rubo-mcp: Instructions file for Claude Code

CLAUDE.md

rubo-mcp CLAUDE.md is an instructions file for Claude Code from Ankur-stockheads/rubo-mcp. It costs 6,435 tokens per session, scanned A, original, MIT.

A project-instruction document for building an MCP server that checks whether a tenant can use a break clause in a UK commercial lease. MCP is a standard way for AI agents to call specialized tools.

In plain words
What is it for?
Use it as guidance when developing the UK break-clause analyzer, including its tools, technology choices, evaluation harness, and evidence-based behavior.
Why use it?
It sets technical and reliability requirements for extracting lease clauses, checking conditions, and grounding every answer in the source text. If the evidence is missing, the intended result is uncertainty rather than a guess.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: reads .claude/ paths; positional $N argument; mentions Codex.

This is Ankur-stockheads/rubo-mcp's own configuration. It tells Claude Code how to work on rubo-mcp 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 rubo-mcp configures →

Reuse

Borrowing it

Nothing to install: this file belongs to Ankur-stockheads/rubo-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.

Copy the file
curl -O https://raw.githubusercontent.com/Ankur-stockheads/rubo-mcp/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/Ankur-stockheads/rubo-mcp

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 rubo-mcp CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/ankur-stockheads/rubo-mcp/claude-md/github.svg)](https://agentmods.dev/instructions/ankur-stockheads/rubo-mcp/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/ankur-stockheads/rubo-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/ankur-stockheads/rubo-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.

agentmods 80×15 button for rubo-mcp CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/ankur-stockheads/rubo-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/ankur-stockheads/rubo-mcp/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 6,435 This file is loaded in full into every session.
When invoked 6,435 The same file — it is already loaded in full.
Security scan A 0 findings. 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 $0.06435 $0.06435
Opus 5 $0.03217 $0.03217
Sonnet 5 $0.01287 $0.01287
Haiku 4.5 $0.00643 $0.00643

Measured 10d ago against content hash 24753e3f2b7b, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

rubo-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 10d 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.

CLAUDE.md · 250 lines

How it starts

The opening of the file, as written. The whole thing — 250 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Project

UK Break Clause Analyzer (MCP)

A public, rigorously-evaluated MCP server that assesses whether a UK commercial-lease tenant break clause can actually be exercised — and proves it isn't hallucinating. It exposes single-purpose tools (extract the clause, check conditions, find citations, assess validity) that an orchestrating Claude composes, and ships a self-evaluating harness that publishes its own measured hallucination rate. Built as a credibility artifact for an Anthropic Applied AI / Forward Deployed Engineer application — the eval suite and reliability engineering are the headline, not the parsing.

Core Value: Every asserted condition is grounded to a verbatim source span or returns NOT_FOUND — never invented — and the server proves with a published hallucination rate that it would rather say "ambiguous — human verify" than guess.

Constraints

  • Tech stack: Python 3.12, managed with uv — modern, reproducible toolchain.
  • Tech stack: FastMCP latest stable 3.x; confirm exact versions against gofastmcp.com and github.com/modelcontextprotocol/python-sdk before coding; pin the official mcp SDK below v2 if used — avoid version drift and hallucinated APIs.
  • Tooling: pytest for the eval harness; MCP Inspector for manual testing.
  • Packaging: PyPI-ready with a [project.scripts] console entry; installable via uvx/pip, not published in v1.
  • Data: synthetic / public data only; never real client leases — confidentiality and reproducibility.
  • Self-containment: generate all scaffolding, parsing, config, and logic from scratch; no external repos cloned, read, or imported; nothing proprietary present anywhere — enforced via gates.
  • Scope: break clauses only; reject any expansion to other provisions.
  • Legal: decision-support, not legal advice; disclaimer required in the README and in tool output.
  • Reproducibility: the eval runs in under 2 minutes and is replayable in CI without an API key (recorded cassettes).
  • Engine: deterministic code for date math, checklist, and grounding; the LLM is used only for extraction and reasoning; explicit grounding for every citation.

Read the full file on GitHub · 250 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. 10d ago First seen · 250 lines · 6,435 tokens per session scan A 24753e3f2b7b

Subscribe to this mod's changes

rubo-mcp CLAUDE.md is an instructions file published in the GitHub repository Ankur-stockheads/rubo-mcp (0 stars, last pushed 2mo ago), licensed MIT. It adds 6,435 tokens to every session, about $0.0322 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.

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

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

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