What is mcp CLAUDE.md?

A checklist for converting HTML or design files into native Android code written in Kotlin, Android’s modern programming language. It covers layouts, standard controls, images, fonts, interactions, and style matching.

Use it to create Kotlin Android screens from HTML, convert images and fonts into Android resources, add control events, use RecyclerView for repeated items, and verify layout styles.

It helps keep the Android result close to the original design while using Android controls such as checkboxes, switches, buttons, and lists. It also requires checking that no original style properties were lost.

mcp CLAUDE.md — Instructions file by platformatic

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods

npx agentmods add instructions/platformatic/mcp/claude-md

Clone the repo

git clone --depth 1 https://github.com/platformatic/mcp

Per session 1,699 This file is loaded in full into every session.

When invoked 1,699 The same file — it is already loaded in full.

Security scan A 0 findings. Scan, not verified.

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.

Model	Per session	Once invoked
Fable 5	$0.01699	$0.01699
Opus 5	$0.00849	$0.00849
Sonnet 5	$0.00340	$0.00340
Haiku 4.5	$0.00170	$0.00170

Measured 2d ago against content hash 772ded1862c0, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

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 2d 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 · 167 lines

How it starts

The opening of the file, as written. The whole thing — 167 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.

Overview

This is a production-ready Fastify adapter for the Model Context Protocol (MCP). The project implements a Fastify plugin that enables MCP communication through the JSON-RPC 2.0 specification with full horizontal scaling capabilities. The codebase includes MCP protocol specifications in the spec/ directory that define the messaging format, lifecycle management, and various protocol features.

Key Features

Complete MCP Protocol Support: Implements the full Model Context Protocol specification
Server-Sent Events (SSE): Real-time streaming communication with session management
Horizontal Scaling: Redis-backed session management and message broadcasting
Session Persistence: Message history and reconnection support with Last-Event-ID
Dual Backend Support: Memory-based for development, Redis-based for production
Cross-Instance Broadcasting: Messages sent from any instance reach all connected clients
High Availability: Sessions survive server restarts with automatic cleanup

Development Commands

Build: npm run build - Compiles TypeScript to dist/ directory
Lint: npm run lint - Run ESLint with caching
Lint Fix: npm run lint:fix - Run ESLint with auto-fix
Type Check: npm run typecheck - Run TypeScript compiler without emitting files
Test Individual: node --experimental-strip-types --no-warnings --test test/filename.test.ts - Run a specific test file
Test: npm run test - Run Node.js test runner on test files, do not use npm run test -- individual.ts to run individual test file
CI: npm run ci - Full CI pipeline (build + lint + test)

Architecture

The main entry point is src/index.ts which exports a Fastify plugin built with fastify-plugin. The plugin structure follows Fastify's standard plugin pattern with proper TypeScript types and supports both memory and Redis backends for horizontal scaling.

Read the full file on GitHub · 167 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.

2d ago First seen · 167 lines · 1,699 tokens per session scan A 772ded1862c0

Subscribe to this mod's changes

mcp CLAUDE.md is an instructions file published in the GitHub repository platformatic/mcp (58 stars, last pushed 2d ago), licensed Apache-2.0. It adds 1,699 tokens to every session, about $0.0085 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.

Mobile Planning

mcp CLAUDE.md

Getting it into your agent

What it costs to keep this loaded

Grade A, and why

Nothing flagged

How it starts

CLAUDE.md

Overview

Key Features

Development Commands

Architecture

What this file has done since we first saw it

Other instructions, from other repositories

AppClaw CLAUDE.md

MobiAI-Core CLAUDE.md

freetube CLAUDE.md

ConsultMe CLAUDE.md

Plonk AGENTS.md

kotlin-app-template AGENTS.md