Update local config and plugin metadata

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>

.claude/ralph-loop.local.md

@@ -1,6 +1,6 @@
 ---
 active: true
-iteration: 16
+iteration: 36
 max_iterations: 0
 completion_promise: "The morning-report skill is fully implemented, tested, and registered"
 started_at: "2026-01-03T08:16:44Z"

docs/plans/.completed/2026-01-05-workstation-monitoring-design.status

@@ -0,0 +1,17 @@
+{
+  "plan": "2026-01-05-workstation-monitoring-design.md",
+  "status": "COMPLETE",
+  "completed_at": "2026-01-05T14:09:00Z",
+  "implementation": {
+    "node_exporter": "installed and running (v1.10.2-1)",
+    "scrape_config": "deployed (workstation-scrape)",
+    "prometheus_rule": "deployed (workstation-alerts, 12 rules)",
+    "prometheus_target": "UP and scraping",
+    "git_commit": "9d17ac8",
+    "network_solution": "Tailscale (100.90.159.78:9100)"
+  },
+  "verification": {
+    "all_success_criteria_met": true,
+    "verified_at": "2026-01-05T14:09:19Z"
+  }
+}

docs/plans/2026-01-05-workstation-monitoring-design.md

@@ -0,0 +1,296 @@
+# Workstation Monitoring Design
+
+## Overview
+
+Deploy comprehensive monitoring for the Arch Linux workstation (willlaptop) by integrating with the existing k8s monitoring stack. This will enable proactive alerting for resource exhaustion, long-term capacity planning, and performance debugging.
+
+**Reference:** Future consideration `fc-001` (workstation monitoring)
+
+## Current Infrastructure
+
+- **Workstation:** Arch Linux on MacBookPro9,2 (hostname: willlaptop)
+- **K8s Cluster:** kube-prometheus-stack deployed with Prometheus, Alertmanager, Grafana
+- **Network:** Direct network connectivity between workstation and cluster nodes
+- **Existing Monitoring:** 3 node_exporters on cluster nodes, cluster-level alerts configured
+
+## Architecture
+
+### Components
+
+```
+┌─────────────────┐     HTTP/9100      ┌──────────────────────┐
+│   Workstation   │ ──────────────────> │   K8s Prometheus    │
+│   (willlaptop)  │   scrape every 15s │   (monitoring ns)   │
+│                 │                    │                      │
+│  node_exporter  │                    │  workstation rules  │
+│  systemd service│                    │  + scrape config    │
+└─────────────────┘                    └──────────────────────┘
+                                                      │
+                                                      v
+                                         ┌──────────────────────┐
+                                         │  Alertmanager        │
+                                         │  (existing setup)    │
+                                         │  unified routing     │
+                                         └──────────────────────┘
+```
+
+### Data Flow
+
+1. **node_exporter** exposes metrics on `http://willlaptop:9100/metrics`
+2. **Prometheus** scrapes metrics every 15s via static target configuration
+3. **PrometheusRule** evaluates workstation-specific alert rules
+4. **Alertmanager** routes alerts to existing notification channels
+
+## Workstation Deployment
+
+### node_exporter Service
+
+**Installation:**
+```bash
