edonadei/caliper

Run your real agent with and without your skills, MCPs, and rules. See which ones actually help, and what they cost in tokens. Supports Claude Code, Codex, Pi, and Hermes.

3 best points · 3 comments · 1 Hacker News post · 229 GitHub stars · View on GitHub

Hacker News discussions

• Show HN: Caliper – pass@k reliability testing for Claude Code and Codex skills (3 points, 3 comments, by edonadei, 2026-06-28)