blueprint-mcp: Instructions file for Claude Code

CLAUDE.md

blueprint-mcp CLAUDE.md is an instructions file for Claude Code from railsblueprint/blueprint-mcp. It costs 3,161 tokens per session, scanned A, original, Apache-2.0.

Project instructions for an AI coding agent working on Blueprint MCP for Chrome, a server and browser extensions that let AI applications control a user's existing browser session.

In plain words
What is it for?
Use them when developing or running the MCP server, working on Chrome, Firefox, or Opera extensions, or handling project issues with the beads tracker.
Why use it?
They give the agent the project's structure, commands, development rules, and debugging guidance so it can work consistently in the repository.

Instructions file for Claude Code

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

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

Needs its repository: it reads a path above its own folder, which exists only inside the repository. The line is node cli.js --debug --log-file ../logs/custom.log --port 5556.

Reuse

Borrowing it

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

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

Your own site · 80×15
<a href="https://agentmods.dev/instructions/railsblueprint/blueprint-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/railsblueprint/blueprint-mcp/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 3,161 This file is loaded in full into every session.
When invoked 3,161 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 $0.03161 $0.03161
Opus 5 $0.01580 $0.01580
Sonnet 5 $0.00632 $0.00632
Haiku 4.5 $0.00316 $0.00316

Measured 10d ago against content hash 9029c4280645, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

blueprint-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 · 371 lines

How it starts

The opening of the file, as written. The whole thing — 371 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

Note: This project uses bd (beads) for issue tracking. Use bd commands instead of markdown TODOs. See AGENTS.md for workflow details.

This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.

Project Overview

Blueprint MCP for Chrome is an MCP (Model Context Protocol) server + browser extensions that allow AI applications to automate the user's existing browser session. Unlike typical browser automation tools, this project uses the user's real browser profile to maintain logged-in sessions and avoid bot detection.

Current Version: 1.5.5 Total Features: 200+ Total Commits: 599+

Supported Browsers:

  • ✅ Chrome - TypeScript extension (4,000 lines + build step)
  • ✅ Firefox - Vanilla JS extension (2,000 lines, no build)
  • ✅ Opera - Uses Chrome source code (Chromium-based)
  • 🚧 Safari - Planned (will share vanilla JS code with Chrome rewrite)

Key Features:

  • Fast local automation without network latency
  • Private - browser activity stays on device (Free tier)
  • Cloud relay with OAuth2 (PRO tier)
  • Uses existing browser profile and logged-in sessions
  • Stealth mode - uses real browser fingerprint to avoid bot detection
  • Tech stack detection - Auto-detects 40+ frameworks/libraries
  • Auto-reconnection - Survives browser/extension reloads

Credits: Originally inspired by Microsoft's Playwright MCP, but completely rewritten for Chrome extension-based automation

Development Commands

Server Development

cd server

# Run MCP server in debug mode
node cli.js --debug

# Run with custom log file and port
node cli.js --debug --log-file ../logs/custom.log --port 5556

# Test the server
npm test

# Version bump and release (from root)
cd ..
./release.sh

Chrome Extension Development (TypeScript + Vite)

cd extensions/chrome

# Install dependencies
npm install

# Build extension
npm run build

# Watch mode for development
npm run dev

# Load unpacked extension from extensions/chrome/dist/

Read the full file on GitHub · 371 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 · 371 lines · 3,161 tokens per session scan A 9029c4280645

Subscribe to this mod's changes

blueprint-mcp CLAUDE.md is an instructions file published in the GitHub repository railsblueprint/blueprint-mcp (99 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 3,161 tokens to every session, about $0.0158 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 2026-08-30.

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

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.

deepseek-ai/deepseek-harness · 3,735 tokens