Thinking-Room

What it is

A Claude Code room with no code in it: the agent harness repurposed for thinking, reflection, and multi-model consultation. The council puts the same question to Claude, Codex, and Gemini and keeps their reads distinct instead of collapsing them into one consensus answer. Underneath: a blackboard protocol, a sealed-envelope moderator, an MCP transport, a turn-aware context extractor, and per-model self-read files that carry reasoning context across stateless CLI invocations.

Why I built it this way

It started from one question: how to give the same agent different context depending on whether I am building or thinking. Directory-scoped instructions answered it, and the rest grew from there. Three models with different training and conditioning give three real vantages, and the room is built to keep that divergence visible.

Implementation and public artifacts

Claude Code, Codex CLI, Gemini CLI, MCP

The source repository is private. This page is a personal project record.