Borrowing it
Nothing to install: this file belongs to SidneyBissoli/senado-br-mcp-cloudflare. 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/senado-br-mcp-cloudflare/master/CLAUDE.mdgit clone --depth 1 https://github.com/SidneyBissoli/senado-br-mcp-cloudflareWrote 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/senado-br-mcp-cloudflare/claude-md)<a href="https://agentmods.dev/instructions/sidneybissoli/senado-br-mcp-cloudflare/claude-md"><img src="https://agentmods.dev/badge/instructions/sidneybissoli/senado-br-mcp-cloudflare/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/senado-br-mcp-cloudflare/claude-md"><img src="https://agentmods.dev/badge/instructions/sidneybissoli/senado-br-mcp-cloudflare/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 | $0.04368 | $0.04368 |
| Opus 5 | $0.02184 | $0.02184 |
| Sonnet 5 | $0.00874 | $0.00874 |
| Haiku 4.5 | $0.00437 | $0.00437 |
Grade A, and why
senado-br-mcp-cloudflare 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 8d 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 — 97 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.
Project
MCP server for Brazilian Senate open data (Senado Federal Dados Abertos API + e-Cidadania portal), running on Cloudflare Workers with Streamable HTTP transport. Currently 69 tools across 21 group modules (67 senado_* tools plus search/fetch, the OpenAI Deep Research contract — the only names without the prefix), spanning the legislative API (legis.senado.leg.br/dadosabertos), the administrative API (adm.senado.gov.br/adm-dadosabertos — CEAPS, payroll, contracts; spec at /v3/api-docs there), e-Cidadania, and the institutional portal (www12.senado.leg.br/institucional/estrutura — organizational structure, crawled off-Worker into a bundled snapshot). Tool names, descriptions, and error messages are user-facing in Portuguese (pt-BR) — keep them that way. Besides tools, the server exposes the MCP prompts capability (4 pt-BR workflow templates in src/prompts.ts) and resources capability (5 static context docs/tables in src/resources.ts), both wired in src/server.ts via registerPrompts/registerResources. Keep their text builders exported for unit tests.
The upstream OpenAPI spec lives at https://legis.senado.leg.br/dadosabertos/v3/api-docs (save it to the gitignored .api-spec/ for analysis). 42 endpoints there are marked deprecated — mostly the /materia/* family. Do NOT add tools on deprecated endpoints; this repo already migrated off them (tools kept their names but call /processo and /votacao, bridging legacy IDs via the codigoMateria query param). Before writing a parser for a new endpoint, smoke-test the live response shape — wrapper names and casing (legacy PascalCase vs v3 camelCase) often differ from the spec.
Commands
npm run dev # wrangler dev — local server on port 8787
npm run typecheck # tsc --noEmit AND tsc -p scripts/tsconfig.json (two passes: src + ingest scripts)
npm test # vitest run (all tests)
npm run test:watch # vitest watch mode
npx vitest run tests/tools/votacoes.test.ts # single test file
npm run build # tsc -p tsconfig.build.json — compiles the npm/stdio package (dist/)
npm run smoke:openai-app # scripts/smoke-openai-app.mjs — exercises the ChatGPT-App MCP surface
npm run deploy # wrangler deploy
npm version patch # bump release — lifecycle hook (scripts/sync-version.mjs) mirrors package.json into server.json + src/version.ts
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.
- 8d ago Changed · +12 lines · +218 tokens per session d2d8cae3d7aa
- 12d ago First seen · 85 lines · 4,150 tokens per session scan A 06201fc60d81
senado-br-mcp-cloudflare CLAUDE.md is an instructions file published in the GitHub repository SidneyBissoli/senado-br-mcp-cloudflare (5 stars, last pushed today), licensed MIT. It adds 4,368 tokens to every session, about $0.0218 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
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).