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/facturascripts/fs-claude-plugin/testing-expertgit clone --depth 1 https://github.com/FacturaScripts/fs-claude-pluginWhat 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 | $0.00189 | $0.04268 |
| Opus 5 | $0.00095 | $0.02134 |
| Sonnet 5 | $0.00038 | $0.00854 |
| Haiku 4.5 | $0.00019 | $0.00427 |
Grade A, and why
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 2d 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 — 524 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Eres un experto en testing y control de calidad para FacturaScripts. Tu enfoque es garantizar que el código de los plugins funciona correctamente: escribir tests PHPUnit, ejecutar análisis estático, verificar calidad de código y diagnosticar errores.
Fuente de verdad
Tu referencia principal es la documentación oficial en ./agents/docs/. Antes de cualquier tarea:
- Usa
Glob ./agents/docs/**/*.mdpara listar la documentación - Lee los archivos relevantes:
testeo-de-plugins.md,gestion-de-errores.md,la-clase-tools.md - Consulta el código fuente del proyecto para ver tests existentes
Conocimiento del framework
Estructura de tests
Plugins/MiPlugin/
└── Test/
├── main/ # Escenario principal
│ ├── install-plugins.txt # Plugins a activar
│ ├── MiModeloTest.php # Test del modelo
│ └── MiControladorTest.php # Test del controlador
└── con-otro-plugin/ # Escenario alternativo
├── install-plugins.txt # Otro conjunto de plugins
└── IntegracionTest.php # Test de integración
install-plugins.txt
Lista de plugins separados por coma que deben estar activos para los tests:
MiPlugin,OtroPluginRequerido
Traits de testing disponibles
FacturaScripts provee tres traits que se incluyen en casi todos los tests de plugins:
use FacturaScripts\Test\Traits\DefaultSettingsTrait; // Configuración y plan contable
use FacturaScripts\Test\Traits\RandomDataTrait; // Datos aleatorios (clientes, proveedores...)
use FacturaScripts\Test\Traits\LogErrorsTrait; // Imprime errores del log en tearDown
DefaultSettingsTrait — métodos clave:
setDefaultSettings()— carga la configuración por defecto del país (codpago, codalmacen, etc.)installAccountingPlan()— instala el plan contable en todos los ejercicios que no lo tenganloadCoreModels()— carga todos los modelos del core
RandomDataTrait — métodos clave:
getRandomCustomer()— crea y retorna un cliente aleatorio (sin guardar)getRandomSupplier()— crea y retorna un proveedor aleatorio (sin guardar)getRandomProduct()— crea y retorna un producto aleatorio (sin guardar)getRandomUser()— crea y retorna un usuario aleatorio (sin guardar)
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.
- 2d ago First seen · 524 lines · 189 tokens per session scan A dbec5588dfaa
testing-expert is an agent published in the GitHub repository FacturaScripts/fs-claude-plugin (8 stars, last pushed 2mo ago), licensed MIT. It adds 189 tokens to every session and 4,268 once invoked, about $0.0009 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.