Benchmark for Evaluating the Performance of Natural Language Models and Agents / Benchmark for evaluating natural language models and agents
4 files for Claude Code, Codex and OpenCode: gcp, question-creator, CAC-final-test AGENTS.md, CAC-final-test CLAUDE.md — 2,001 tokens loaded in every session.
AGENTS.md A 841 tok CLAUDE.md A 1,160 tok .claude/skills/question-creator/SKILL.md A 81 tok .claude/commands/gcp.md A 12 tok These files are T-Auto/CAC-final-test's own configuration — they tell Claude Code, 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.