Tommkruix/agentrulebench

A reproducible benchmark: do AI coding agents violate architectural import-boundary rules inferred from real codebases? Harness, pre-registration, data, and a null result.

2 best points · 0 comments · 1 Hacker News post · 4 GitHub stars · View on GitHub

Hacker News discussions

• Show HN: AgentRuleBench, does AI agents violate inferred architecture rules? (2 points, 0 comments, by Tommkruix123, 2026-09-12)