Claude Code burns 5x more tokens before you type a word. Here's where they go.
Article summary
Quick briefing — cleaned from the original RSS feed
Somebody finally put a logging proxy between the harnesses and the API and measured what actually goes over the wire. Systima did it, and the numbers are not subtle. Claude Code opens a session with roughly 33,000 tokens of system prompt, tool schemas, and injected scaffolding. OpenCode, running the same model on the same machine, opens with about 7,000. You haven't typed anything yet. What actually goes in those 33k tokens The breakdown is illuminating: 27 tool schemas — Claude Code ships the…
1Key Takeaways
- Somebody finally put a logging proxy between the harnesses and the API and measured what actually goes over the wire.
- Systima did it, and the numbers are not subtle.
- Claude Code opens a session with roughly 33,000 tokens of system prompt, tool schemas, and injected scaffolding.
- OpenCode, running the same model on the same machine, opens with about 7,000.
2AIWedia Score
9/10
Must-read — high impact for AI builders
Based on source trust, recency, category impact, and story depth.
3Why it matters
Coding AI shifts how fast software ships and how much human review each change needs. DEV — AI reports that somebody finally put a logging proxy between the harnesses and the API and measured what actually goes over the wire.
Explore related
Browse toolsCoding AI news
Explore curated coding ai tools on AIWedia — compare, rank, and launch from our directory.
Full story on DEV — AI
Read full articleHeadlines aggregated via RSS for discovery on AIWedia. Original content © DEV — AI. We link to the source and do not republish full articles.