I've had very good experience with building a very architecture-conscious folder structure and putting AGENTS.md in every folder (and, of course, instruction to read _and_ update those in the root prompt). But with Agent-written docs I also have to run doc maintainer agent pretty often.

> and putting AGENTS.md in every folder (and, of course, instruction to read _and_ update those in the root prompt).

For me, Claude Code completely ignores the instruction to read and follow AGENTS.md, and I have to remind it every time.

The joys of non-deterministic blackboxes.