jupyter-rmcp: Instructions file for Claude Code

CLAUDE.md

jupyter-rmcp CLAUDE.md is an instructions file for Claude Code from tmlksu/jupyter-rmcp. It costs 1,526 tokens per session, scanned A, original, MIT.

A contributor guide for working on jupyter-rmcp, a project that connects assistants to Jupyter notebooks. Jupyter is a tool for running code in notebook files, and the guide explains how to orient yourself and protect key design decisions.

In plain words
What is it for?
It is for safely modifying the repository, checking its current state, reviewing recorded architecture decisions, and preserving its fixed tool interface.
Why use it?
It helps contributors understand the project before changing it and avoid breaking its security and notebook-storage rules.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: mentions CLAUDE.md.

This is tmlksu/jupyter-rmcp's own configuration. It tells Claude Code how to work on jupyter-rmcp itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything jupyter-rmcp configures →

Reuse

Borrowing it

Nothing to install: this file belongs to tmlksu/jupyter-rmcp. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/tmlksu/jupyter-rmcp/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/tmlksu/jupyter-rmcp

Made for: Claude Code.

Wrote 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.

agentmods badge for jupyter-rmcp CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/tmlksu/jupyter-rmcp/claude-md.svg)](https://agentmods.dev/instructions/tmlksu/jupyter-rmcp/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/tmlksu/jupyter-rmcp/claude-md"><img src="https://agentmods.dev/badge/instructions/tmlksu/jupyter-rmcp/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 1,526 This file is loaded in full into every session.
When invoked 1,526 The same file — it is already loaded in full.
Security scan A 1 finding. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.01526 $0.01526
Opus 5 $0.00763 $0.00763
Sonnet 5 $0.00305 $0.00305
Haiku 4.5 $0.00153 $0.00153

Measured 8d ago against content hash 1e6ff55ab3e1, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

jupyter-rmcp CLAUDE.md scanned grade A 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

docker compose ps && curl -s http://127.0.0.1:7130/health
CLAUDE.md · 115 lines

How it starts

The opening of the file, as written. The whole thing — 115 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md — working on jupyter-rmcp

Orientation for a Claude session (or any new contributor) touching this repo. Read README.md first for what the project is; this file is about how to change it safely.

Orient before touching anything

git log --oneline -8 && git status
docker compose ps && curl -s http://127.0.0.1:7130/health

Then skim docs/adr/ before revisiting anything that looks like a settled decision — most surprising choices here have a recorded reason.

Invariants (do not break without a new ADR)

  • Jupyter is never the exposed surface. It has no host port beyond a loopback JupyterLab; the MCP server is the only thing meant to go anywhere, and only behind auth. Raw Jupyter is arbitrary code execution with a token.
  • Notebooks live on the server hosting this stack, always. Colab and any future remote backend are compute-only; write-back targets the local .ipynb. This is why colab-only mode disables local execution rather than the local backend — all notebook I/O goes through its Contents API (ADR 0005, 0014).
  • The MCP tool surface is frozen at exactly the set in tests/test_tool_surface.py and scripts/smoke_test.py. Adding or removing a tool means updating both in the same commit, deliberately. Deployment mode changes behavior, never the API.
  • Execution routing is explicit. An unknown kernel_id raises; it never falls back to the local backend. backends._resolve_backend is the single choke point — new execution paths go through it (ADR 0013).
  • The server always answers before the client gives up, and never kills work to do it. One foreground execution per kernel (state.run_single_flight); a second one is refused, not queued; past the soft deadline it detaches rather than blocking or interrupting. Any new code path that runs user code goes through that guard (ADR 0017, 0018).
  • Secrets never in git. .env, secrets/, data/, deploy.local/ are git-ignored. Check git diff --cached --name-only before every commit.
  • Nothing personal in the tracked tree. Hostnames, domains, emails, absolute paths and provider-specific policy identifiers belong in git-ignored files (.env, deploy.local/), never in code or docs. This repo is public.

Read the full file on GitHub · 115 lines

Changes

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.

  1. 8d ago First seen · 115 lines · 1,526 tokens per session scan A 1e6ff55ab3e1

Subscribe to this mod's changes

jupyter-rmcp CLAUDE.md is an instructions file published in the GitHub repository tmlksu/jupyter-rmcp (0 stars, last pushed 1mo ago), licensed MIT. It adds 1,526 tokens to every session, about $0.0076 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

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.

vercel/next.js · 7,296 tokens

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.

openai/codex · 5,153 tokens

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).

microsoft/vscode · 6,785 tokens

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).

microsoft/vscode · 5,001 tokens

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.

langchain-ai/langchain · 4,469 tokens

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.

github/spec-kit · 7,104 tokens