start_here — Markdown Lane Check - llms.txt, .md twins, Accept: text/markdown MCP Prompt

start_here is one of 1 prompt on the Markdown Lane Check - llms.txt, .md twins, Accept: text/markdown MCP server. Connect the server and it appears in your client, ready to invoke.

by client

How to invoke start_here from your client

• Claude Code Markdown Lane Check - llms.txt, .md twins, Accept: text/markdown Prompt/start_here run in your project directory
• Claude Desktop Markdown Lane Check - llms.txt, .md twins, Accept: text/markdown Prompt/start_here ~/Library/Application Support/Claude/claude_desktop_config.json
• Cursor Markdown Lane Check - llms.txt, .md twins, Accept: text/markdown Prompt/start_here ~/.cursor/mcp.json
• VS Code Markdown Lane Check - llms.txt, .md twins, Accept: text/markdown Prompt/start_here .vscode/mcp.json
• Zed Markdown Lane Check - llms.txt, .md twins, Accept: text/markdown Prompt/start_here ~/.config/zed/settings.json
• Windsurf Markdown Lane Check - llms.txt, .md twins, Accept: text/markdown Prompt/start_here ~/.codeium/windsurf/mcp_config.json
• Cline Markdown Lane Check - llms.txt, .md twins, Accept: text/markdown Prompt/start_here ~/Library/Application Support/Code/User/globalStorage/saoudrizwan.claude-dev/settings/cline_mcp_settings.json
• Gemini CLI Markdown Lane Check - llms.txt, .md twins, Accept: text/markdown Prompt/start_here ~/.gemini/settings.json
• Grok Markdown Lane Check - llms.txt, .md twins, Accept: text/markdown Prompt/start_here .mcp.json (in your project root)
• ChatGPT Markdown Lane Check - llms.txt, .md twins, Accept: text/markdown Prompt/start_here Settings → Connectors → Advanced → Developer mode
• Claude.ai Markdown Lane Check - llms.txt, .md twins, Accept: text/markdown Prompt/start_here Settings → Connectors → Add custom connector
• LangChain Markdown Lane Check - llms.txt, .md twins, Accept: text/markdown Prompt/start_here pip install langchain-mcp-adapters

Markdown Lane Check - llms.txt, .md twins, Accept: text/markdown also offers 4 resources — data you attach as context, where a prompt is something you run.

Read from the server itself, by connecting to it and calling prompts/list on 24 September 2026. A listing does not declare its prompts, so asking is the only way to know them, and this is what the server actually offers rather than what its listing claims. Names only are stored; connect the server for each prompt's arguments.