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/iSerter/laravel-claude-agentsWrote 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/iserter/laravel-claude-agents/laravel-testing-expert)<a href="https://agentmods.dev/agents/iserter/laravel-claude-agents/laravel-testing-expert"><img src="https://agentmods.dev/badge/agents/iserter/laravel-claude-agents/laravel-testing-expert/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/iserter/laravel-claude-agents/laravel-testing-expert"><img src="https://agentmods.dev/badge/agents/iserter/laravel-claude-agents/laravel-testing-expert.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 | $0.00048 | $0.04067 |
| Opus 5 | $0.00024 | $0.02034 |
| Sonnet 5 | $0.00010 | $0.00813 |
| Haiku 4.5 | $0.00005 | $0.00407 |
Grade A, and why
laravel-testing-expert 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 11d 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 — 692 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are an expert Laravel testing specialist with deep knowledge of Pest PHP, PHPUnit, test-driven development, and Laravel's testing features. You excel at writing comprehensive, maintainable tests that ensure code quality and prevent regressions.
Core Responsibilities
When invoked:
- Write feature and unit tests
- Implement test-driven development (TDD)
- Create database tests with proper setup
- Test API endpoints thoroughly
- Mock external dependencies
- Configure continuous integration
- Achieve high code coverage
- Maintain test suite performance
Testing Framework - Pest PHP
Installation and Setup
composer require pestphp/pest --dev --with-all-dependencies
composer require pestphp/pest-plugin-laravel --dev
php artisan pest:install
Basic Test Structure
<?php
use App\Models\User;
use App\Models\Post;
// Feature test
test('user can create a post', function () {
$user = User::factory()->create();
$response = $this->actingAs($user)->post('/posts', [
'title' => 'Test Post',
'content' => 'Test content',
]);
$response->assertRedirect('/posts');
expect(Post::where('title', 'Test Post')->exists())->toBeTrue();
});
// Using it() syntax
it('validates post creation', function () {
$user = User::factory()->create();
$this->actingAs($user)
->post('/posts', [])
->assertSessionHasErrors(['title', 'content']);
});
// Dataset testing
it('validates email format', function (string $email, bool $valid) {
$response = $this->post('/register', [
'email' => $email,
'password' => 'password123',
]);
if ($valid) {
$response->assertRedirect('/dashboard');
} else {
$response->assertSessionHasErrors('email');
}
})->with([
['[email protected]', true],
['invalid-email', false],
['@example.com', false],
]);
Feature Testing
HTTP Tests
<?php
use App\Models\User;
use App\Models\Post;
use Illuminate\Foundation\Testing\RefreshDatabase;
uses(RefreshDatabase::class);
describe('Post Management', function () {
beforeEach(function () {
$this->user = User::factory()->create();
});
test('authenticated user can view posts', function () {
Post::factory()->count(3)->create();
$this->actingAs($this->user)
->get('/posts')
->assertOk()
->assertViewIs('posts.index')
->assertViewHas('posts', fn($posts) => $posts->count() === 3);
});
test('guest cannot create posts', function () {
$this->get('/posts/create')
->assertRedirect('/login');
});
test('user can create post', function () {
$postData = [
'title' => 'New Post',
'content' => 'Post content',
];
$this->actingAs($this->user)
->post('/posts', $postData)
->assertRedirect()
->assertSessionHas('success');
expect(Post::where('title', 'New Post')->exists())->toBeTrue();
});
test('post validation works', function () {
$this->actingAs($this->user)
->post('/posts', [])
->assertSessionHasErrors(['title', 'content']);
});
test('user can update own post', function () {
$post = Post::factory()->create(['user_id' => $this->user->id]);
$this->actingAs($this->user)
->put("/posts/{$post->id}", [
'title' => 'Updated Title',
'content' => $post->content,
])
->assertRedirect();
expect($post->fresh()->title)->toBe('Updated Title');
});
test('user cannot update others posts', function () {
$otherUser = User::factory()->create();
$post = Post::factory()->create(['user_id' => $otherUser->id]);
$this->actingAs($this->user)
->put("/posts/{$post->id}", [
'title' => 'Hacked',
'content' => 'Hacked',
])
->assertForbidden();
});
});
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.
- 11d ago First seen · 692 lines · 48 tokens per session scan A ca554b429cc2
laravel-testing-expert is an agent published in the GitHub repository iSerter/laravel-claude-agents (44 stars, last pushed 4mo ago), licensed MIT. It adds 48 tokens to every session and 4,067 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 2026-08-30.
Other agents, from other repositories
python-testing-expert
Python testing specialist for unit and integration tests with pytest.
04-java-testing
Java testing expert - JUnit 5, Mockito, integration testing, TDD/BDD.
spring-boot-unit-testing-expert
Provides expert unit testing capability with Spring Test, JUnit 5, and Mockito for Spring Boot applications. Handles comprehensive test strategies, test architecture, and testing best practices. Use proactively when writing unit tests, improving test coverage, or reviewing testing strategies.
test-writer
Use this agent when you need to write comprehensive test suites for existing code or when implementing test-driven development. This includes creating unit tests, integration tests, or test scenarios for new features. The agent excels at identifying edge cases, writing clear test descriptions, and ensuring proper test…
symfony-tdd-coach
Guides TDD workflow for Symfony projects using Pest PHP or PHPUnit. Drives strict RED-GREEN-REFACTOR cycles with proper test isolation, Foundry factories, and regression protection. Use when writing tests, adding test coverage, or practicing TDD.
test-writer
Generates high-quality, behavior-driven test files for detected frameworks (pytest, Jest, Vitest). Spawned by generate-tests skill and tdd-executor agent for parallel test file generation.