2 sources filed · EN 1 · KO 1
Without the sentence, 90.1% of choices matched the stale file: 86.4% for Claude Code, 93.9% for Codex CLI.
90.1%share of agent choices (649 of 720) that followed a stale instruction file over the existing code
A harness is described as workflow, skills, tools and context, and operating instructions around a model.
270,000+tokens in the jansori knowledge base
1 source filed · RU 1
Tree docs beat skills on answer accuracy and on calling the docs or skills a question implied, in both Claude and Codex.
30%extra tokens Claude spent with tree docs compared with skills, per the tester (not seen in Codex)