bence-toth/agent-benchmark

Benchmark Claude configuration changes against your own tasks in your own repositories

1 file for Codex and OpenCode: agent-benchmark AGENTS.md — 989 tokens loaded in every session.

Open on GitHub bence-toth.github.io

2Stars on the repository

1Files it configures its agents with

989Tokens loaded in every session

2Agents configured

Instructions

agent-benchmark AGENTS.md AGENTS.md A 989 tok

These files are bence-toth/agent-benchmark'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.