Rework the Development Plan around live testing and the revised architecture

SSH execution and the agent as a container image come first (Phase 1),
then the new loop as a thin end-to-end slice, widened milestone by
milestone with a live run after each. Outline, Vikunja and per-agent VMs
are gone; the vault, the infrastructure repository and the agent host
replace them. The survey and issue map are refreshed.

Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01PPQ14L3LikyefCMFBqEbKE

docs/Development-Plan.md

@@ -1,10 +1,9 @@
 # Nisse — Development Plan
 
-**Status: agreed (PR #84); reworked in PR #92 after the architecture revision (PR
+**Status: agreed (PR #84); reworked in PR #92 after the architecture revision (PR #90).** How
-#90).** How to get from the code as it is to the architecture in
+to get from the code as it is to the architecture in `docs/Architecture.md`, in
-`docs/Architecture.md`, in what order, and how each step is accepted. The
+what order, and how each step is accepted. The architecture says *what and why*;
-architecture says *what and why*; this document says *how and when*, and is revised
+this document says *how and when*, and is revised as work lands.
-as work lands.
 
 **The priority is live testing.** Work is ordered so the agent runs live against
 real resources as early and as often as possible, and what each run finds steers