+pacman -S prometheus-node-exporter
+```
+
+**Systemd Configuration:**
+- Service: `node_exporter.service`
+- User: `node_exporter` (created by package)
+- Listen address: `0.0.0.0:9100`
+- Restart policy: `always` with 10s delay
+- Logging: systemd journal (`journalctl -u node_exporter`)
+
+**ExecStart flags:**
+```bash
+/usr/bin/node_exporter --collector.filesystem.mount-points-exclude=^/(sys|proc|dev|host|etc)($|/)
+```
+
+Excludes system mounts to reduce noise.
+
+**Firewall Configuration:**
+- Allow TCP 9100 from cluster nodes
+- Use ufw or iptables to restrict access
+
+**Metrics Collected:**
+All default collectors except resource-intensive ones:
+- CPU, memory, filesystem, network
+- System stats (uptime, load average, systemd)
+- Thermal (if available on hardware)
+- Disk I/O
+
+## Prometheus Configuration
+
+### Static Scrape Target
+
+**Job configuration:**
+- Job name: `workstation/willlaptop`
+- Target: `willlaptop:9100` (DNS resolution) or workstation IP
+- Scrape interval: `15s` (matches cluster node_exporter)
+- Scrape timeout: `10s`
+- Metrics path: `/metrics`
+- Honor labels: `true`
+
+**Relabeling rules:**
+- Add `env: "workstation"` label for identification
+- Preserve `instance: "willlaptop"` from target
+
+**Integration:**
+Add to existing Prometheus CRD configuration in kube-prometheus-stack. This can be done via:
+- PrometheusRule with additional scrape config, or
+- Direct modification of Prometheus configuration
+
+## Alert Rules
+
+### PrometheusRule Resource
+
+**Namespace:** `monitoring`
+**Kind:** `PrometheusRule`
+**Labels:** Standard discovery labels for Prometheus operator
+
+### Alert Categories
+
+#### Critical Alerts (Paging)
+
+1. **WorkstationDiskSpaceCritical**
+   - Condition: `<5%` free on any mounted filesystem
+   - Duration: 5m
+   - Severity: critical
+
+2. **WorkstationMemoryCritical**
+   - Condition: `>95%` memory usage
+   - Duration: 5m
+   - Severity: critical
+
+3. **WorkstationCPUCritical**
+   - Condition: `>95%` CPU usage
+   - Duration: 10m
+   - Severity: critical
+
+4. **WorkstationSystemdFailed**
+   - Condition: Failed systemd units detected
+   - Duration: 5m
+   - Severity: critical
+
+#### Warning Alerts (Email/Slack)
+
+1. **WorkstationDiskSpaceWarning**
+   - Condition: `<10%` free on any mounted filesystem
+   - Duration: 10m
+   - Severity: warning
+
+2. **WorkstationMemoryWarning**
+   - Condition: `>85%` memory usage
+   - Duration: 10m
+   - Severity: warning
+
+3. **WorkstationCPUWarning**
+   - Condition: `>80%` CPU usage
+   - Duration: 15m
+   - Severity: warning
+
+4. **WorkstationLoadHigh**
+   - Condition: 5m load average > # CPU cores
+   - Duration: 10m
+   - Severity: warning
+
+5. **WorkstationDiskInodeWarning**
+   - Condition: `<10%` inodes free
+   - Duration: 10m
+   - Severity: warning
+
+6. **WorkstationNetworkErrors**
+   - Condition: High packet loss or error rate
+   - Duration: 10m
+   - Severity: warning
+
+#### Info Alerts (Log Only)
+
+1. **WorkstationDiskSpaceInfo**
+   - Condition: `<20%` free on any mounted filesystem
+   - Duration: 15m
+   - Severity: info
+
+2. **WorkstationUptime**
