rubberduck-mcp: Instructions file for Claude Code

CLAUDE.md

rubberduck-mcp CLAUDE.md is an instructions file for Claude Code from superiorsd10/rubberduck-mcp. It costs 2,278 tokens per session, scanned A, original, MIT.

Project instructions for Rubberduck MCP, a server that gives a coding agent tools for asking for clarification and sharing progress. It also documents how to build, test, run, and publish the TypeScript project.

In plain words
What is it for?
Building and running Rubberduck MCP, developing it with TypeScript, testing it, publishing it, and using its clarification or progress tools.
Why use it?
It gives the agent and developers a shared way to handle unclear requirements and use the repository's documented commands.

Instructions file for Claude Code

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

This is superiorsd10/rubberduck-mcp's own configuration. It tells Claude Code how to work on rubberduck-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 rubberduck-mcp configures →

Reuse

Borrowing it

Nothing to install: this file belongs to superiorsd10/rubberduck-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/superiorsd10/rubberduck-mcp/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/superiorsd10/rubberduck-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 rubberduck-mcp CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/superiorsd10/rubberduck-mcp/claude-md/github.svg)](https://agentmods.dev/instructions/superiorsd10/rubberduck-mcp/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/superiorsd10/rubberduck-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/superiorsd10/rubberduck-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 rubberduck-mcp CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/superiorsd10/rubberduck-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/superiorsd10/rubberduck-mcp/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 2,278 This file is loaded in full into every session.
When invoked 2,278 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 $0.02278 $0.02278
Opus 5 $0.01139 $0.01139
Sonnet 5 $0.00456 $0.00456
Haiku 4.5 $0.00228 $0.00228

Measured 11d ago against content hash 0bbcb6bc62f5, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

rubberduck-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.

CLAUDE.md · 253 lines

How it starts

The opening of the file, as written. The whole thing — 253 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.

You have access to two Rubberduck MCP tools: clarify() and yap().

Use clarify() when you're confused, need human input for ambiguous requirements, or aren't 100% confident about changes you're making - it will pause your work until you get a response.

Use yap() to share your thoughts, emotions, feelings, progress updates, and insights while working for an engaging experience with the human - it's non-blocking and keeps humans informed of your thinking process.

Use both tools proactively for better collaboration.

Development Commands

# Build TypeScript to JavaScript
npm run build

# Development mode with tsx
npm run dev

# Start built MCP server 
npm start

# Clean build artifacts
npm run clean

# Prepare for distribution (runs build)
npm run prepare

# Prepare for npm publishing (clean + build)
npm run prepublishOnly

# Start CLI interface for human interaction (requires MCP server running in MCP compatible IDE)
npx rubberduck-mcp cli
# OR: ./bin/rubberduck cli (local dev)

Architecture Overview

This is an MCP (Model Context Protocol) tool that enables bidirectional communication between LLMs and humans through two main tools: clarification and yapping. The system has been refactored from file-based IPC to a TCP-based message broker architecture for better performance and multi-client support.

Core Architecture Components

TCP Message Broker System:

  1. Message Broker (src/broker/message-broker.ts): Central TCP server on port 8765 that routes messages between MCP servers and CLIs
  2. Broker Manager (src/broker/broker-manager.ts): Handles automatic broker lifecycle - detects existing brokers and starts new ones when needed
  3. Broker Client (src/broker/broker-client.ts): TCP client that connects MCP servers and CLIs to the central broker
  4. Message Router (src/broker/message-router.ts): Implements clarification queuing and yap message ordering logic

Read the full file on GitHub · 253 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. 11d ago First seen · 253 lines · 2,278 tokens per session scan A 0bbcb6bc62f5

Subscribe to this mod's changes

rubberduck-mcp CLAUDE.md is an instructions file published in the GitHub repository superiorsd10/rubberduck-mcp (3 stars, last pushed 1y ago), licensed MIT. It adds 2,278 tokens to every session, about $0.0114 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

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

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