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 skills/facturascripts/fs-claude-plugin/testing-expertnpx skills add FacturaScripts/fs-claude-plugin --skill testing-expertgit clone --depth 1 https://github.com/FacturaScripts/fs-claude-pluginWrote 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/skills/facturascripts/fs-claude-plugin/testing-expert)<a href="https://agentmods.dev/skills/facturascripts/fs-claude-plugin/testing-expert"><img src="https://agentmods.dev/badge/skills/facturascripts/fs-claude-plugin/testing-expert.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 | $0.00264 | $0.00969 |
| Opus 5 | $0.00132 | $0.00485 |
| Sonnet 5 | $0.00053 | $0.00194 |
| Haiku 4.5 | $0.00026 | $0.00097 |
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 3d 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 — 76 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Skill: testing-expert — Especialista en testing y calidad de FacturaScripts
Esta skill conecta las tareas de testing y calidad del usuario con el agente testing-expert,
que domina PHPUnit en FacturaScripts, PHPStan, CS-Check, modo debug y diagnóstico de errores.
Por qué usar el agente
El agente testing-expert conoce la estructura de tests específica de FacturaScripts:
la carpeta Test/ con escenarios (main/, con-otro-plugin/), los archivos install-plugins.txt,
el namespace FacturaScripts\Test\Plugins, los patrones de test para modelos (CRUD, validación,
relaciones, sanitización), el nivel de PHPStan habitual (5-6), las reglas PSR-12 del framework,
y las herramientas fsmaker para testing. Estos patrones son propios del ERP y no se encuentran
en documentación genérica de PHPUnit.
Cómo invocar el agente
Usa el agente testing-expert pasándole la tarea del usuario:
Agente: testing-expert
Tarea: [descripción exacta de lo que necesita el usuario]
El agente:
- Consulta la documentación en
./agents/docs/(testeo-de-plugins, gestion-de-errores, la-clase-tools) - Analiza los tests existentes del plugin
- Implementa tests o ejecuta herramientas de calidad
- Reporta resultados con métricas claras
Qué tareas activan esta skill
- "Escribe tests PHPUnit para mi modelo Proyecto"
- "Ejecuta PHPStan y corrige los errores"
- "Verifica que mi código cumple PSR-12"
- "¿Cómo activo el modo debug en FacturaScripts?"
- "Mi extensión no se está aplicando, ¿cómo lo diagnostico?"
- "Necesito tests para verificar que el worker se ejecuta correctamente"
- "¿Cómo uso Tools::log() para depurar mi plugin?"
- "La tabla no se crea al instalar el plugin, ¿qué puede ser?"
- "Crea tests de validación para datos inválidos (XSS, campos vacíos, duplicados)"
- "¿Cómo configuro install-plugins.txt para mis tests?"
- "Escribe un test que verifique los asientos contables de los prepagos"
- "Necesito un test con un documento en 2025 y un pago en 2026 (ejercicios distintos)"
- "¿Cómo uso DefaultSettingsTrait e installAccountingPlan en mis tests?"
- "El test necesita que existan ejercicios contables, ¿cómo los creo si no existen?"
- "Verifica que las subcuentas de las partidas pertenecen al ejercicio correcto"
- "Añade el test para este caso en el archivo PrePagoCliTest o PrePagoProvTest existente"
- Cualquier tarea que involucre testing, calidad de código o diagnóstico de errores
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.
- 3d ago First seen · 76 lines · 264 tokens per session scan A 5110a93b61ec
testing-expert is a skill published in the GitHub repository FacturaScripts/fs-claude-plugin (8 stars, last pushed 2mo ago), licensed MIT. It adds 264 tokens to every session and 969 once invoked, about $0.0013 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 skills, from other repositories
run-helix-tests
Submit and monitor .NET MAUI unit tests on Helix infrastructure. Supports running XAML, Resizetizer, Core, Essentials, and other unit test projects on distributed Helix queues.
agui-dotnet-unit-tests
Author unit tests for the AG-UI .NET SDK (the .UnitTests projects), following the SDK's serialization and compatibility conventions. USE FOR: adding unit-test coverage for a new type/method in AGUI.Abstractions/Formatting/Protobuf/Client/Server, event serialization round-trips, JsonDocument property-name assertions…
prowler-test-api
Testing patterns for Prowler API: JSON:API, Celery tasks, RLS isolation, RBAC. Trigger: When writing tests for api/ (JSON:API requests/assertions, cross-tenant isolation, RBAC, Celery tasks, viewsets/serializers).
gen-test
Generate idiomatic tests for Go packages and handlers in the Meshery project.
golang-testing
Production-ready Golang tests — table-driven tests, testify suites and mocks, parallel tests, fuzzing, fixtures, goroutine leak detection with goleak, snapshot testing, code coverage, integration tests, idiomatic test naming. Use when writing or reviewing Go tests, choosing a testing approach, setting up Go test CI…
nunit-testing
Use when writing or modifying tests in NUnit's own test projects, or when making a behavioral change to production code that needs test coverage. Covers test structure, attribute choice, helper visibility, platform guards, and which test projects are real.