+   - Condition: System uptime metric (recording rule)
+   - Severity: info
+
+### Alert Annotations
+
+Each alert includes:
+- `summary`: Brief description
+- `description`: Detailed explanation with metric values
+- `runbook_url`: Link to troubleshooting documentation (if available)
+
+## Versioning
+
+### Repository Structure
+
+```
+~/.claude/repos/homelab/charts/willlaptop-monitoring/
+├── prometheus-rules.yaml         # PrometheusRule for workstation alerts
+├── values.yaml                    # Configuration values
+└── README.md                     # Documentation
+```
+
+### Values.yaml Configuration
+
+Configurable parameters:
+```yaml
+workstation:
+  hostname: willlaptop
+  ip: <workstation_ip>  # optional, fallback to DNS
+
+scrape:
+  interval: 15s
+  timeout: 10s
+
+alerts:
+  disk:
+    critical_percent: 5
+    warning_percent: 10
+    info_percent: 20
+  memory:
+    critical_percent: 95
+    warning_percent: 85
+  cpu:
+    critical_percent: 95
+    critical_duration: 10m
+    warning_percent: 80
+    warning_duration: 15m
+```
+
+### Integration with ArgoCD
+
+Follows existing GitOps pattern (charts/kube-prometheus-stack). Can be added to ArgoCD for automated deployments if desired.
+
+## Testing and Verification
+
+### Phase 1 - Workstation Deployment
+
+1. Verify node_exporter installation:
+   ```bash
+   pacman -Q prometheus-node-exporter
+   ```
+
+2. Check systemd service status:
+   ```bash
+   systemctl status node_exporter
+   ```
+
+3. Verify metrics endpoint locally:
+   ```bash
+   curl http://localhost:9100/metrics | head -20
+   ```
+
+4. Test accessibility from cluster:
+   ```bash
+   kubectl run -it --rm debug --image=curlimages/curl -- curl willlaptop:9100/metrics
+   ```
+
+### Phase 2 - Prometheus Integration
+
+1. Verify Prometheus target:
+   - Access Prometheus UI → Targets → workstation/willlaptop
+   - Confirm target is UP
+
+2. Verify metric ingestion:
+   ```bash
+   # Query in Prometheus UI
+   node_up{instance="willlaptop"}
+   ```
+
+3. Verify label injection:
+   - Confirm `env="workstation"` label appears on metrics
+
+### Phase 3 - Alert Verification
+
+1. Review PrometheusRule:
+   ```bash
+   kubectl get prometheusrule workstation-alerts -n monitoring -o yaml
+   ```
+
+2. Verify rule evaluation:
+   - Access Prometheus UI → Rules
+   - Confirm workstation rules are active
+
+3. Test critical alert:
+   - Temporarily trigger a low disk alert (or simulate)
+   - Verify alert fires in Prometheus UI
+
+4. Verify Alertmanager integration:
+   - Check Alertmanager UI → Alerts
+   - Confirm workstation alerts are received
+
+## Success Criteria
+
+- [ ] node_exporter running on workstation
+- [ ] Metrics accessible from cluster nodes
+- [ ] Prometheus scraping workstation metrics
+- [ ] Alert rules evaluated and firing correctly
+- [ ] Alerts routing through Alertmanager
+- [ ] Configuration versioned in homelab repository
+- [ ] Documentation complete
+
+## Future Enhancements
+
+- Grafana dashboards for workstation metrics
+- Alert tuning based on observed patterns
+- Additional collectors (e.g., temperature sensors if available)
+- Integration with morning-report skill for health status

