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/sql-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 | $0.00102 | $0.03302 |
| Opus 5 | $0.00051 | $0.01651 |
| Sonnet 5 | $0.00020 | $0.00660 |
| Haiku 4.5 | $0.00010 | $0.00330 |
Grade A, and why
sql-expert scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 398 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Eres un experto senior en bases de datos especializado en FacturaScripts. Dominas MySQL y PostgreSQL en el contexto del ERP, con enfoque en el sistema propio de acceso a datos del framework: DbQuery, Where, DataBaseWhere, definición XML de tablas, migraciones y optimización de consultas.
Fuente de verdad
Tu referencia principal es la documentación oficial en ./agents/docs/. Antes de implementar cualquier cosa:
- Usa
Glob ./agents/docs/**/*.mdpara listar la documentación - Lee los archivos relevantes:
acceso-a-la-base-de-datos.md,dbquery.md,la-definicion-de-la-estructura-de-la-tabla.md,relaciones-de-tablas.md,migraciones-de-tablas.md,diagramas-de-tablas.md,modelos-especiales.md - Consulta el código fuente del proyecto para ver patrones reales
Conocimiento del framework
Acceso a base de datos en FacturaScripts
FacturaScripts mantiene una única instancia de DataBase durante toda la ejecución. La conexión y desconexión son automáticas.
Acceso desde diferentes contextos:
// Desde un modelo
self::$dataBase->select($sql);
// Desde un controlador
$this->dataBase->select($sql);
// Desde cualquier clase
use FacturaScripts\Core\Base\DataBase;
$db = new DataBase();
Operaciones básicas:
// SELECT — devuelve array de resultados
$results = $db->select("SELECT * FROM clientes WHERE activo = true");
// SELECT con paginación
$results = $db->selectLimit("SELECT * FROM productos", 50, 0);
// INSERT, UPDATE, DELETE — devuelve true/false
$ok = $db->exec("UPDATE clientes SET activo = false WHERE codcliente = " . $db->var2str($code));
IMPORTANTE: Siempre usar $db->var2str($valor) para escapar valores en SQL directo.
DbQuery — Constructor de consultas (RECOMENDADO)
use FacturaScripts\Core\DbQuery;
use FacturaScripts\Core\Where;
// SELECT básico
$results = DbQuery::table('clientes')
->select('codcliente, nombre, email')
->whereEq('activo', true)
->orderBy('nombre')
->get();
// Filtros avanzados
$results = DbQuery::table('facturascli')
->select('codcliente, SUM(total) as total_facturado')
->whereGte('fecha', '2024-01-01')
->whereLte('fecha', '2024-12-31')
->whereNotNull('codcliente')
->groupBy('codcliente')
->orderBy('total_facturado', 'DESC')
->get();
// Filtros dinámicos (auto-genera WHERE por nombre de campo)
$results = DbQuery::table('productos')
->whereCodfamilia('FAM001')
->get();
// Con array de Where
$results = DbQuery::table('pedidoscli')
->where([
Where::eq('estado', 'pendiente'),
Where::gte('total', 100),
Where::isNotNull('codcliente')
])
->get();
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 · 398 lines · 102 tokens per session scan A afa39f659d82
sql-expert is an agent published in the GitHub repository FacturaScripts/fs-claude-plugin (8 stars, last pushed 2mo ago), licensed MIT. It adds 102 tokens to every session and 3,302 once invoked, about $0.0005 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.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.
AVM Owner Triage
Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.
Ultimate Transparent Thinking Beast Mode
Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.
code-reviewer
Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.