sub-agents-mcp and mcp-ai-agent-guidelines
About sub-agents-mcp
shinpr/sub-agents-mcp
Define task-specific AI sub-agents in Markdown for any MCP-compatible tool.
Markdown-defined agents execute via pluggable CLI backends (Cursor, Claude Code, Gemini, or Codex), with built-in session management and error handling for multi-step workflows. The MCP server architecture enables teams to define reusable agents once and consume them across any MCP-compatible IDE or tool, creating portable Claude Code–style sub-agent capabilities outside Claude's environment.
About mcp-ai-agent-guidelines
Anselmoo/mcp-ai-agent-guidelines
A Model Context Protocol (MCP) server offering professional tools and templates for hierarchical prompting, code hygiene, visualization, memory optimization, and agile planning.
Implements agent-to-agent orchestration with tool chaining and context propagation, enabling multi-step workflows where tools invoke each other with shared state. Built as a Node.js MCP server with TypeScript, it exposes specialized tools for code quality analysis (hygiene scoring 0-100), flow-based prompting, Mermaid diagram generation, and dependency-aware sprint planning, integrating via stdio transport with Claude and compatible AI agents.
Related comparisons
Scores updated daily from GitHub, PyPI, and npm data. How scores work