Which tools Claude Code, Codex, and Cursor pick in 16,893 real coding sessions
Which tools do Claude, Codex and Cursor choose? We measured 17k runs to find out
Armature ran nearly 17k experiments across 75 repos and 1,163 prompt variants to see which services Claude Code, Codex, and Cursor actually install. They simulated four personas—vibe coder, junior, senior, and enterprise engineer—and had agents go from analysis to implementation. The post discloses partial findings: in object storage, Cloudflare R2 started beating Amazon S3 once a simulated human was added to the loop; in databases, Neon was repeatedly recommended. Full leaderboards and raw traces are published, but the article body cuts off before covering more categories.
Why it matters: The Armature team ran nearly 17,000 sessions to measure how Claude Code, Codex and Cursor pick third-party services in real codebases, covering 1,163 prompt variants, 75 repositories and four user personas.