GitHub template for autonomous AI coding agents: Docker-isolated runs, beads task tracking, iterative implementation from a spec
2 files for Codex, OpenCode and Claude Code: ralph_harness AGENTS.md, ralph_harness CLAUDE.md — 562 tokens loaded in every session.
AGENTS.md A 121 tok CLAUDE.md A 441 tok These files are coobeeyon/ralph_harness's own configuration — they tell Codex, OpenCode and Claude Code 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.