chore(memory): flush runtime memories and promote managed skills

Memory-file flush for the dotfiles-deploy session with the blankpad admin
credential scrubbed to a placeholder; sessions transcripts untracked
(gitignored) since harness transcripts can carry raw secrets.
Managed skills: command-center-dotfiles-import, ssh-fish-host-remote-exec,
stash-supersession-audit-before-drop.

agent/memories/--home-dank-.omp--/MEMORY.md

@@ -1,36 +1,29 @@
-# Environment & OS
-- User: Frank | Home: `/home/dank/` | Work Dir: `/home/dank/.omp`
-- OS/Kernel: CachyOS (Linux 7.2.0-1) with niri Wayland compositor
-- Default Browser: Firefox (managed via `xdg-settings`)
-- Cursor Config: `~/.config/niri/cfg/misc.kdl` (capitaine-cursors, size 48). Apply via `niri-msg reload` or `kill -SIGUSR1 $(pgrep niri)` to avoid full session restart.
-- NVIDIA/GPU Note: `nvidia-modeset` semaphore deadlock can freeze niri GUI. Fix: install `/etc/modprobe.d/nvidia-workarounds.conf`, rebuild initramfs (`mkinitcpio -P`), force-reboot (`systemctl reboot --force --force`). Note: force reboot kills active SSH sessions mid-flight.
+# Environment & Repository
+- **Home/Repo**: `/home/dank` → `/home/dank/.omp` (command center)
+- **Branch/Deploy**: `main` synced with `origin/main`. Deploy via `~/.omp/scripts/deploy.sh` (stow-style dotfiles/<pkg>/<path>).
+- **Git Workflow**: Execute `git stash` before `git checkout` to bypass dirty `agent/memories/` files. PRs branch from `pr/fix-*`.
+- **Secrets**: `GITEA_TOKEN` extracted to `~/.config/environment.d/secrets.env` (0600). .zshrc has guarded source stub.
+- **Gitea**: UI at `http://dankclaw:3000`, API resolves to `192.168.0.143:3000`. Repo: `dank/command-center`.
 
-# Model Configuration & Inference
-- Config Files (Edit in lock-step):
-  - Source: `~/.pi/agent/models.json`
-  - Import/Generation: `~/.omp/agent/models.yml` (co-located with `models.db` WAL/SHM files)
-- Provider Layout:
-  - `llamacpp (dankserver)` @ `http://192.168.0.235:7770/v1` | Model: `frank-default-small` | Context: 204800 | Reasoning: true | Inputs: [text, image]
-  - `llamacpp (dankclaw)` @ `http://192.168.0.143:7770/v1` | Model: `frank-default-large` | Context: 262144 | Reasoning: true | Inputs: [text, image]
-  - `dankclaw-npu` @ `http://192.168.0.143:7771/v1` | Model: `gemma4-it:e4b` (FastFlowLM) | Context: 131072 | Reasoning: true | Inputs: [text, image, audio]
-- Model Details:
-  - `frank-default-large`: Qwen3.8-Flash-Next Uncensored ROCmFP4 STRIX_LEAN (177B params, 56B MoE, ~98.3GB GGUF across 3 shards). Uses `--spec-type ngram-mod` speculative decoding (MTP head stripped). Vision enabled via `mmproj` (~866M). Docs updated in `/home/dank/.pi/agent/docs/pi/models.md` (commit `eda2edb`).
-  - Context Sizing: Uses Ki-style multiples (e.g., 200k = 204800). Always update both `contextWindow` and `maxTokens` when changing context. Config-only changes apply on next read; no cache flush required.
-  - NPU Image Constraint: FLM decoder strictly rejects WebP. Convert WebP to PNG/JPEG upstream before sending to the FLM endpoint.
-- Non-message token overhead: ~17301 tokens per context window.
+# Model Configuration
+- **Files**: `~/.pi/agent/models.json` (source of truth) ↔ `~/.omp/agent/models.yml` (imported/generated). Edit in lock-step to prevent overwrite on regeneration.
+- **Context Sizing**: Ki-style (×1024). e.g., 200k = 204800. Update both `contextWindow` and `maxTokens` simultaneously.
+- **frank-default-small**: llamacpp (dankserver :7770), ~204800 context, text/image, ngram-mod speculative decoding.
+- **frank-default-large**: llamacpp (dankclaw :7770), Qwen3.8-Flash-Next Uncensored ROCmFP4 STRIX_LEAN, 262144 context, 177B/56B-MoE, vision/mmproj, ngram-mod.
+- **Docs**: `~/.pi/agent/docs/pi/models.md` updated. Port migrated to 7770. MTP head stripped; use `ngram-mod` wording.
 