plans/valiant-hugging-dahl.md

@@ -0,0 +1,171 @@
+# Plan: Improve pi50 (Control Plane) Resource Usage
+
+## Problem Summary
+
+pi50 (control plane) is running at **73% CPU / 81% memory** while worker nodes have significant headroom:
+- pi3: 7% CPU / 65% memory (but only 800MB RAM - memory constrained)
+- pi51: 18% CPU / 64% memory (8GB RAM - plenty of capacity)
+
+**Root cause**: pi50 has **NO control-plane taint**, so the scheduler treats it as a general worker node. It currently runs ~85 pods vs 38 on pi51.
+
+## Current State
+
+| Node | Role | CPUs | Memory | CPU Used | Mem Used | Pods |
+|------|------|------|--------|----------|----------|------|
+| pi50 | control-plane | 4 | 8GB | 73% | 81% | ~85 |
+| pi3 | worker | 4 | 800MB | 7% | 65% | 13 |
+| pi51 | worker | 4 | 8GB | 18% | 64% | 38 |
+
+## Recommended Approach
+
+### Option A: Add PreferNoSchedule Taint (Recommended)
+
+Add a soft taint to pi50 that tells the scheduler to prefer other nodes for new workloads, while allowing existing pods to remain.
+
+```bash
+kubectl taint nodes pi50 node-role.kubernetes.io/control-plane=:PreferNoSchedule
+```
+
+**Pros:**
+- Non-disruptive - existing pods continue running
+- New pods will prefer pi51/pi3
+- Gradual rebalancing as pods are recreated
+- Easy to remove if needed
+
+**Cons:**
+- Won't immediately reduce load
+- Existing pods stay where they are
+
+### Option B: Move Heavy Workloads Immediately
+
+Identify and relocate the heaviest workloads from pi50 to pi51:
+
+**Top CPU consumers on pi50:**
+1. ArgoCD application-controller (157m CPU, 364Mi) - should stay (manages cluster)
+2. Longhorn instance-manager (139m CPU, 707Mi) - must stay (storage)
+3. ai-stack workloads (ollama, litellm, open-webui, etc.)
+
+**Candidates to move to pi51:**
+- `ai-stack/ollama` - can run on any node with storage
+- `ai-stack/litellm` - stateless, can move
+- `ai-stack/open-webui` - can move
+- `ai-stack/claude-code`, `codex`, `gemini-cli`, `opencode` - can move
+- `minio` - can move (uses PVC)
+- `pihole2` - can move
+
+**Method**: Add `nodeSelector` or `nodeAffinity` to deployments:
+```yaml
+spec:
+  template:
+    spec:
+      nodeSelector:
+        kubernetes.io/hostname: pi51
+```
+
+Or use anti-affinity to avoid pi50:
+```yaml
+spec:
+  template:
+    spec:
+      affinity:
+        nodeAffinity:
+          preferredDuringSchedulingIgnoredDuringExecution:
+          - weight: 100
+            preference:
+              matchExpressions:
+              - key: node-role.kubernetes.io/control-plane
+                operator: DoesNotExist
+```
+
+### Option C: Combined Approach (Best)
+
+1. Add `PreferNoSchedule` taint to pi50 (prevents future imbalance)
+2. Immediately move 2-3 heaviest moveable workloads to pi51
+3. Let remaining workloads naturally migrate over time
+
+## Execution Steps
+
+### Step 1: Add taint to pi50
+```bash
+kubectl taint nodes pi50 node-role.kubernetes.io/control-plane=:PreferNoSchedule
+```
+
+### Step 2: Verify existing workloads still running
+```bash
+kubectl get pods -A -o wide --field-selector spec.nodeName=pi50 | grep -v Running
+```
+
+### Step 3: Move heavy ai-stack workloads (optional, for immediate relief)
+
+For each deployment to move, patch with node anti-affinity or selector:
+```bash
+kubectl patch deployment -n ai-stack ollama --type=merge -p '{"spec":{"template":{"spec":{"nodeSelector":{"kubernetes.io/hostname":"pi51"}}}}}'
+```
+
+Or delete pods to trigger rescheduling (if PreferNoSchedule taint is set):
+```bash
+kubectl delete pod -n ai-stack <pod-name>
+```
+
+### Step 4: Monitor
+```bash
+kubectl top nodes
+```
+
+## Workloads That MUST Stay on pi50
+
+- `kube-system/*` - Core cluster components
+- `longhorn-system/csi-*` - Storage controllers
+- `longhorn-system/longhorn-driver-deployer` - Storage management
+- `local-path-storage/*` - Local storage provisioner
+
+## Expected Outcome
+
+After changes:
+- pi50: ~50-60% CPU, ~65-70% memory (control plane + essential services)
+- pi51: ~40-50% CPU, ~70-75% memory (absorbs application workloads)
+- New pods prefer pi51 automatically
+
+## Risks
+
+- **Low**: PreferNoSchedule is a soft taint - pods with tolerations can still schedule on pi50
+- **Low**: Moving workloads may cause brief service interruption during pod recreation
+- **Note**: pi3 cannot absorb much due to 800MB RAM limit
+
+## Selected Approach: A + B (Combined)
+
+User selected combined approach:
+1. Add `PreferNoSchedule` taint to pi50
+2. Move heavy ai-stack workloads to pi51 immediately
+
+## Execution Plan
+
+### Phase 1: Add Taint
+```bash
+kubectl taint nodes pi50 node-role.kubernetes.io/control-plane=:PreferNoSchedule
+```
+
+### Phase 2: Move Heavy Workloads to pi51
+
+Target workloads (heaviest on pi50):
+- `ai-stack/ollama`
+- `ai-stack/open-webui`
+- `ai-stack/litellm`
+- `ai-stack/claude-code`
+- `ai-stack/codex`
+- `ai-stack/gemini-cli`
+- `ai-stack/opencode`
+- `ai-stack/searxng`
+- `minio/minio`
+
+Method: Delete pods to trigger rescheduling (taint will push them to pi51):
+```bash
+kubectl delete pod -n ai-stack -l app.kubernetes.io/name=ollama
+# etc for each workload
+```
+
+### Phase 3: Verify
+```bash
+kubectl top nodes
+kubectl get pods -A -o wide | grep -E "ollama|open-webui|litellm"
+```

