Introduce LLM guardrails for ADRs: add `/docs/adr/AGENTS.md`
#3591583+ has been working well for me. Things I've noticed during my intense use of AI in the past few weeks while working on %"Symmetric Translation: Phase 1", where I worked solely on back-end functionality that introduced 2 new ADRs, both of which were AI-accelerated: 1. It referenced the current state of the implementation, pointing to prior issues, future issues and `@todo`s 2. In its writing, it would refer to concrete code in Drupal core, documentation handbook pages for Drupal core etc (which may change!) instead of referring exclusively to other ADRs
issue