codingbuddy

Overview

Codingbuddy is a comprehensive MCP server that coordinates multiple AI agents across various tools to deliver code quality comparable to a team of human experts. It features a structured development cycle with PLAN, ACT, and EVAL modes, plus an AUTO mode that runs the full cycle autonomously. The system tracks impact metrics and generates detailed session reports showing issues prevented, agents dispatched, and quality improvements.

Try asking AI

After installing, here are 5 things you can ask your AI assistant:

• get_session_impact

  Generate a summary report of coding session impact including issues prevented, agents dispatched, and quality improvements.

  Try:Show me my coding session impact reportTry:What issues were prevented in the last session?
• ship

  Run CI checks, create branch, commit, push, and pull request.

  Try:Ship the current changesTry:Create PR for these commits
• retrospective

  Analyze session archives for patterns and improvements.

  Try:Run a retrospective on recent sessionsTry:What patterns should I improve?
• test-driven-development

  Enforce Red → Green → Refactor TDD cycle.

  Try:Start TDD for this featureTry:Implement with test-driven development
• systematic-debugging

  Perform root cause analysis before proposing fixes.

  Try:Debug this issue systematicallyTry:Find root cause of the bug
• security-audit

  Conduct OWASP Top 10 review and scan for secrets.

  Try:Audit this code for security issuesTry:Perform security review
• performance-optimization

  Profiling-first optimization workflow.

  Try:Optimize this code for performanceTry:Improve the application's performance
• refactoring

  Apply Tidy First principles with test safety.

  Try:Refactor this codeTry:Improve code structure without changing functionality
• brainstorming

  Explore intent and requirements before building.

  Try:Brainstorm solutions for this problemTry:Explore requirements before implementation

Note: Tool names inferred from the 'Built-in Skills' section, but actual MCP tool signatures not explicitly documented in the README.

Comparable tools

Installation

# 1. Install
npm install -g codingbuddy

# 2. Initialize your project
npx codingbuddy init

# 3. Add to your AI tool's MCP config

{
  "mcpServers": {
    "codingbuddy": {
      "command": "npx",
      "args": ["codingbuddy", "mcp"]
    }
  }
}

FAQ

What AI tools are supported by Codingbuddy?

Codingbuddy supports 9 AI tools including Claude Code, Cursor, GitHub Copilot, Amazon Q, and others. See the full list in the README.

How does Codingbuddy measure code quality improvements?

Codingbuddy tracks impact metrics throughout each session and generates a Session Impact Report showing issues prevented, agents dispatched, and mode transitions.

Compare codingbuddy with