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/mercadopago/mercadopago-claude-marketplaceWrote 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/mercadopago/mercadopago-claude-marketplace/mp-commerce)<a href="https://agentmods.dev/commands/mercadopago/mercadopago-claude-marketplace/mp-commerce"><img src="https://agentmods.dev/badge/commands/mercadopago/mercadopago-claude-marketplace/mp-commerce/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/mercadopago/mercadopago-claude-marketplace/mp-commerce"><img src="https://agentmods.dev/badge/commands/mercadopago/mercadopago-claude-marketplace/mp-commerce.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 | $0.00014 | $0.00349 |
| Opus 5.5 | $0.00006 | $0.00140 |
| Sonnet 5 | $0.00003 | $0.00070 |
| Haiku 4.5 | $0.00001 | $0.00035 |
Grade A, and why
mp-commerce scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 5d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
/mp-commerce
Integrate a server-side Python commerce agent with Mercado Pago Checkout Pro
through mercadopago-commerce-agents-checkout==0.1.0.
Required flow
- Hand control to the
mp-commerce-checkoutskill, passing$ARGUMENTS. - Always start with its read-only discovery phase. Do not install dependencies or edit files during discovery.
- Present the discovered checkout entry point, cart mapping, authoritative catalog, durable attempt store, safe handoff boundary, dependency manager, target files, and verification plan.
- Ask for explicit confirmation before applying the displayed plan, including
when
$ARGUMENTScontainsapply. - During apply, pin
mercadopago-commerce-agents-checkout==0.1.0; never recreate its Orders API transport in the generated project. - Run local or mocked verification only. Do not authenticate, create an Order, or call Mercado Pago as a preflight.
For a non-Python project, do not generate a multilingual implementation. Give the official server-side Orders API fallback documented by the skill and stop.
If the developer separately asks for test users, webhooks, or an integration
review, suggest the corresponding capability from the mercadopago plugin.
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.
- 5d ago Changed · +8 lines · -6 tokens per session 94078fb695d7
- 9d ago First seen · 26 lines · 20 tokens per session scan A dcafd408967e
mp-commerce is a command published in the GitHub repository mercadopago/mercadopago-claude-marketplace (29 stars, last pushed 6d ago), licensed Apache-2.0. It adds 14 tokens to every session and 349 once invoked, about $0.0001 per session on Opus 5.5. 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 2026-09-19.
Other commands, from other repositories
pricing
Gera estrategia de pricing completa analisando 7 modelos de pricing, willingness-to-pay, estrutura de tiers, e plano de experimentacao. Baseado nos frameworks de Lenny Rachitsky e Phuryn.
billing
Add Stripe billing/payments to the Convex app via @convex-dev/stripe (checkout + webhook + gating).
add
Add a second payment provider alongside an existing integration, without touching the one already running.
signed-policy-agentic-commerce
Run an agentic commerce chain under a signed Work Mandate, trip the escalation gate on purpose, and replay the gates on the ledger.
legal-payment
Payment integration and subscription management.
k-trade
A command for looking up HS codes, customs duty rates, exchange rates, and clearance information through Korea Customs Service UNI-PASS.