Garry Tan spends $200K/yr on a 23-skill Claude Code setup — benchmarks show elaborate harnesses can lose to vanilla
echen · x · 2026-11-05
echen sparked discussion: YC's Garry Tan reportedly spends $200K/year on tokens via a Claude Code setup with 23 skills covering CEOs, designers, and eng managers.
- He questions whether elaborate coding-agent setups actually help, comparing them to fancy prompt-engineer titles.
- His team benchmarked harnesses on 100 sudo L7 tasks: one with 37 skills, 17 agents, and 8x cost performed worse than vanilla Claude Code; the best was simply xhigh effort with no add-ons.
Related event: Garry Tan's $200K Claude Code Setup Beaten by Bare Claude Code in Tests(2 posts)→
More from coding & agent
- LMArena opens Agent Arena for agent evaluation — arena · 2026-11-05
- Running Qwen 27B Q4 at 0.7 tok/s on a 4GB-VRAM laptop as a main coding model — Felix_455-788 · 2026-11-05
- His agent now auto-labels his Google Calendar in the background — steren · 2026-11-05
- The security startups racing to rein in AI agents — pstAsiatech · 2026-11-05
- OpenAI October dev roundup: Decisions API, 12-hour caching, 8x faster Codex tokens — OpenAIDevs · 2026-11-05
- Datadog previews Canvas, a new way to collaborate with AI agents on observability — farooqib · 2026-11-05