Claude Code sends about 33k tokens of overhead before the prompt, OpenCode about 7k

Category: Agentic coding
Status: discussion
Sources: systima.ai measurement, HN discussion
Summary: A logging-proxy measurement published 2026-07-12 reports that Claude Code 2.1.207 sends roughly 33,000 tokens of system prompt, tool schemas, and injected reminder blocks before the user prompt on claude-sonnet-4-5, against about 7,000 for OpenCode 1.17.18, a 4.7x floor difference. The gap is mostly tool schemas (27 tools, about 24,000 tokens, versus 10 tools, about 4,800 tokens) plus a larger system prompt (about 6,500 versus about 2,000 tokens). The author reports the ratio narrows to about 3.3x on Claude Fable 5 and that Claude Code rewrites its cached prefix mid-session, writing up to 54x more cache tokens than OpenCode's byte-identical prefix.
Comments: HN commenters note the test pinned an older Sonnet 4.5 and reads as AI-assisted writing, argue Anthropic is incentivized to spend tokens for agent quality while other harnesses trade cost against performance, and report other agents firing 30+ tool calls on trivial prompts such as "commit".
Why it matters: The per-request token floor and cache-write behavior set coding-agent latency and cost before any work begins, so harness overhead is a direct operational cost, not a detail.