opf-br-mcp: Skill for Claude Code

.agents/skills/consultar-opf-br/SKILL.md

consultar-opf-br is a skill for Claude Code, Codex from jrogeriosilva/opf-br-mcp. It costs 68 tokens per session (1,510 once invoked), scanned A, original, MIT.

A reference lookup service for implementing and testing Open Finance Brasil integrations. Open Finance Brasil is Brazil's regulated system for sharing financial data and services between participating institutions.

In plain words
What is it for?
Use it to find OpenAPI contracts, business rules, supported versions, filters, and workflow transitions for an integration.
Why use it?
It helps resolve uncertainty about API fields, request formats, allowed states, business rules, and error conditions using official sources instead of guesses.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: installed under .agents/ (shared by several agents).

This is jrogeriosilva/opf-br-mcp's own configuration. It tells Claude Code and Codex how to work on opf-br-mcp itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything opf-br-mcp configures →

Reuse

Borrowing it

Nothing to install: this file belongs to jrogeriosilva/opf-br-mcp. 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/jrogeriosilva/opf-br-mcp/main/.agents/skills/consultar-opf-br/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/jrogeriosilva/opf-br-mcp

Made for: Claude Code, Codex.

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.

agentmods badge for consultar-opf-br

README.md
[![agentmods](https://agentmods.dev/badge/skills/jrogeriosilva/opf-br-mcp/consultar-opf-br/github.svg)](https://agentmods.dev/skills/jrogeriosilva/opf-br-mcp/consultar-opf-br)
Your own site
<a href="https://agentmods.dev/skills/jrogeriosilva/opf-br-mcp/consultar-opf-br"><img src="https://agentmods.dev/badge/skills/jrogeriosilva/opf-br-mcp/consultar-opf-br/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.

agentmods 80×15 button for consultar-opf-br

Your own site · 80×15
<a href="https://agentmods.dev/skills/jrogeriosilva/opf-br-mcp/consultar-opf-br"><img src="https://agentmods.dev/badge/skills/jrogeriosilva/opf-br-mcp/consultar-opf-br.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 68 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,510 The whole file, excluding the scripts and references it only reads on demand.
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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00068 $0.01510
Opus 5.5 $0.00027 $0.00604
Sonnet 5.5 $0.00014 $0.00302
Haiku 4.5 $0.00007 $0.00151

Measured 1mo ago against content hash 6a2e2fb6b892, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

consultar-opf-br 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.

.agents/skills/consultar-opf-br/SKILL.md · 53 lines

How it starts

The opening of the file, as written. The whole thing — 53 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Consultar Open Finance Brasil

Use o MCP opf-br-mcp para reunir a evidência necessária à implementação, revisão ou consulta técnica, mesmo sem acesso a uma codebase. As ferramentas podem ter um prefixo definido pelo cliente; localize list_domains, search, get_item e refresh desse servidor. Se não estiverem disponíveis, informe a limitação; não simule resultados.

Escolher a fonte

  1. Identifique no pedido e, quando houver, no código a API, a versão, o papel da instituição e a dúvida concreta. Se uma dessas informações mudar a resposta e não puder ser determinada, explicite a hipótese ou peça esclarecimento antes de decidir o contrato.
  2. Chame list_domains quando o catálogo ainda não estiver no contexto. Escolha pelos descritivos e specVersion; não presuma que a maior versão cadastrada seja a mais recente publicada ou a usada pelo projeto.
  3. Reconstrua os filtros aceitos unindo filters do domínio a filterSets[filterSet], quando presentes. live: true identifica consulta remota sem cache.

Para contratos HTTP, payloads e schemas, consulte *-openapi. Para condições de uso, transições e fluxos, consulte o domínio *-business-rules pareado da mesma API e major. Use os descritivos do catálogo para localizar convenções compartilhadas, guias, PCM e requisitos não funcionais quando pertinentes. Não carregue todas as famílias preventivamente.

Recuperar o mínimo suficiente

  • Comece com search no domínio escolhido e limit: 5. Use um termo curto, path, nome de campo, estado ou código de erro. Nos domínios extraídos, query exige todos os termos nos campos indexados, por substring e sem distinguir acentos ou maiúsculas: uma pergunta longa ou um campo interno de detail pode não ser encontrado.
  • Use apenas filtros anunciados. Eles se combinam em AND; não combine filtros de tipos incompatíveis, como method de endpoint e schema de componente. Faça buscas separadas.
  • Leia matches, returned e os resumos. Se precisar continuar, some returned ao offset, mantendo a consulta; pare quando returned for zero ou atingir matches. Em live, esse total cobre os resultados obtidos da fonte, não necessariamente todos os existentes nela.
  • Use get_item para os itens que sustentam a decisão. Copie o id exato e mantenha o mesmo domínio. Em OpenAPI, leia detail e siga os ids de refs apenas onde forem necessários; mantenha um conjunto de ids já visitados para evitar ciclos. Não monte ids a partir de paths ou nomes de schemas.
  • Pare de recuperar quando tiver contrato, regra aplicável e referências suficientes para a alteração solicitada. Não percorra toda a spec nem todas as referências por padrão.

Read the full file on GitHub · 53 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.

  1. 1mo ago First seen · 53 lines · 68 tokens per session scan A 6a2e2fb6b892

Subscribe to this mod's changes

consultar-opf-br is a skill published in the GitHub repository jrogeriosilva/opf-br-mcp (0 stars, last pushed 20d ago), licensed MIT. It adds 68 tokens to every session and 1,510 once invoked, about $0.0003 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 2026-09-29.

Related

consultar-opf-br compared with skills from other repositories

consultar-opf-br next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
consultar-opf-brjrogeriosilva/opf-br-mcpSkill020d agoMITA68Claude Code, Codex
x402browser-use/browser-useSkill120kyesterdayMITA175Claude Code
tushareHKUDS/Vibe-TradingSkill38kyesterdayMITA79Claude Code, Codex
stripe-best-practicesstripe/aiSkill2.0kyesterdayMITA161Claude Code, Codex
wechatpay-payment-integrationwechatpay-apiv3/wechatpay-skillsSkill3725d agoMITA330Claude Code, Codex
hyperliquid-websocketgalleonlabs/hypergrok-trading-deskSkill3502d agoMITA89Claude Code
crypto-market-data-service-guidenirholas/three.wsSkill269yesterdayApache-2.0A56Claude Code, Codex