Stenobird

Episode

Structuring Codebases for AI, Claude Code in GitHub, Scale Acquired! Granola Cafe, AI Rules and More MCP

Podcast
You've Been a Bad Agent
Published
Jun 12, 2025
Duration seconds
3826
Processing state
processed
Canonical source
https://share.transistor.fm/s/82181cce
Audio
https://media.transistor.fm/82181cce/ad5f58a3.mp3
JSON
/v1/public/podcasts/you-ve-been-a-bad-agent-7334728/episodes/structuring-codebases-for-ai-claude-code-in-github-scale-acquired-granola-cafe-ai-rules-and-more-mcp
Markdown
/podcast/you-ve-been-a-bad-agent-7334728/structuring-codebases-for-ai-claude-code-in-github-scale-acquired-granola-cafe-ai-rules-and-more-mcp.md

Actions

  • POST https://stenobird.com/v1/public/podcasts/you-ve-been-a-bad-agent-7334728/episodes/structuring-codebases-for-ai-claude-code-in-github-scale-acquired-granola-cafe-ai-rules-and-more-mcp/transcription-requests
    Idempotently request low-priority transcript generation for this episode.
  • GET https://stenobird.com/podcast/you-ve-been-a-bad-agent-7334728/structuring-codebases-for-ai-claude-code-in-github-scale-acquired-granola-cafe-ai-rules-and-more-mcp.md
    Read the agent-friendly Markdown representation of this episode resource.

Summary

To leverage AI coding agents effectively, you must move beyond simple file access and focus on structuring codebases with clear boundaries and trace-based context. The discussion explores how tools like Claude Code and MCP servers can be optimized through better documentation and rule-based instructions.

Topics

  • Claude Code
  • Model Context Protocol
  • AI Coding Agents
  • Software Architecture
  • MCP Servers
  • Codebase Refactoring
  • Developer Tooling
  • Automated Migrations

Highlights

  • Main idea: Effective AI coding requires structuring codebases with clear boundaries and high-signal documentation to prevent model confusion
  • Practical takeaway: Use compact representations of key code transactions (traces) to teach agents which functions and files are critical to core logic
  • Failure mode: Models struggle with 'cleaning up' after themselves, necessitating strict rule files (like cursor-rules) to prevent unused variables and messy refactors
  • Technical insight: Using URL-based secrets in MCP servers can bypass the complexities and broken implementations of standard OAuth flows in AI clients
  • Tooling trend: The rise of subagents in tools like Shippie allows for parallel processing of complex coding tasks across different parts of a codebase

Chapters

  1. 1:00 Tech Industry Drama & Meta's Scale Acquisition: A discussion on the implications of Meta's 49% stake in Scale AI and the strategic importance of data distribution.
  2. 11:00 Codebase Structure for Parallelization: Exploring how separating testing frameworks, UI components, and logic allows for better parallel processing in AI-driven development.
  3. 15:00 Automating Migrations with Claude Code: Using Claude Code and custom utility libraries to automate large-scale version migrations and codebase updates.
  4. 20:00 Stateful AI Tools and Gitli: Discussing the emergence of stateful development tools and the utility of Gitli for managing developer workflows.
  5. 30:00 Solving Authentication in MCP Servers: Analyzing the Supermemory MCP approach to using URL-based secrets to avoid broken OAuth and Bearer token implementations.
  6. 44:00 Enforcing Strict Coding Standards via Rules: The necessity of using rule files to prevent models from introducing unused variables and unoptimized code.
  7. 53:00 Context-Aware Agents and Trace-Based Learning: The future of coding agents: providing models with traces of key transactions to improve understanding of complex logic flows.