Your AI Agents Are Exploring Blind. Here's How to Give Them a Map.

Your AI Agents Are Exploring Blind. Here's How to Give Them a Map. Draft — queued after ai-autonomy-dod Every session, Claude reads the same files. Codex re-discovers the same plugin pattern. Gemini asks the same questions about folder structure. The agents aren't slow. They're starting from zero every time. The missing piece isn't a smarter model. It's a standing index. The Exploration Tax In a multi-agent workflow, every agent pays an exploration tax at the start of every session. Before it can do anything useful, it has to orient itself: Where does the plugin system live? What naming conventions apply? Which files are subtree-managed and off-limits? What decisions have already been made? In a small codebase, this is annoying. In a large one — or one with multiple agents running in parallel — it's where tokens go to die. The standard fix is a CLAUDE.md or AGENTS.md that describes the codebase in prose. That helps. But prose is passive. An agent reads it and still has to map it to the