Claude Code used 83k tokens to write a Fibonacci script. Pi (OpenClaw) used 8k. Same task. Same output. Where did the rest of tokens go? Here's the tax no one's talking about.

Portkey's resource offers insights, tutorials, and resources for web developers and designers. Readers can learn about frontend development, user experience design, and web development tools. With articles, tutorials, and design showcases, Portkey provides  guidance and expertise for creating modern and responsive web applications.

portkey

A benchmark comparing the token overhead of three AI coding agents (Claude Code, OpenAI Codex, and Pi/OpenClaw) reveals a hidden cost called the 'harness tax' — the tokens an agent spends on itself before doing any useful work. Claude Code consumed ~27,000 input tokens per request vs Pi's ~2,600 for the same trivial task. Over a 40-turn session, this compounds to over 1 million wasted input tokens. Beyond cost, harness bloat causes 'context rot,' degrading model attention on actual task content. The post argues that as models improve, thick harnesses become dead weight, and the better design pushes complexity into the model and infrastructure rather than the context window.

The Harness Tax: The Dead Weight Inside Your Coding Agent