← Founder Notes
Archive

Opencode hit 1274 hn points this week with a 7k-token system prompt; claude code's is 32k. the moat…

Yethikrishna ROriginal on Threads

opencode hit 1274 hn points this week with a 7k-token system prompt; claude code's is 32k.

the moat in coding agents moved from how much context a model can hold to how much the harness throws away.

Context

A Hacker News item titled Claude Code sends 33k tokens before reading the prompt; OpenCode sends 7k (systima.ai) has 706 points at the time it was read and a search date of 12 July 2026. The 7k figure matches that title.

How it compares

The item gives 33k for Claude Code, not 32k, and 706 points, not 1274, and it is from 12 July 2026, not the week of the note. No Hacker News item with 1274 points was found, so the claim is unverified. The underlying systima.ai post was not read, and a title is not evidence of an audited system-prompt measurement. The HN wording is tokens sent before the prompt, which the note calls a system prompt. That the moat moved to what the harness throws away is the author's opinion.

Related work

Watch next

  • The systima.ai post's measurement method.

Sources

  1. Claude Code sends 33k tokens before reading the prompt; OpenCode sends 7k (Hacker News)news.ycombinator.com

Provenance

The note above is reproduced unedited from the original post, first published on Threads on 5 September 2026 at 19:03 IST. Sources are the papers and datasets the note draws on.

View the original post
Embed this note
<iframe src="https://founder.myndlabs.tech/notes/embed/opencode-hit-1274-hn-points-this-week-with-Dc6FBWajuO8" width="480" height="420" style="border:0;max-width:100%" loading="lazy" title="Opencode hit 1274 hn points this week with a 7k-token system prompt; claude code's is 32k. the moat…"></iframe>

More notes