The Model Isn't the Product. The Harness Is.
After auditing a publicly posted Claude Code source snapshot and reading OpenAI's harness essays, I came away with one conclusion: the model is only the brain. The product is the runtime around it.
3 parts · Mar 31, 2026 – Mar 31, 2026
After auditing a publicly posted Claude Code source snapshot and reading OpenAI's harness essays, I came away with one conclusion: the model is only the brain. The product is the runtime around it.
The most important file in the Claude Code snapshot isn't a prompt file or a tool definition. It's a state machine. Once you see that, a lot of agent design decisions start making sense.
The most novel thing in the Claude Code snapshot isn't a tool or a prompt. It's how aggressively the runtime is built around preserving prompt-cache identity across forks, compaction, and long-running sessions.
© Xingfan Xia 2024 - 2026 · CC BY-NC 4.0