Garry Tan's $200K Claude Code Setup Beaten by Bare Claude Code in Tests

Garry Tan spends about $200K a year on tokens running a 23-skill Claude Code setup, but Surge AI's benchmarks show bare Claude Code outperforms such elaborate agent frameworks.

2026-11-05 ~ 2026-11-05 · 2 related posts

• Garry Tan spends $200K/yr on a 23-skill Claude Code setup — benchmarks show elaborate harnesses can lose to vanilla — echen · 2026-11-05
• Surge AI benchmarked coding-agent harnesses: vanilla Claude Code beat them all — echen · 2026-11-05