benchflow-ai/agents

Minimal coding agents, easy to play with (opencode TUI) and easy to benchmark (ACP on BenchFlow) — built around mini-swe-agent

1 file for GitHub Copilot: agents copilot-instructions.md — 378 tokens loaded in every session.

Open on GitHub

11Stars on the repository

1Files it configures its agents with

378Tokens loaded in every session

1Agent configured

Instructions

agents copilot-instructions.md .github/copilot-instructions.md A 378 tok

These files are benchflow-ai/agents's own configuration — they tell GitHub Copilot 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.