Multiple agents, one source of truth: a Planner/Coder/Reviewer demo of how a shared Statewave subject prevents parallel-agent context collisions.
1 file for Codex and OpenCode: statewave-multi-agent-shared-context AGENTS.md — 380 tokens loaded in every session.
AGENTS.md A 380 tok These files are smaramwbc/statewave-multi-agent-shared-context'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.