHub · 362 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. 4d ago First seen · 362 lines · 24 tokens per session scan A ba5b9969cd19

Subscribe to this mod's changes

gpui-review is a command published in the GitHub repository geoffjay/claude-plugins (8 stars, last pushed 10mo ago), licensed MIT. It adds 24 tokens to every session and 2,053 once invoked, about $0.0001 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.