nyosegawa/agentic-bench

Agentic benchmark runner for GPU cloud providers (beam.cloud, Colab, Modal, etc.)

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.

5Stars on the repository

6Files it configures its agents with

306Tokens loaded in every session

3Agents configured

Instructions

agentic-bench AGENTS.md AGENTS.md A 303 tok
agentic-bench CLAUDE.md CLAUDE.md A 3 tok

Skills

agentic-bench .claude/skills/agentic-bench/SKILL.md A 109 tok
eval-reporter .claude/skills/eval-reporter/SKILL.md B 81 tok
gpu-runner .claude/skills/gpu-runner/SKILL.md A 107 tok
model-researcher .claude/skills/model-researcher/SKILL.md A 74 tok