AI Summary
→ WHAT IT COVERS James Phoenix shares advanced Claude Code optimization techniques, spending $3,400 monthly on 2.3 billion tokens. He covers hierarchical rule systems, parallelized testing architecture, git work trees, and transitioning from coder to engineering manager. → KEY INSIGHTS - **Hierarchical Claude.md Files:** Place global rules in root Claude.md but create localized Claude.md files in subdirectories for package-specific patterns. This prevents context rot from excessive input tokens while maintaining relevant rules at appropriate application layers without degrading model performance. - **Testing Parallelization Architecture:** Eliminate seed data from SQL files entirely. Use factory functions to generate dynamic test data at runtime, prefix users with branch names, and create custom Postgres schemas per test. This enables true database isolation for parallel test execution across multiple agents. - **Code Review Timing:** Push back on Claude Code mistakes immediately during the active session rather than later. Finding the specific session ID afterward requires searching through histories with dash dash resume. Real-time correction prevents merging poor quality code that becomes harder to trace after multiple commits. - **Mutative vs Additive Code Risk:** Additive features that don't touch existing files pose minimal risk and can be deleted easily. Modificative code that updates dependencies, service layers, or existing infrastructure creates dangerous technical debt. Use separate git work trees for risky refactors to isolate potential failures. → NOTABLE MOMENT Phoenix reveals he downgraded his $200 Cursor Ultra subscription while keeping the $200 Claude Code plan, using Cursor only for fixing work or slowing down. Most development work now happens entirely through Claude Code, demonstrating a fundamental shift in development workflows. 💼 SPONSORS [{"name": "Paddle", "url": "https://paddle.com"}] 🏷️ Claude Code, Agentic Coding, AI Development Tools, Software Testing