plugins/known_marketplaces.json

@@ -5,7 +5,7 @@
       "repo": "anthropics/claude-plugins-official"
     },
     "installLocation": "/home/will/.claude/plugins/marketplaces/claude-plugins-official",
-    "lastUpdated": "2026-01-05T07:22:46.460Z"
+    "lastUpdated": "2026-01-05T20:44:45.874Z"
   },
   "superpowers-marketplace": {
     "source": {

reports/archive/2026-01-05.md

@@ -0,0 +1,27 @@
+# Morning Report - Mon Jan 05, 2026
+
+## 🌤 Weather
+Overcast, 44°F (feels 41°F), rain likely—bring umbrella ☔
+
+## 📧 Email
+⚠️ Could not fetch emails: No module named 'pydantic_core._pydantic_core'
+
+## 📅 Today
+⚠️ Could not fetch calendar: No module named 'pydantic_core._pydantic_core'
+
+## 📈 Stocks
+CRWV $77.64 ▼2.1% | NVDA $187.84 ▼0.5% | MSFT $473.50 ▲0.1%
+
+## 🖥 Infrastructure
+K8s: 🟡  |  Workstation: 🟢
+  └ K8s: 2 pods not running
+
+## 📰 Tech News
+• O-Ring Automation (Hacker News)
+• Novo Nordisk launches Wegovy weight-loss pill in US, triggering price war (Hacker News)
+• Refactoring – Not on the backlog (Hacker News)
+• It's hard to justify Tahoe icons (Lobsters)
+• Databases in 2025: A Year in Review (Lobsters)
+
+---
+*Generated: 2026-01-05 12:44:47 PT*

reports/morning.md

@@ -1,30 +1,27 @@
-# Morning Report - Sun Jan 04, 2026
+# Morning Report - Mon Jan 05, 2026
 
 ## 🌤 Weather
-Seattle: 51°F, Partly cloudy | High 52° Low 43°
+Overcast, 44°F (feels 41°F), rain likely—bring umbrella ☔
 
 ## 📧 Email
-15 unread
-  • Capital One | Quicks - Your requested balance summary
-  • Uber Receipts - [Personal] Your Saturday evening trip wi
-  • Experian - William, it's time to check your utiliza
-  • Experteer Search Age - William, we have 2 new opportunities for
-  • Chase - You can start your mortgage preapproval 
+⚠️ Could not fetch emails: No module named 'pydantic_core._pydantic_core'
 
 ## 📅 Today
-  • 2:00 PM - Seattle Saturday (SAM + QED + Lecosho) (5h)
+⚠️ Could not fetch calendar: No module named 'pydantic_core._pydantic_core'
 
 ## 📈 Stocks
-CRWV $79.32 +10.8% ▲  NVDA $188.85 +1.3% ▲  MSFT $472.94 -2.2% ▼
+CRWV $77.64 ▼2.1% | NVDA $187.84 ▼0.5% | MSFT $473.50 ▲0.1%
 
 ## 🖥 Infrastructure
-K8s: 🟢  |  Workstation: 🟢
+K8s: 🟡  |  Workstation: 🟢
+  └ K8s: 2 pods not running
 
 ## 📰 Tech News
-  • C-Sentinel: System prober that captures "system fingerprints... (Hacker News)
-  • Show HN: An LLM-Powered PCB Schematic Checker (Major Update) (Hacker News)
-  • Can I finally start using Wayland in 2026? (Lobsters)
-  • Saying goodbye to the servers at our physical datacenter (Lobsters)
+• O-Ring Automation (Hacker News)
+• Novo Nordisk launches Wegovy weight-loss pill in US, triggering price war (Hacker News)
+• Refactoring – Not on the backlog (Hacker News)
+• It's hard to justify Tahoe icons (Lobsters)
+• Databases in 2025: A Year in Review (Lobsters)
 
