Agentic benchmark runner for GPU cloud providers (beam.cloud, Colab, Modal, etc.)
6 files for Claude Code, Codex and OpenCode: agentic-bench, eval-reporter, gpu-runner, model-researcher and 2 more — 306 tokens loaded in every session.
AGENTS.md A 303 tok CLAUDE.md A 3 tok .claude/skills/agentic-bench/SKILL.md A 109 tok .claude/skills/eval-reporter/SKILL.md B 81 tok .claude/skills/gpu-runner/SKILL.md A 107 tok .claude/skills/model-researcher/SKILL.md A 74 tok These files are nyosegawa/agentic-bench'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.