Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add instructions/markusl/statfin-mcp/claude-mdgit clone --depth 1 https://github.com/markusl/statfin-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/markusl/statfin-mcp/claude-md)<a href="https://agentmods.dev/instructions/markusl/statfin-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/markusl/statfin-mcp/claude-md.svg" alt="Measured on agentmods" 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 | $0.00802 | $0.00802 |
| Opus 5 | $0.00401 | $0.00401 |
| Sonnet 5 | $0.00160 | $0.00160 |
| Haiku 4.5 | $0.00080 | $0.00080 |
Grade A, and why
statfin-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 — 78 lines — stays where its author put it; the contents beside it link to each section on GitHub.
StatFin MCP Server
MCP server for Statistics Finland's StatFin database. See README.md for project overview and ARCHITECTURE.md for technical details.
Quick Reference
Development Commands
npm install # Install dependencies
npm run dev # Development (stdio, watch mode)
npm run build # Build TypeScript
npm run typecheck # Type checking
npm run test:run # Run unit tests
npm run test:coverage # Run tests with coverage
npm start # Production (HTTP transport)
Project Structure
src/
├── server.ts # MCP server (stdio + HTTP transports)
├── config.ts # Environment configuration
├── tools/ # 7 MCP tools (search, list, query, etc.)
├── services/ # PxWeb client, cache, rate limiter
├── types/ # TypeScript definitions
└── utils/ # Logger, HTTP helpers
tests/
├── unit/ # Unit tests (vitest)
├── integration/ # Real API tests
└── fixtures/ # API response fixtures
MCP Tools
search_statistics- Full-text search (primary discovery)list_subject_areas- Browse 149 topic areaslist_tables- Tables in a subject areaget_table_metadata- Table structure/variablesget_variable_values- Variable codes (regions, years)query_table- Execute data queriesget_api_status- Health and rate limits
Key Patterns
Rate Limiting: Token bucket, 8 req/min per instance (3 instances = 24 req/min, under 30 limit)
Caching: Timestamp-validated. Query results cached until table's updated timestamp changes.
Query Selection (variable codes are table-specific and version-stamped — always fetch them via get_table_metadata; the codes below are from table 11re.px):
{ variable: "alue_23_20260101", filter: "item", values: ["KU091"] } // Specific values
{ variable: "timeperiod_y", filter: "top", top: 5 } // Latest N values
{ variable: "sukupuoli_9_20180101", filter: "all" } // All values (caution!)
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 First seen · 78 lines · 802 tokens per session scan A 2e9d81cb90e2
statfin-mcp CLAUDE.md is an instructions file published in the GitHub repository markusl/statfin-mcp (11 stars, last pushed 2mo ago), licensed MIT. It adds 802 tokens to every session, about $0.0040 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 2026-08-30.
Other instructions, from other repositories
OpenQuantum AGENTS.md
AGENTS.md instructions for xi-zhao/OpenQuantum, covering openquantum, 四个职责面, 扩展对象不可混用, 不变量 and 代码位置.
chemdraw-mcp CLAUDE.md
Instructions for jurimaxam-dotcom/chemdraw-mcp, covering chemdraw-mcp, build / run, auto-gate (the project's green/red), the five tool areas (where a new tool goes) and architecture.
cdc-health-mcp-server CLAUDE.md
Instructions for cyanheads/cdc-health-mcp-server, covering agent protocol, domain, api surface, socrata api endpoints and cdc wonder api.
OASiS copilot-instructions.md
Instructions for Hereon-InstituteMS/OASiS, covering oasis — project instructions, how to handle complex simulation tasks, developer mode: extending solvers, mandatory quality control and gate: no simulation without critic approval.
aurora-agent AGENTS.md
AGENTS.md instructions for AURORA-NEURO/aurora-agent, covering aurora agent, what we can never compromise on, 1. honest labelling is the product, 2. invariants belong in the type system, not in comments and 3. determinism, byte for byte.
hea-bench AGENTS.md
AGENTS.md instructions for dfieser/hea-bench, covering agents.md, what this is, install and import, the one mental model you need and descriptors (pure functions, exact units).