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 skills add synerarg/claude-code-skills --skill mercadopagogit clone --depth 1 https://github.com/synerarg/claude-code-skillsWrote 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/synerarg/claude-code-skills/mercadopago)<a href="https://agentmods.dev/skills/synerarg/claude-code-skills/mercadopago"><img src="https://agentmods.dev/badge/skills/synerarg/claude-code-skills/mercadopago/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/skills/synerarg/claude-code-skills/mercadopago"><img src="https://agentmods.dev/badge/skills/synerarg/claude-code-skills/mercadopago.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 | $0.00457 | $0.03116 |
| Opus 5 | $0.00229 | $0.01558 |
| Sonnet 5 | $0.00091 | $0.00623 |
| Haiku 4.5 | $0.00046 | $0.00312 |
Grade A, and why
mercadopago 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 9d 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.
The source is not reproduced here
No licence file
A repository with no LICENSE is all rights reserved by default, so the body is not copied here. The metadata, the measurements and the link are.
What ships with it
15 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- assets/migration.sql 1.5 KB
- references/checkout-bricks.md 10 KB
- references/checkout-pro.md 13 KB
- references/database-adapters.md 9.0 KB
- references/fees-pricing.md 3.3 KB
- references/marketplace-split.md 3.2 KB
- references/mcp-server.md 9.5 KB
- references/money-out.md 4.6 KB
- references/orders-api.md 5.6 KB
- references/payment-methods.md 4.0 KB
- references/refunds-cancellations.md 6.3 KB
- references/subscriptions.md 3.4 KB
- references/troubleshooting.md 7.9 KB
- references/usage-examples.md 4.0 KB
- references/webhooks.md 6.6 KB
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.
- 9d ago First seen · 256 lines · 457 tokens per session scan A b699d8b3de5c
mercadopago is a skill published in the GitHub repository synerarg/claude-code-skills (3 stars, last pushed 2mo ago), with no licence file. It adds 457 tokens to every session and 3,116 once invoked, about $0.0023 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
afip-constancia
Fetch the official ARCA (ex-AFIP) Constancia de Inscripción for an Argentine CUIT from the PUBLIC web form (no Clave Fiscal, no login). Returns the parsed fiscal situation — régimen (monotributo + categoría / responsable inscripto / exento), domicilio fiscal, actividades CLAE, impuestos, fecha de inscripción — AND the…
mejorar-publicaciones-ml
Audita y mejora publicaciones de MercadoLibre usando el conector MCP de Algoritmo Digital (herramientas ml). Usar SIEMPRE que el usuario quiera mejorar, optimizar o auditar sus publicaciones, títulos, precios o conversión en MercadoLibre; cuando pregunte "por qué no vendo", "cómo subo las ventas", "revisá mi tienda"…
competencia-ml
Analiza la competencia en MercadoLibre con el conector MCP de Algoritmo Digital. Usar SIEMPRE que el usuario pregunte cómo está frente a la competencia, si está caro o barato, quién le baja los precios, quién gana el catálogo, qué está pasando en el mercado o quiera monitorear a otros vendedores — cualquier pregunta…
publicidad-ml
Analiza y optimiza la publicidad de MercadoLibre (Product Ads) y las promociones/campañas ofrecidas, usando el conector MCP de Algoritmo Digital. Usar SIEMPRE que el usuario pregunte por sus campañas, cuánto gasta en ads, si le conviene la pauta, el ACOS, si entrar al Hot Sale u otra promoción, qué publicaciones poner…
responder-preguntas-ml
Responde preguntas de compradores en MercadoLibre usando el conector MCP de Algoritmo Digital. Usar SIEMPRE que el usuario quiera ver o contestar preguntas pendientes, "ponerse al día con las preguntas", pida ayuda para redactar respuestas a compradores, o pregunte cuántas preguntas tiene sin responder — aunque no…
reporte-ventas-ml
Genera el reporte de ventas de MercadoLibre (día, semana o mes) con el conector MCP de Algoritmo Digital. Usar SIEMPRE que el usuario pregunte cómo viene el día, cómo van las ventas, cuánto facturó, cuánta plata le va a entrar, pida un resumen o reporte de la tienda, o quiera comparar períodos — cualquier pregunta…