Borrowing it
Nothing to install: this file belongs to bjornwalther/statsbudget-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/bjornwalther/statsbudget-mcp/main/CLAUDE.mdgit clone --depth 1 https://github.com/bjornwalther/statsbudget-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/bjornwalther/statsbudget-mcp/claude-md)<a href="https://agentmods.dev/instructions/bjornwalther/statsbudget-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/bjornwalther/statsbudget-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/bjornwalther/statsbudget-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/bjornwalther/statsbudget-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 | $0.01225 | $0.01225 |
| Opus 5.5 | $0.00490 | $0.00490 |
| Sonnet 5 | $0.00245 | $0.00245 |
| Haiku 4.5 | $0.00122 | $0.00122 |
Grade A, and why
statsbudget-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 10d 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 — 60 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 (Model Context Protocol) server exposing Swedish national budget data (statsbudgeten) — expenditure outturn, tax revenue, and tax quota/Laffer analysis — as tools for Claude Desktop and other MCP clients. Built on FastMCP. Python 3.12+.
Commands
# Setup
python -m venv .venv && source .venv/bin/activate
pip install -e ".[dev]"
# Run the server
statsbudget-mcp # or: python -m statsbudget_mcp.server
# Tests (unit only — no network calls)
pytest tests/ -m "not integration"
# Single test
pytest tests/test_statskontoret.py::test_name -v
# All tests, including live SCB/Statskontoret API calls
pytest tests/
# Lint
ruff check src/ tests/
Tests marked @pytest.mark.integration (in test_scb_client.py, test_laffer.py) hit live external APIs — excluded by default via -m "not integration". asyncio_mode = "auto" is set in pyproject.toml, so async test functions don't need @pytest.mark.asyncio.
Architecture
Three independent data sources feed one FastMCP server (server.py), which holds module-level singleton clients (_scb, _sk, _cache) initialized in the lifespan context manager and accessed via _require_*() guards from each tool.
statskontoret.py—StatskontoretClientscrapes the Statskontoret open-data page for download links, classifies them (expenditure vs. income, ZIP vs. Excel), downloads ZIPs, and parses semicolon-delimited Swedish-locale CSVs (comma decimals) intoExpenditureRow/IncomeRowdataclasses. Column mapping is header-name-based (Swedish column names, e.g.Utgiftsområde,Utfall) with a fallback default, since Statskontoret's schema isn't guaranteed stable.scb_client.py—SCBClientqueries SCB's PxWeb v1 REST API (JSON POST) for tax revenue (SkatteIntakt) and tax quota (SkattekvotBNP) tables, with retry/backoff on transient errors (_RETRYABLE_EXCEPTIONS).laffer.py— builds tax-quota-vs-GDP timeseries fromSCBClientdata, annotated with a static list of Swedish tax reforms (TAX_REFORMS, 1971–2020). Explicitly descriptive, not a causal Laffer curve (see module docstring).cache.py—BudgetCacheis a schema-versioned SQLite cache (~/.statsbudget-cache/statsbudget.db). A cache is only considered "populated" when both expenditure and income tables have rows ANDsnapshot_completeis true — partial snapshots are never trusted.formatters.py— ASCII visualizations (bars, flow diagrams, decision chains, Laffer timeline) for terminal/text MCP clients.server.py— defines all MCP tools/resources and owns startup semantics (see below).
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.
- 10d ago First seen · 60 lines · 1,225 tokens per session scan A 1cf82b903714
statsbudget-mcp CLAUDE.md is an instructions file published in the GitHub repository bjornwalther/statsbudget-mcp (0 stars, last pushed 11d ago), licensed MIT. It adds 1,225 tokens to every session, about $0.0049 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 2026-09-15.
Other instructions, from other repositories
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).
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, repository design references, quickstart — add a new integration in 5 steps and integration architecture.
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 oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).
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.