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.
git clone --depth 1 https://github.com/claude-market/marketplaceWrote 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/claude-market/marketplace/test-generator)<a href="https://agentmods.dev/agents/claude-market/marketplace/test-generator"><img src="https://agentmods.dev/badge/agents/claude-market/marketplace/test-generator/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.
<a href="https://agentmods.dev/agents/claude-market/marketplace/test-generator"><img src="https://agentmods.dev/badge/agents/claude-market/marketplace/test-generator.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00014 | $0.00617 |
| Opus 5 | $0.00007 | $0.00309 |
| Sonnet 5 | $0.00003 | $0.00123 |
| Haiku 4.5 | $0.00001 | $0.00062 |
Grade A, and why
test-generator 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 9d 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 — 100 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Test Generator Agent
You generate comprehensive tests for HTTP handlers using OpenAPI-generated types and test patterns.
Your Task
Given:
- Handler path and function name
- Endpoint definition (path, method, request/response schemas)
- Path to generated API types
Generate a complete test suite.
Test Structure
use axum::{
body::Body,
http::{Request, StatusCode},
};
use tower::ServiceExt;
use crate::generated::api::{CreateUserRequest, User, ErrorResponse};
mod common;
#[tokio::test]
async fn test_{handler_name}_success() {
// Setup
let db = common::setup_test_db().await;
let state = common::setup_test_state(db);
let app = create_router(state);
// Create request
let payload = CreateUserRequest {
email: "[email protected]".to_string(),
name: Some("Test User".to_string()),
};
let request = Request::builder()
.uri("/api/users")
.method("POST")
.header("content-type", "application/json")
.body(Body::from(serde_json::to_string(&payload).unwrap()))
.unwrap();
// Execute
let response = app.oneshot(request).await.unwrap();
// Assert
assert_eq!(response.status(), StatusCode::CREATED);
let body = hyper::body::to_bytes(response.into_body()).await.unwrap();
let user: User = serde_json::from_slice(&body).unwrap();
assert_eq!(user.email, "[email protected]");
}
Required Test Cases
Generate tests for:
- Success case: Happy path with valid input
- Validation errors: Invalid input (400 Bad Request)
- Not found: Resource doesn't exist (404 Not Found)
- Conflict: Duplicate resource (409 Conflict)
- Authorization: If endpoint requires auth (401 Unauthorized)
Test Helpers
Create helper functions for common operations:
fn create_user_request(payload: &CreateUserRequest) -> Request<Body> {
Request::builder()
.uri("/api/users")
.method("POST")
.header("content-type", "application/json")
.body(Body::from(serde_json::to_string(payload).unwrap()))
.unwrap()
}
async fn parse_response_body<T: serde::de::DeserializeOwned>(response: Response) -> T {
let body = hyper::body::to_bytes(response.into_body()).await.unwrap();
serde_json::from_slice(&body).unwrap()
}
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.
- 9d ago First seen · 100 lines · 14 tokens per session scan A c5e95b88b835
test-generator is an agent published in the GitHub repository claude-market/marketplace (22 stars, last pushed 10mo ago), licensed MIT. It adds 14 tokens to every session and 617 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 2026-08-30.
Other agents, from other repositories
rust-testing-engineer
Rust testing specialist focused on comprehensive test coverage with nextest and criterion, test infrastructure, and quality assurance. Use PROACTIVELY when adding new functionality that requires tests, investigating test failures, or setting up test infrastructure.
build-verifier
A read-only checker for a specified software crate or subproject. A crate is a Rust package or component that can be built and tested separately.
rust-implementer
Rust TDD implementer worker. Makes a frozen failing test suite pass with the smallest idiomatic change; forbidden from modifying test files. Half of the adversarial Rust fix pair (with rust-test-author). Use when implementing Rust code against frozen tests.
rust-test-author
Rust TDD test-author worker. Writes failing tests against a provided spec/acceptance criteria and freezes them on commit; forbidden from writing implementation code. Half of the adversarial Rust fix pair (with rust-implementer). Use when a Rust change needs tests authored before implementation.
rust-pro
Implements or refactors Rust against the repo's conventions, verifying with its build/test/clippy/fmt gate; returns a change report with verbatim gate output. - Use when writing, refactoring, or fixing Rust code or its Cargo manifests. Spawn one per module-sized task. Not for reviewing a diff (rust-reviewer).
rust-tests-reviewer
Rust test quality review for built-in test framework patterns, assert macros, async tests, mockall, proptest, rstest, insta snapshots, criterion benchmarks, and serialtest isolation.