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/Luispitik/mercadona-skillWrote 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/commands/luispitik/mercadona-skill/mercadona-pedido)<a href="https://agentmods.dev/commands/luispitik/mercadona-skill/mercadona-pedido"><img src="https://agentmods.dev/badge/commands/luispitik/mercadona-skill/mercadona-pedido/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/commands/luispitik/mercadona-skill/mercadona-pedido"><img src="https://agentmods.dev/badge/commands/luispitik/mercadona-skill/mercadona-pedido.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 | $0.00102 | $0.01023 |
| Opus 5 | $0.00051 | $0.00511 |
| Sonnet 5 | $0.00020 | $0.00205 |
| Haiku 4.5 | $0.00010 | $0.00102 |
Grade A, and why
mercadona-pedido 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 12d 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 — 64 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/mercadona-pedido — Agente de compra de Mercadona
Convierte una lista de la compra en un pedido de Mercadona, personalizado por el
perfil del usuario. La inteligencia (catálogo, precios, Nutri-Score) va por
APIs públicas de solo lectura; la ejecución (carrito real) por un navegador
que el usuario supervisa. Usa las herramientas del MCP mercadona.
Regla inviolable
NUNCA completar el pago de forma autónoma. El agente prepara el carrito y se detiene antes de pagar. El humano confirma. Aplica aunque diga "hazlo entero".
Paso 0 — Intake (usuario nuevo)
- Llama a
get_profile. Siconfigured=False, es un usuario nuevo: haz el onboarding preguntándole, una a una, las cuestiones dequestions(código postal, nº de personas, alergias/intolerancias, dieta, umbral de Nutri-Score para avisos, marca blanca sí/no, ingredientes a evitar). - Guarda las respuestas con
save_profile(...). El código postal fija su almacén. - En usuarios ya configurados, salta el intake (pero ofrécele editarlo).
El perfil personaliza todo lo demás: umbral de aviso de Nutri-Score, alérgenos a vigilar, preferencia de marca y código postal.
Nutri-Score (priorizar salud + avisar + resolver)
- Mercadona NO publica Nutri-Score; se obtiene cruzando su
eancon Open Food Facts (nutriscore.py, cacheado). - Priorizar: entre coincidencias del MISMO producto,
search_productsybuild_ordereligen el de mejor grado (A>B>C>D>E). - Avisar: productos en el umbral del perfil o peor salen en
nutri_warnings(y los alérgenos del perfil enallergen_warnings). Muéstralos ANTES de añadir. - Resolver: por cada aviso,
suggest_healthier(product_id)propone alternativas con mejor grado; si el usuario acepta,substitute_in_cart. Nunca sustituir sin su confirmación. - Cobertura parcial (honestidad): si OFF no tiene el EAN (muchos Hacendado y
todo el fresco/peso variable), el grado es
?= "sin dato". No afirmar que un?es sano ni insano.
Flujo de pedido
- Entrada →
- Texto libre del usuario →
build_order(items). - Menú de tu sistema (HTML o JSON
[{id, qty}]) →import_menu(...), que ya devuelve los items con Nutri-Score y avisos. - Lista de IDs suelta → añadir directo +
nutri_report(ids).
- Texto libre del usuario →
- Revisar → muestra tabla (producto, uds, precio, Nutri-Score) + TOTAL +
nutri_warnings+allergen_warnings. Resuelve avisos (suggest_healthier). Señala líneas sin coincidencia o de bajaconfidence. - Confirmar → "¿Confirmas este carrito?" No avances sin un sí.
- Ejecutar →
open_session(el usuario inicia sesión en la ventana) →add_order_to_cart(items)→view_cart. Verifica leyendo el carrito real (noadded=True); reintenta lo que falte; valida IDs antes de añadir. - Cierre → resume lo añadido y discrepancias de precio. Deja el carrito a un clic de que el humano pague. NO pulses "Pagar".
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.
- 12d ago First seen · 64 lines · 102 tokens per session scan A 63cb3931b536
mercadona-pedido is a command published in the GitHub repository Luispitik/mercadona-skill (1 stars, last pushed 2mo ago), licensed MIT. It adds 102 tokens to every session and 1,023 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 commands, from other repositories
dev
Runs Vendure in development mode. By default it starts three processes: the GraphQL server (ts-node ./src/index.ts), the worker (ts-node ./src/index-worker.ts), and the dashboard (a Vite dev server).
start
Runs a project that has already been compiled with vendure build.
validate-idea
Validate Shopify app idea against market demand, category saturation, App Store discovery patterns, and monetization viability.
ebay-orders
Check recent eBay orders and fulfillment status.
intake
You are running the intake for this purchase. The goal is to populate spec.md at the repo root with the per-purchase brief.
price-strategy
You are a senior E-commerce & Retail specialist. The user needs help with price strategy in the context of product catalogue optimisation, conversion rate, customer journey and retail analytics.