Borrowing it
Nothing to install: this file belongs to eins78/meteoswiss-llm-tools. 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/eins78/meteoswiss-llm-tools/main/CLAUDE.mdgit clone --depth 1 https://github.com/eins78/meteoswiss-llm-toolsWrote 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/eins78/meteoswiss-llm-tools/claude-md)<a href="https://agentmods.dev/instructions/eins78/meteoswiss-llm-tools/claude-md"><img src="https://agentmods.dev/badge/instructions/eins78/meteoswiss-llm-tools/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/eins78/meteoswiss-llm-tools/claude-md"><img src="https://agentmods.dev/badge/instructions/eins78/meteoswiss-llm-tools/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 | $0.05910 | $0.05910 |
| Opus 5.5 | $0.02364 | $0.02364 |
| Sonnet 5.5 | $0.01182 | $0.01182 |
| Haiku 4.5 | $0.00591 | $0.00591 |
Grade A, and why
meteoswiss-llm-tools 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 today.
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 — 403 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. It contains key information and context needed to assist with development, debugging, and decision making.
How to Use This File
- Project Context: Brief overview of the project's purpose, architecture, and main components
- Design Decisions: Document major design or implementation decisions, along with their rationale and any trade-offs considered
- Open Tasks and Issues: List outstanding tasks, bugs, or technical debt
- References: Include links to relevant documentation, tickets, or external resources
- Update Regularly: Keep this file current whenever the project context changes or new decisions are made
Essential Commands
All commands run from packages/meteoswiss-mcp/ or via pnpm --filter meteoswiss-mcp from the root.
Development
- Run development server with hot reloading:
pnpm run dev - Start server:
pnpm run start - Test with MCP Inspector:
pnpm run dev:inspect - Type checking:
pnpm run lint(runs both TypeScript and ESLint checks) - Run tests:
pnpm test - Run integration tests:
pnpm test:integration - Format code:
pnpm run format
Build (when needed)
- Build project:
pnpm run build
Git Commands (Devcontainer)
When running in a devcontainer, use the following for git commits:
- Commit without GPG signing:
git commit --no-gpg-sign -m "commit message"
Architecture Overview
This is a monorepo (meteoswiss-llm-tools) for MeteoSwiss LLM tooling:
| Package | Description | Validation |
|---|---|---|
packages/meteoswiss-mcp/ |
MCP server (TypeScript) | pnpm --filter meteoswiss-mcp run ci |
packages/meteoswiss-skills/ |
Agent skill for direct OGD access | pnpm --filter meteoswiss-skills test |
packages/meteoswiss-docs-site/ |
Public docs site (Astro Starlight → GitHub Pages, https://code.178.is/meteoswiss-llm-tools/) | cd packages/meteoswiss-docs-site && pnpm install && pnpm run build |
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.
- today Changed · +4 lines · +213 tokens per session ae23b39129e6
- 19d ago Changed · +19 lines · +508 tokens per session e1d9eea62873
- 1mo ago Changed · +20 lines · +459 tokens per session 745ed913759f
- 2mo ago First seen · 360 lines · 4,730 tokens per session scan A 098cd1f10172
meteoswiss-llm-tools CLAUDE.md is an instructions file published in the GitHub repository eins78/meteoswiss-llm-tools (4 stars, last pushed today), licensed CC0-1.0. It adds 5,910 tokens to every session, about $0.0236 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 2026-08-31.
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).
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.
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.
vscode copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).
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.