This started based off of a hunch. We usually use OpenCode, but were 'forced' to use Claude Code for a while due to issues with Meridian. In that time, we saw the usage meter rise…

Stay ahead with insights on agentic AI, EU AI Act compliance, and automation in regulated industries. We put Claude Code and OpenCode on the same model, the same machine, and the same tasks, then examined everything sent and received. When we asked both harnesses for a one-line reply, Claude Code used roughly 33,000 tokens of system prompt, tool schemas, and injected scaffolding before the prompt even arrived. OpenCode used about 7,000. OpenCode's request prefix was byte-identical in every run we captured; it paid to cache its payload once per session and read it back for pennies. Claude Code on the other hand re-wrote tens of thousands of prompt-cache tokens mid-session, run after run, and on the same task wrote up to 54x more cache tokens than OpenCode. Cache writes of course are billed at a premium, which accounted for the usage dashboard climbing when using Claude Code. A production repository's 72KB instruction (AGENTS.md or CLAUDE.md) file adds another (avg) 20,000 tokens to every single request. Five modest MCP servers add 5,000 to 7,000 more. By the time a real working setup sends its first request, it is 75,000 to 85,000 tokens deep before the user has typed a word. A small task that cost 121,000 tokens done directly cost 513,000 tokens when fanned out to two subagents, because every subagent has its own bootstrap cost, and the parent then consumes its transcript.