Borrowing it
Nothing to install: this file belongs to LittleAndi/smhi-mcp-server. 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/LittleAndi/smhi-mcp-server/main/CLAUDE.mdgit clone --depth 1 https://github.com/LittleAndi/smhi-mcp-serverWrote 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/littleandi/smhi-mcp-server/claude-md)<a href="https://agentmods.dev/instructions/littleandi/smhi-mcp-server/claude-md"><img src="https://agentmods.dev/badge/instructions/littleandi/smhi-mcp-server/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/littleandi/smhi-mcp-server/claude-md"><img src="https://agentmods.dev/badge/instructions/littleandi/smhi-mcp-server/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 | $0.01656 | $0.01656 |
| Opus 5 | $0.00828 | $0.00828 |
| Sonnet 5 | $0.00331 | $0.00331 |
| Haiku 4.5 | $0.00166 | $0.00166 |
Grade B, and why
smhi-mcp-server CLAUDE.md scanned grade B 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 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.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
This machine also has a Codex config (`~/.codex/config.toml`) and a Gemini CLI config (`~/.gemini/`, `GEMINI.md`) at the user level. If you want to bring over MCP servers, slash commands, or instructions from those into How it starts
The opening of the file, as written. The whole thing — 65 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 (Model Context Protocol) server exposing SMHI (Swedish Meteorological and Hydrological Institute) weather data as tools, built against SMHI's current snow1g point-forecast API. SMHI retired the older pmp3g API on 2026-03-31; this is a fresh implementation, not a migration.
Commands
npm install
npm run typecheck # tsc --noEmit
npm test # vitest run (all tests, single run)
npm run test:watch # vitest (watch mode)
npm run test:coverage # vitest run --coverage
npm run build # tsc -> dist/
npm start # node dist/index.js
Run a single test file: npx vitest run src/__tests__/tools.test.ts
Run tests matching a name: npx vitest run -t "getFireRisk"
CI (.github/workflows/ci.yml) runs on Node 20.x/22.x/24.x: npm ci, npm run typecheck, npm test, npm run build. Match this locally before pushing.
Architecture
Request flow: src/index.ts (MCP server, stdio transport) → tool module in src/tools/*.ts (zod schema + handler) → src/smhi-client.ts (fetches SMHI APIs, shapes raw responses) → lookup tables (weather-symbols.ts, fire-risk-classes.ts) for human-readable descriptions.
Adding a new tool touches four places:
src/smhi-client.ts— fetch function against the relevant SMHI API/category, plus a converter from the raw SMHI shape to a processed type.src/types.ts— raw API response types and processed output types for the new data.src/tools/<name>.ts— zod input schema (z.objectwith.describe()on each field) + async handler calling the client function. Exports the schema, the handler, and the inferred input type.src/tools/index.ts— re-export the new schema/handler/type.src/index.ts— callserver.registerTool(name, { description, inputSchema, annotations: { title, ...READONLY_ANNOTATIONS } }, handler), passing the zod schema straight through asinputSchema(it doubles as the wire-format JSON Schema, generated automatically) and wrapping the handler inwithErrorHandlingunless it needs a non-JSON content block (seeget_radar_image, which returns animageblock alongsidetextand so wires its own try/catch).
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 First seen · 65 lines · 1,656 tokens per session scan B ea816886594c
smhi-mcp-server CLAUDE.md is an instructions file published in the GitHub repository LittleAndi/smhi-mcp-server (0 stars, last pushed 1mo ago), licensed MIT. It adds 1,656 tokens to every session, about $0.0083 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
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.
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.
deepseek-harness AGENTS.md
AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.