agent: repoint roles to frank-medium/dankclaw-3090; sync niri tweaks, memories, managed skills

- config.yml: default/commit -> frank-medium (dankserver); task/tiny/smol/vision -> frank-small (dankclaw-3090); vision xhigh
- models.yml: add llamacpp (dankclaw-3090) provider; frank-large preserve_thinking + context notes
- niri: focus-ring/border/shadow layout, hot-corners off, re-add noctalia.kdl include; blankpad eDP-1 scale 1.0
- memories: flush rollouts; retire frank_large + marreta_authentik skills; add auth-chain/kv-pool/quadlet-log skills
- managed-skills: 40+ new fleet runbook skills
- agent/skills: import built-in skill set

agent/memories/--home-blank-Projects-serverAppConfig--/memory_summary.md

@@ -1 +1 @@
-dankclaw hosts frank-large (rootless Quadlet, 103.4 GiB RAM, 3 KV slots, greedy default) and marreta (podman compose, Caddy/Anubis/Authentik guard chain). Key ops: probe marreta internally to avoid netns HTTP 000; set temperature: 0 on frank-small for determinism; preserve_thinking is client-side per-request. Watch for file-cache uninterruptible sleep and missing pyyaml on system python3. Authentik flows must link Application(slug=marreta) to prevent Rust outpost crashes.
+dankclaw/dankserver systems featuring ROCmFPX and llama.cpp. frank-large (HALOGEN) uses a 524288 KV pool and is managed via rootless Quadlets (mandatory for persistence). Key hardware fix: M.2 riser for R9700 chipset PCIe issues. Key software behavior: Halogen stalls are documented (don't restart), first-request silence is normal, and HIP env vars (TEMP/HOST) must be handled carefully. Marreta is secured via an Authentik/Anubis auth chain.