arquivo-pt-mcp: Instructions file for Claude Code

CLAUDE.md

arquivo-pt-mcp CLAUDE.md is an instructions file for Claude Code from thaenor/arquivo-pt-mcp. It costs 1,515 tokens per session, scanned A, original, MIT.

A set of instructions for building and working on an MCP server for Arquivo.pt, Portugal’s web archive. The server can search archived pages and images, list saved versions, retrieve snapshots, extract text, and take screenshots.

In plain words
What is it for?
Developing, testing, formatting, and checking the Arquivo.pt MCP server, including its six archive-search tools.
Why use it?
It gives an agent the project’s workflow, commands, architecture, and rules for running code inside a development container. This helps avoid running project commands or installing dependencies in the wrong environment.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: mentions CLAUDE.md.

This is thaenor/arquivo-pt-mcp's own configuration. It tells Claude Code how to work on arquivo-pt-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 arquivo-pt-mcp configures →

Reuse

Borrowing it

Nothing to install: this file belongs to thaenor/arquivo-pt-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/thaenor/arquivo-pt-mcp/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/thaenor/arquivo-pt-mcp

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.

agentmods badge for arquivo-pt-mcp CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/thaenor/arquivo-pt-mcp/claude-md/github.svg)](https://agentmods.dev/instructions/thaenor/arquivo-pt-mcp/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/thaenor/arquivo-pt-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/thaenor/arquivo-pt-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.

agentmods 80×15 button for arquivo-pt-mcp CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/thaenor/arquivo-pt-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/thaenor/arquivo-pt-mcp/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 1,515 This file is loaded in full into every session.
When invoked 1,515 The same file — it is already loaded in full.
Security scan A 1 finding. 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 $0.01515 $0.01515
Opus 5 $0.00758 $0.00758
Sonnet 5 $0.00303 $0.00303
Haiku 4.5 $0.00152 $0.00152

Measured 11d ago against content hash 00c14a2ec738, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

arquivo-pt-mcp CLAUDE.md scanned grade A with 1 finding 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 11d 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

- related curl commands to troubleshoot issues with git or huggingFace
CLAUDE.md · 91 lines

How it starts

The opening of the file, as written. The whole thing — 91 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

MCP server for Arquivo.pt, the Portuguese Web Archive. Exposes 6 tools: search, image_search, list_versions, get_snapshot, extract_text, get_screenshot.

Workflow

This Claude session is expected to run inside the project's DevContainer.

container: id: 5f6c44112660 name: pensive_moser image: mcr.microsoft.com/devcontainers/python:3.12

What do run inside the Docker Container:

  • Python commands
  • tests
  • anything tightly couple with the code

What to run on bare metal (Macbook)

  • git and gh (already authenticated)
  • hf (hugging face) (already authenticated)
  • related curl commands to troubleshoot issues with git or huggingFace

When in doubt, pause the process and confirm with the user. Never install any dependencies on the bare metal machine.

Commands

  • Install dev deps: uv sync --extra dev (or pip install -e ".[dev]")
  • Lint / format: ruff check src tests · ruff format src tests
  • Tests: pytest -q · single file: pytest tests/test_search.py -q · single test: pytest tests/test_search.py::test_search_basic -q
  • Coverage: pytest --cov=arquivo_pt_mcp
  • Integration (live API, opt-in): RUN_INTEGRATION=1 pytest -m integration -v
  • Run server (stdio): uv run arquivo-pt-mcp
  • Run server (HTTP): arquivo-pt-mcp --transport http --host 127.0.0.1 --port 8000
  • Build wheel: python -m build

pytest.ini_options sets asyncio_mode = "auto" — async tests don't need @pytest.mark.asyncio. The integration marker is registered; tests without RUN_INTEGRATION=1 skip via tests/integration_fixtures.py.

Architecture

Single-module core, thin wrappers

src/arquivo_pt_mcp/__init__.py is the whole server: tool implementations, MCP wiring (@server.list_tools, @server.call_tool), HTTP helpers, and the main() entry point all live there. The other source files are deliberately thin:

  • server.py — re-exports main for python -m arquivo_pt_mcp.server-style use. Don't add logic here.
  • cli.py — argparse + env-var fallbacks for transport/host/port/security flags. Pure parsing; no I/O.
  • http_app.py — Starlette ASGI factory used only when --transport http. Lazy-imported from __init__._async_main_http to avoid pulling Starlette/uvicorn into stdio runs.
  • models.py — Pydantic *Params models. Validation runs in call_tool before dispatch via the PARAM_MODELS map; tool handlers themselves accept loose kwargs.

Read the full file on GitHub · 91 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. 11d ago First seen · 91 lines · 1,515 tokens per session scan A 00c14a2ec738

Subscribe to this mod's changes

arquivo-pt-mcp CLAUDE.md is an instructions file published in the GitHub repository thaenor/arquivo-pt-mcp (0 stars, last pushed 3mo ago), licensed MIT. It adds 1,515 tokens to every session, about $0.0076 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other instructions, from other repositories

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.

vercel/next.js · 7,296 tokens

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.

openai/codex · 5,153 tokens

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).

microsoft/vscode · 6,785 tokens

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.

github/spec-kit · 7,126 tokens

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.

langchain-ai/langchain · 4,469 tokens

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).

microsoft/vscode · 5,001 tokens