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.
npx agentmods add instructions/syndicats/mcp-initializer/claude-mdgit clone --depth 1 https://github.com/Syndicats/mcp-initializerWrote 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.
[](https://agentmods.dev/instructions/syndicats/mcp-initializer/claude-md)<a href="https://agentmods.dev/instructions/syndicats/mcp-initializer/claude-md"><img src="https://agentmods.dev/badge/instructions/syndicats/mcp-initializer/claude-md.svg" alt="Measured on agentmods" height="20"></a>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 | $0.00381 | $0.00381 |
| Opus 5 | $0.00191 | $0.00191 |
| Sonnet 5 | $0.00076 | $0.00076 |
| Haiku 4.5 | $0.00038 | $0.00038 |
Grade A, and why
mcp-initializer 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 4d 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.
What it actually says
CLAUDE.md
This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
Project Overview
This is an MCP (Model Context Protocol) Project Initializer - a command-line MCP server that automates the setup of new AI-powered software projects. The tool acts as a conversational guide through any standard MCP client to set up projects with necessary context, rules, and documentation for AI-assisted development.
Architecture
Core Requirements
- Language: TypeScript
- Runtime: Node.js (LTS version)
- Protocol: Model Context Protocol (MCP) communicating over STDIO
- Core Dependency:
@modelcontextprotocol/sdkTypeScript SDK - LLM Interaction: Uses "Prompt Server / Response" pattern (
mcp_prompt_requestandmcp_llm_response) - no direct LLM API keys
Key Features to Implement
- Conversational Project Initialization - Trigger setup workflow via
/init-mcpcommand - Technology-Specific Context Fetching - Download best-practice rules and SDK docs
- Custom Documentation Ingestion - Handle URLs and raw text input
- LLM-Powered PRD Generation - Generate project documentation using gathered context
- Local File System Operations - Create directories and save files to project structure
Development Status
This is a greenfield project - currently contains only planning documentation:
docs/prd.md: Complete Product Requirements Documentdocs/llms-full.txt: MCP client compatibility matrix and examples
Key Design Principles
- Server must NOT have its own LLM API key
- Final script should be executable directly from command line
- Focus on TypeScript/Node.js ecosystem initially
- Leverage existing MCP protocol patterns for client communication
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.
- 4d ago First seen · 36 lines · 381 tokens per session scan A 8d652536aeb9
mcp-initializer CLAUDE.md is an instructions file published in the GitHub repository Syndicats/mcp-initializer (3 stars, last pushed 1y ago), licensed MIT. It adds 381 tokens to every session, about $0.0019 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.
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.
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.
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).
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.
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.
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).