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 agentmods add commands/geoffjay/claude-plugins/gpui-reviewgit 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-review)<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>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 | $0.00024 | $0.02053 |
| Opus 5 | $0.00012 | $0.01026 |
| Sonnet 5 | $0.00005 | $0.00411 |
| Haiku 4.5 | $0.00002 | $0.00205 |
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.
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
.rsfiles 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
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.
- 4d ago First seen · 362 lines · 24 tokens per session scan A ba5b9969cd19
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.
Other commands, from other repositories
git
Git operations with intelligent commit messages and workflow optimization.
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.