Whole-system evaluation harness for SIS: models, memory, retrieval, datasets, named weaknesses, and proof cadence.
1 file for Codex and OpenCode: starlight-evals AGENTS.md — 1,072 tokens loaded in every session.
AGENTS.md A 1,072 tok These files are frankxai/starlight-evals's own configuration — they tell Codex and OpenCode how to work on this repository, so they are not mods to install elsewhere. Copy one as a starting point and replace the parts that are about this project.