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.
curl -O https://raw.githubusercontent.com/mercadopago/mercadopago-claude-marketplace/main/CLAUDE.mdgit 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/instructions/mercadopago/mercadopago-claude-marketplace/claude-md)<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.
<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>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 | $0.01125 | $0.01125 |
| Opus 5 | $0.00562 | $0.00562 |
| Sonnet 5 | $0.00225 | $0.00225 |
| Haiku 4.5 | $0.00112 | $0.00112 |
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 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 — 113 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, andmp-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.jsoninto the developer's project. Claude Code registers the MCP server from the enabled plugin.
File contracts
- Agent frontmatter requires
tools,model,tags,category, andversion. - Skill frontmatter uses
metadata. Never add top-leveltoolsormodelto a skill. - Command frontmatter uses
allowed-tools, nottools. - 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.txtat 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_documentationonly for a gap in the first two sources, and always for products explicitly marked MCP-required, such as SmartApps.
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 · 113 lines · 1,125 tokens per session scan A a736a28dfe1d
mercadopago-claude-marketplace CLAUDE.md is an instructions file published in the GitHub repository mercadopago/mercadopago-claude-marketplace (26 stars, last pushed 8d ago), licensed Apache-2.0. It adds 1,125 tokens to every session, about $0.0056 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 2026-08-30.
Other instructions, from other repositories
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).