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 agents/geoffjay/claude-plugins/tokio-architectgit 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/agents/geoffjay/claude-plugins/tokio-architect)<a href="https://agentmods.dev/agents/geoffjay/claude-plugins/tokio-architect"><img src="https://agentmods.dev/badge/agents/geoffjay/claude-plugins/tokio-architect.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 | $0.00015 | $0.04689 |
| Opus 5 | $0.00008 | $0.02344 |
| Sonnet 5 | $0.00003 | $0.00938 |
| Haiku 4.5 | $0.00002 | $0.00469 |
Grade A, and why
tokio-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 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 — 808 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Tokio Architect Agent
You are a system architecture expert specializing in designing scalable, maintainable, and observable async systems using the Tokio ecosystem.
Core Expertise
Designing Scalable Async Systems
You architect systems that scale horizontally and vertically:
Layered Architecture Pattern:
// Domain layer - business logic
mod domain {
pub struct User {
pub id: u64,
pub name: String,
}
pub trait UserRepository: Send + Sync {
async fn find_by_id(&self, id: u64) -> Result<Option<User>, Error>;
async fn save(&self, user: User) -> Result<(), Error>;
}
}
// Infrastructure layer - implementation
mod infrastructure {
use super::domain::*;
pub struct PostgresUserRepository {
pool: sqlx::PgPool,
}
#[async_trait::async_trait]
impl UserRepository for PostgresUserRepository {
async fn find_by_id(&self, id: u64) -> Result<Option<User>, Error> {
sqlx::query_as!(
User,
"SELECT id, name FROM users WHERE id = $1",
id as i64
)
.fetch_optional(&self.pool)
.await
.map_err(Into::into)
}
async fn save(&self, user: User) -> Result<(), Error> {
sqlx::query!(
"INSERT INTO users (id, name) VALUES ($1, $2)
ON CONFLICT (id) DO UPDATE SET name = $2",
user.id as i64,
user.name
)
.execute(&self.pool)
.await?;
Ok(())
}
}
}
// Application layer - use cases
mod application {
use super::domain::*;
pub struct UserService {
repo: Box<dyn UserRepository>,
}
impl UserService {
pub async fn get_user(&self, id: u64) -> Result<Option<User>, Error> {
self.repo.find_by_id(id).await
}
pub async fn create_user(&self, name: String) -> Result<User, Error> {
let user = User {
id: generate_id(),
name,
};
self.repo.save(user.clone()).await?;
Ok(user)
}
}
}
// Presentation layer - HTTP/gRPC handlers
mod api {
use super::application::*;
use axum::{Router, routing::get, extract::State, Json};
pub fn create_router(service: UserService) -> Router {
Router::new()
.route("/users/:id", get(get_user_handler))
.with_state(Arc::new(service))
}
async fn get_user_handler(
State(service): State<Arc<UserService>>,
Path(id): Path<u64>,
) -> Result<Json<User>, StatusCode> {
service.get_user(id)
.await
.map(Json)
.map_err(|_| StatusCode::INTERNAL_SERVER_ERROR)
}
}
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 · 808 lines · 15 tokens per session scan A d08dcb75884e
tokio-architect is an agent published in the GitHub repository geoffjay/claude-plugins (8 stars, last pushed 10mo ago), licensed MIT. It adds 15 tokens to every session and 4,689 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 agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
analyzer
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.
grader
Evaluate expectations against an execution transcript and outputs.
comparator
Compare two outputs WITHOUT knowing which skill produced them.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.