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/sync-modelsnpx skills add FacturaScripts/fs-claude-plugin --skill sync-modelsgit 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 | $0.00100 | $0.04406 |
| Opus 5 | $0.00050 | $0.02203 |
| Sonnet 5 | $0.00020 | $0.00881 |
| Haiku 4.5 | $0.00010 | $0.00441 |
Grade A, and why
sync-models 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 — 292 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Sync Models — Mantenimiento de la metadata del MCP
Esta skill es la herramienta de mantenimiento del catálogo de modelos del plugin fs-mcp. Úsala cuando:
- Quieras añadir un modelo nuevo del core de FacturaScripts o de un plugin privado.
- Hayas actualizado FacturaScripts (o un plugin) y quieras revisar si algún modelo ya configurado tiene columnas nuevas, modificadas o eliminadas.
- Quieras hacer un refresh masivo de todos los modelos del catálogo y actualizar la versión registrada del core.
La skill respeta la separación entre core y privados:
- Core → modifica archivos del repo del MCP (
server/src/...) y compila. - Privados → modifica archivos en la ruta privada del usuario (
<outputBase>/...); no compila (los privados se cargan dinámicamente al arrancar el servidor).
Cómo invocar
El usuario te indicará tres datos por cada modelo:
- Nombre del modelo en snake_case (ej:
cliente,factura_cliente,task). - Tipo:
coreoprivate. - Origen (de dónde leer la fuente):
- Ruta local absoluta: ej.
/Users/yo/facturascriptso/Users/yo/facturascripts/Plugins/Forja. - URL de GitHub: ej.
https://github.com/NeoRazorX/facturascriptso de un plugin.
- Ruta local absoluta: ej.
Ejemplos de invocación habituales:
Revisa el modelo cliente del core, fuente /Users/yo/facturascriptsRevisa los modelos cliente, producto y factura_cliente, todos en /Users/yo/facturascriptsRevisa task y publication, ambos privados, en /Users/yo/facturascripts/Plugins/ForjaRevisa task del plugin privado en https://github.com/X/ForjaRefresca todos los modelos del core desde /Users/yo/facturascripts y actualiza la versión
Si el usuario no aporta alguno de los tres datos, pregúntale antes de continuar.
Conceptos previos
Lo primero que debes hacer es familiarizarte con el estado actual del MCP si no lo has hecho ya:
| Archivo | Rol |
|---|---|
server/src/scripts/generate-metadata.ts |
Genera la metadata (modo CORE y modo PLUGIN). Contiene MODEL_CATALOG con los modelos del core. |
server/src/metadata/descriptions-overrides.json |
Descripciones contextuales del core. Single source of truth (committed). |
server/src/metadata/models/*.ts |
Metadata generada por modelo (CORE). No editar a mano. |
server/src/metadata/index.ts |
Agregador auto-generado. |
<outputBase>/manifest.json |
Manifest del plugin privado (declara los modelos del plugin). Siempre se llama manifest.json, nunca manifest-nombre.json. |
<outputBase>/descriptions.json |
Descripciones del plugin privado. Siempre se llama descriptions.json, nunca nombre-descriptions.json. |
<outputBase>/<modelo>/metadata.js |
Metadata generada del modelo privado. No editar a mano. |
<outputBase>/<modelo>/index.js |
Loader del módulo privado. Re-exporta modelMetadata desde ./metadata.js. |
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 · 292 lines · 100 tokens per session scan A 27f107c3d250
sync-models is a skill published in the GitHub repository FacturaScripts/fs-claude-plugin (8 stars, last pushed 2mo ago), licensed MIT. It adds 100 tokens to every session and 4,406 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 skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
auto-perf-optimize
Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.
chat-perf
Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…