Borrowing it
Nothing to install: this file belongs to SidneyBissoli/bcb-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.
curl -O https://raw.githubusercontent.com/SidneyBissoli/bcb-br-mcp/main/CLAUDE.mdgit clone --depth 1 https://github.com/SidneyBissoli/bcb-br-mcpWrote 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/sidneybissoli/bcb-br-mcp/claude-md)<a href="https://agentmods.dev/instructions/sidneybissoli/bcb-br-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/sidneybissoli/bcb-br-mcp/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/sidneybissoli/bcb-br-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/sidneybissoli/bcb-br-mcp/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 | $0.07286 | $0.07286 |
| Opus 5 | $0.03643 | $0.03643 |
| Sonnet 5 | $0.01457 | $0.01457 |
| Haiku 4.5 | $0.00729 | $0.00729 |
Grade A, and why
bcb-br-mcp 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 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.
How it starts
The opening of the file, as written. The whole thing — 381 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
What this is
An MCP server, published to npm as bcb-br-mcp, exposing three public APIs of
the Brazilian Central Bank as 17 tools over STDIO and Streamable HTTP: the SGS
time series (Selic, IPCA, FX, GDP and 135 verified indicators), the Focus
market-expectations survey (Olinda OData) and PTAX exchange rates. Pure
TypeScript, ESM, four runtime dependencies: @modelcontextprotocol/server (MCP SDK
v2), @sbissoli/mcp-stats (motor de estatística do portfólio),
@sbissoli/mcp-search (contrato Deep Research: search/fetch, desde a 1.11.0)
e @sbissoli/mcp-provenance (contrato de proveniência). Este último traz zod de
volta, como dependência transitiva — custo aceito de propósito no D4: a regra
do portfólio é não reimplementar componente da Fase 0 localmente, e uma
proveniência local faria o campo motor do bloco derivacao mentir, que é o
mesmo argumento que decidiu a correlação na sessão 06. O zod é interno; a
superfície publicada continua sendo JSON Schema escrito à mão. No database;
the only state is module-level — the curated series catalog and the 24-hour cache
of the Open Data Portal index (metadata only).
Two consumer channels, both in production and both protected:
- npm (
bcb-br-mcp, ~500 downloads/month, 1.36k uses on Smithery) — stdio. - Hosted —
https://bcb.sidneybissoli.com/mcp(custom domain) and the historicalhttps://bcb.sidneybissoli.workers.dev.
Commands
npm run build # limpa dist/ e compila com tsconfig.build.json (sem testes nem evals)
npm start # node dist/index.js (servidor MCP em stdio)
npm test # vitest run
npm run typecheck # tsc --noEmit (inclui os testes — o build os exclui)
npm run smoke # smoke contra o worker hospedado
node scripts/smoke-mcp.mjs --stdio # o mesmo smoke sobre dist/index.js local
node scripts/dump-surface.mjs --stdio # dump normalizado da superfície (ver baselines/)
npx tsx src/evals/run.ts # eval de seleção com MODELO REAL — CUSTA DINHEIRO
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 · +5 lines · +327 tokens per session 25e00eb04d2a
- 9d ago First seen · 376 lines · 6,959 tokens per session scan A 130431912442
bcb-br-mcp CLAUDE.md is an instructions file published in the GitHub repository SidneyBissoli/bcb-br-mcp (7 stars, last pushed yesterday), licensed MIT. It adds 7,286 tokens to every session, about $0.0364 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 instructions, from other repositories
vibetags com-example-config-AsyncTestConfig.instructions.md
Instructions for PIsberg/vibetags, covering copilot instructions for asynctestconfig and immutable type.
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).
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).
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.