Borrowing it
Nothing to install: this file belongs to MauroDruwel/Smartschool-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/MauroDruwel/Smartschool-MCP/main/CLAUDE.mdgit clone --depth 1 https://github.com/MauroDruwel/Smartschool-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/maurodruwel/smartschool-mcp/claude-md)<a href="https://agentmods.dev/instructions/maurodruwel/smartschool-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/maurodruwel/smartschool-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/maurodruwel/smartschool-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/maurodruwel/smartschool-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 | $0.00851 | $0.00851 |
| Opus 5 | $0.00426 | $0.00426 |
| Sonnet 5 | $0.00170 | $0.00170 |
| Haiku 4.5 | $0.00085 | $0.00085 |
Grade A, and why
Smartschool-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 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.
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 — 71 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.
Commands
# Install all dependencies (including dev)
uv sync --extra dev
# Run all tests
uv run pytest
# Run a single test
uv run pytest tests/test_tools.py::test_get_courses_returns_list
# Lint
uv run ruff check .
# Format (check only)
uv run ruff format --check .
# Format (apply)
uv run ruff format .
# Type check
uv run mypy smartschool_mcp/
CI runs lint → typecheck → tests (Python 3.10–3.13) in that order. All three must pass before merging.
Architecture
The package is a single-file MCP server (smartschool_mcp/server.py) plus an entry-point module (smartschool_mcp/__main__.py).
Transport modes
__main__.py handles two transports selected via --transport (or MCP_TRANSPORT env var):
stdio(default) — used by Claude Desktop; callsmcp.run()directly.streamable-http— used by claude.ai remote integrations; builds a Starlette ASGI app viamcp.streamable_http_app(), wraps it inCORSMiddleware(required so claude.ai can readMcp-Session-Id), then optionally wraps that in_BearerAuthMiddleware(enabled by settingMCP_API_KEY). Served with uvicorn onMCP_HOST:MCP_PORT.
Tool registration
All MCP tools live in server.py and are registered with @mcp.tool() decorators on plain Python functions. FastMCP("Smartschool MCP") is the server instance (mcp). Adding a new tool means writing a new @mcp.tool() function — no registration table to update.
Session and credentials
_session() is an @lru_cache(maxsize=1) function that creates a Smartschool(EnvCredentials()) instance on first call. It is lazy on purpose — startup never touches the network, so missing credentials surface as tool-level errors rather than process crashes. In tests, conftest.py patches _session with an autouse fixture so no real credentials are needed.
smartschool library
The upstream library (github.com/svaningelgem/smartschool, pinned via uv.lock) exposes lazy-loaded objects. Accessing .details on a result, for example, triggers an HTTP request. Many attributes use getattr(..., default) defensively because the library's type stubs are incomplete. Every tool wraps its body in try/except Exception as e and returns {"error": f"...{e!s}"} (or a list variant) so failures surface as tool results rather than MCP errors.
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.
- 11d ago First seen · 71 lines · 851 tokens per session scan A e2b3f91d4997
Smartschool-MCP CLAUDE.md is an instructions file published in the GitHub repository MauroDruwel/Smartschool-MCP (4 stars, last pushed 4d ago), licensed MIT. It adds 851 tokens to every session, about $0.0043 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 2026-08-31.
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).
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.
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 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).