Adopt the suite working method

AGENTS.md

@@ -9,9 +9,9 @@ osrlib is a Python library implementing the classic 1981 B/X (Basic/Expert) fant
 - `osrlib/data/` is generated by `tools/srd_compile/` and is never hand-edited. CI regenerates and fails on diff.
 - When a rules question comes up, the SRD text in `srd/` is the authority. Quote it in review discussions rather than working from memory.
 
-## The phase loop
+## Working method
 
-Each roadmap phase in `docs/spec.md` ships as two PRs — a plan, then an implementation — and both follow the same create → rubber-duck → revise-until-solid → PR loop. "Work up a plan for phase N" or "implement the plan for phase N" means run this loop end to end, unprompted. The full runbook — planning, implementing, and the rubber-duck review loop — is `.claude/skills/phase-loop/SKILL.md`.
+Work is divided into chunks that the lead role packets to coder roles, with acceptance tests written before the implementation by a different agent and committed marked expected-to-fail. The method, the roles, the packet, and the worktree rules are in the suite guide at `../CLAUDE.md`, and the role definitions are in `../.claude/agents/`. Each roadmap phase in `docs/spec.md` is a batch of chunks. The plans under `docs/phase-N-plan.md` are the record of phases already built.
 
 ## Toolchain