What is mercadopago-claude-marketplace CLAUDE.md?

A set of development instructions for building the public Mercado Pago plugin for Claude Code, an AI coding tool. It defines the plugin’s structure, file locations, and how it connects to external tools.

Use it when developing, reviewing, or validating the Mercado Pago Claude Code plugin, including its commands, skills, scaffolding, and tool connections.

It gives contributors shared rules for keeping the plugin’s paths, files, offline behavior, and authentication handling consistent. This reduces mistakes when changing or extending the plugin.

How mercadopago/mercadopago-claude-marketplace configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to mercadopago/mercadopago-claude-marketplace. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/mercadopago/mercadopago-claude-marketplace/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/mercadopago/mercadopago-claude-marketplace

Made for: Claude Code.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/mercadopago/mercadopago-claude-marketplace/claude-md/github.svg)](https://agentmods.dev/instructions/mercadopago/mercadopago-claude-marketplace/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/mercadopago/mercadopago-claude-marketplace/claude-md"><img src="https://agentmods.dev/badge/instructions/mercadopago/mercadopago-claude-marketplace/claude-md/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.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/mercadopago/mercadopago-claude-marketplace/claude-md"><img src="https://agentmods.dev/badge/instructions/mercadopago/mercadopago-claude-marketplace/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 1,166 This file is loaded in full into every session.

When invoked 1,166 The same file — it is already loaded in full.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

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	$0.01166	$0.01166
Opus 5.5	$0.00466	$0.00466
Sonnet 5.5	$0.00233	$0.00233
Haiku 4.5	$0.00117	$0.00117

Measured 1mo ago against content hash 12f9a217130d, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

mercadopago-claude-marketplace CLAUDE.md 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 1mo 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.

CLAUDE.md · 115 lines

How it starts

The opening of the file, as written. The whole thing — 115 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Claude Code Development Contract — Mercado Pago Plugin

This repository builds the public Mercado Pago marketplace plugin for Claude Code. Runtime instructions, paths, hooks, examples, and validation must target Claude Code and must be safe for developers outside Mercado Pago/Mercado Libre.

Current architecture (v4.3.2)

One thin router: plugins/mercadopago/agents/mp-integration-expert.md.
Four passive skills only: mp-integrate, mp-webhooks, mp-test-setup, and mp-review.
Commands are the user-facing entry points. Skills contain orchestration and approved scaffold contracts; they are not independent agents.
Static scaffolding, bundled references, test cards, and local security checks work without MCP authentication.
MCP OAuth is requested only immediately before a selected operation needs an authenticated MCP tool.

Claude plugin paths

Use ${CLAUDE_PLUGIN_ROOT} for files shipped with the active plugin version.
Use ${CLAUDE_PLUGIN_DATA} for persistent plugin-owned state.
Use ${CLAUDE_PROJECT_DIR} for the developer's application.
Never hardcode or scan ~/.claude/plugins/cache.
Never copy the plugin .mcp.json into the developer's project. Claude Code registers the MCP server from the enabled plugin.

File contracts

Agent frontmatter requires tools, model, tags, category, and version.
Skill frontmatter uses metadata. Never add top-level tools or model to a skill.
Command frontmatter uses allowed-tools, not tools.
Keep the router under 150 lines and the skill count at four unless the architecture is intentionally redesigned.

Sources and MCP boundary

Use this documentation order:

Fetch the official country-specific developers/llms.txt at most once per interaction when live product documentation is needed.
Read approved bundled references under skills/mp-integrate/references/ for stable, version-pinned facts and tested scaffold contracts.
Use MCP search_documentation only for a gap in the first two sources, and always for products explicitly marked MCP-required, such as SmartApps.

Read the full file on GitHub · 115 lines

Changes

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.

1mo ago Changed · +2 lines · +41 tokens per session 12f9a217130d
2mo ago First seen · 113 lines · 1,125 tokens per session scan A a736a28dfe1d

Subscribe to this mod's changes

mercadopago-claude-marketplace CLAUDE.md is an instructions file published in the GitHub repository mercadopago/mercadopago-claude-marketplace (32 stars, last pushed yesterday), licensed Apache-2.0. It adds 1,166 tokens to every session, about $0.0047 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 2026-08-30.

mercadopago-claude-marketplace CLAUDE.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
mercadopago-claude-marketplace CLAUDE.mdmercadopago/mercadopago-claude-marketplace	Instructions file	32	yesterday	Apache-2.0	A	1,166	Claude Code
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	yesterday	MIT	A	7,461	Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	yesterday	MIT	A	4,680	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	5,516	GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	3,093	GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness	Instructions file	274k	2d ago	MIT	A	4,313	Codex, OpenCode

mercadopago-claude-marketplace: Instructions file for Claude Code