-# Git & Gitea Workflow
-- Gitea UI: `http://dankclaw:3000` (IP: 192.168.0.143:3000). API may return IP, but UI resolves best via hostname.
-- Repository: `dank/command-center`
-- PR Workflow: Branch `pr/fix-models` -> PR #1. Single commit, clean history.
-- Checkout Pitfall: `git checkout main` fails due to dirty tracked files in `agent/memories/` (e.g., `learned.md`).
-- Resolution: Execute `git stash` before `git checkout`. Stash is automatically saved on the previous branch (develop) for later retrieval.
+# Packages & Shell
+- **Shell**: Zsh + `cachyos-zsh-config`. `powerlevel10k-zsh` skipped (inert symlink due to dual sourcing).
+- **UI/Compositor**: `niri` (Wayland). Default browser: Firefox (`xdg-settings`). Cursor: `capitaine-cursors` @ 48px in `~/.config/niri/cfg/misc.kdl`. Reload via `niri-msg reload` or `kill -SIGUSR1`.
+- **Installed**: `quickshell` (`qs -c noctalia-shell`), `ghostty` (auto-sources via `GHOSTTY_RESOURCES_DIR`), `gnome-calculator`.
 
-# Migration & Tools (Pi → OMP)
-- `~/.pi/agent/SYSTEM.md` migrated to `~/.omp/agent/APPEND_SYSTEM.md` (8.4KB). New sessions pick up APPEND automatically.
-- `omp config set personality none` removes built-in personality block while keeping APPEND_SYSTEM.md intact.
-- Tool Mappings: `subagent` → `task`. Parameters `concurrency`, `context`, and `async` are dropped or handled by the harness (excess queues).
-- Skills: Auto-discovered from `~/.claude/skills`. Syntax: `/skill:grilling`, `/skill:tdd`. `skills.enableSkillCommands` defaults to true.
-- References: `okf-spec.md` points to pi-tree (`~/.pi/agent/docs/references/`); consider copying to `~/.omp` for full ownership. `omp://` provides 130+ docs. Use `skill://find-skills` for discovery.
-- Persona: 'Comrade Chief Designer' (Soviet-themed humor, friendly, concise).
-- Date Context: "It is September 2026" baked into persona; OMP injects real date per-request (may drift slightly).
+# NPU & Hardware
+- **NPU**: Dankclaw NPU (`gemma4-it:e4b`, FastFlowLM) at `http://192.168.0.143:7771/v1`.
+- **Image Constraint**: FLM strictly rejects WebP ('Unsupported image format'). Convert upstream to PNG/JPEG.
+- **Nvidia Fix**: `nvidia-modeset` semaphore deadlock resolved via `/etc/modprobe.d/nvidia-workarounds.conf`, `mkinitcpio -P`, force-reboot.
+
+# OMP & Agent Migration
+- **Migration**: pi-agent → OMP harness. `SYSTEM.md` → `APPEND_SYSTEM.md` (Comrade Chief Designer persona). `omp config set personality none` removes built-in block.
+- **Tools**: `subagent` → `task`. `concurrency`, `context`, `async` params dropped/managed by harness.
+- **Skills**: Auto-discovered from `~/.claude/skills`. Harness docs via `omp://`.
+- **State**: `main` 6 ahead of origin; push pending. `agent/managed-skills/*` auto-learn.