 ---
-*Generated: 2026-01-04 14:40:48 PT*
+*Generated: 2026-01-05 12:44:47 PT*

skills/morning-report/scripts/collectors/gtasks.py

@@ -29,17 +29,26 @@ TOKEN_PATH = Path.home() / ".gmail-mcp/tasks_token.json"
 CREDS_PATH = Path.home() / ".gmail-mcp/credentials.json"
 
 
-def get_credentials():
-    """Get or refresh Google credentials for Tasks API."""
+def get_credentials(force_reauth: bool = False):
+    """Get or refresh Google credentials for Tasks API.
+
+    If ``force_reauth`` is True, skip refresh and run a new OAuth flow.
+    This is useful when a stored refresh token is bound to a different
+    scope set and refresh keeps failing with invalid_scope.
+    """
     creds = None
 
     if TOKEN_PATH.exists():
         creds = Credentials.from_authorized_user_file(str(TOKEN_PATH), SCOPES)
 
-    if not creds or not creds.valid:
-        if creds and creds.expired and creds.refresh_token:
-            creds.refresh(Request())
-        else:
+    if not creds or not creds.valid or force_reauth:
+        if not force_reauth and creds and creds.expired and creds.refresh_token:
+            try:
+                creds.refresh(Request())
+            except Exception:
+                creds = None
+
+        if not creds or not creds.valid:
             if not CREDS_PATH.exists():
                 return None
             flow = InstalledAppFlow.from_client_secrets_file(str(CREDS_PATH), SCOPES)
@@ -168,7 +177,9 @@ if __name__ == "__main__":
 
     if "--auth" in sys.argv:
         print("Starting Tasks API authentication...")
-        creds = get_credentials()
+        # Force a fresh OAuth flow so we can recover from invalid_scope
+        # errors caused by stale refresh tokens.
+        creds = get_credentials(force_reauth=True)
         if creds:
             print(f"✅ Authentication successful! Token saved to {TOKEN_PATH}")
         else:

skills/rag-search/references/sources.json

@@ -9,6 +9,15 @@
       "glob": "**/*.md",
       "version": "main",
       "last_indexed": "2026-01-04T23:27:40.175671"
+    },
+    {
+      "id": "argocd",
+      "name": "ArgoCD Documentation",
+      "type": "git",
+      "url": "https://github.com/argoproj/argo-cd.git",
+      "path": "docs/",
+      "glob": "**/*.md",
+      "last_indexed": "2026-01-05T01:04:53.930441"
     }
   ]
 }

state/personal-assistant/history/index.json

@@ -224,6 +224,48 @@
       "ended": null,
       "summarized": false,
       "topics": []
+    },
+    {
+      "id": "2026-01-04_23-56-03",
+      "started": "2026-01-04T23:56:03-08:00",
+      "ended": null,
+      "summarized": false,
+      "topics": []
+    },
+    {
+      "id": "2026-01-05_00-28-11",
+      "started": "2026-01-05T00:28:11-08:00",
+      "ended": null,
+      "summarized": false,
+      "topics": []
+    },
+    {
+      "id": "2026-01-05_00-50-41",
+      "started": "2026-01-05T00:50:41-08:00",
+      "ended": null,
+      "summarized": false,
+      "topics": []
+    },
+    {
+      "id": "2026-01-05_00-51-05",
+      "started": "2026-01-05T00:51:05-08:00",
+      "ended": null,
+      "summarized": false,
+      "topics": []
+    },
+    {
+      "id": "2026-01-05_12-10-41",
+      "started": "2026-01-05T12:10:41-08:00",
+      "ended": null,
+      "summarized": false,
+      "topics": []
+    },
+    {
+      "id": "2026-01-05_12-11-40",
+      "started": "2026-01-05T12:11:40-08:00",
+      "ended": null,
+      "summarized": false,
+      "topics": []
     }
   ]
 }