Initial commit: Claude Code config and K8s agent orchestrator design

- Add .gitignore for logs, caches, credentials, and history - Add K8s agent orchestrator design document - Include existing Claude Code settings and plugin configs 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
2025-12-26 11:16:07 -08:00
commit 216a95cec4
9 changed files with 1116 additions and 0 deletions
--- a/.gitignore
+++ b/.gitignore
@@ -0,0 +1,37 @@
+# Logs
+logs/
+
+# Secrets and credentials
+*.key
+*.pem
+*.secret
+credentials/
+.credentials.json
+
+# Cache and state
+.cache/
+stats-cache.json
+statsig/
+
+# History and debug
+history.jsonl
+file-history/
+shell-snapshots/
+debug/
+
+# Plugin caches (contain embedded git repos)
+plugins/cache/
+plugins/marketplaces/
+
+# Local settings
+settings.local.json
+
+# Conversation history (private/large)
+projects/
+
+# Temporary files
+*.tmp
+*.swp
+
+# Todos (managed by Claude Code)
+todos/
--- a/docs/plans/2025-12-26-agent-orchestrator-brainstorm.md
+++ b/docs/plans/2025-12-26-agent-orchestrator-brainstorm.md
@@ -0,0 +1,85 @@
+# Agent Orchestrator System - Brainstorming Notes
+
+## Overview
+User-level Claude Code agent system with orchestrator + specialized subagents + workflows.
+Location: `~/.claude/`
+
+## Target Domains (for future expansion)
+- **A) DevOps/Infrastructure** - PRIMARY - Raspberry Pi K8s cluster management
+- B) Software development - Code generation, refactoring, testing
+- C) Research & analysis - Information gathering, summarizing
+- D) Personal productivity - Files, notes, tasks, schedules
+- E) Multi-domain - General-purpose tasks
+
+## Primary Use Case
+- Raspberry Pi Kubernetes cluster management
+- App deployment to the cluster
+- K8s distribution: **k0s**
+- Deployment method: **GitOps with ArgoCD**
+
+## Cluster Hardware
+| Node | Hardware | RAM | Role |
+|------|----------|-----|------|
+| Node 1 | Raspberry Pi 5 | 8GB | Control plane + Worker |
+| Node 2 | Raspberry Pi 5 | 8GB | Worker |
+| Node 3 | Raspberry Pi 3B+ | 1GB | Worker (tainted, tolerations required) |
+
+**Pi 3 node**: Reserved for lightweight workloads only. Good candidate for dashboard deployment.
+**Architecture**: All nodes run arm64 (64-bit OS).
+
+## Workloads
+- Self-hosted services (home automation, media, personal tools)
+- Development/testing environments
+- Infrastructure services (monitoring, logging, databases)
+
+## Agent Tasks (priority order)
+1. **Cluster health monitoring** - Detect issues, diagnose, suggest/apply fixes (TOP PRIORITY)
+2. Deployment management - Create/update deployments, ArgoCD sync, rollbacks
+3. Resource management - Scaling, allocation, cleanup
+4. App lifecycle - End-to-end "I want to run X" to deployed
+5. Incident response - Alerting, investigation, remediation
+
+## Autonomy Model
+- **Tiered autonomy**: Safe actions auto-apply, risky actions require confirmation
+- Safe: restart pod, scale replicas, clear completed jobs
+- Risky: delete PVC, modify configs, node operations
+
+## Interaction Methods
+- **Terminal/CLI** - Primary interaction via Claude Code (also fallback when cluster is down)
+- **Dashboard/UI** - Web interface deployed on cluster via ArgoCD
+- **Push notifications** - Future consideration (Discord/Slack/Telegram)
+
+## Infrastructure Stack
+- Monitoring: **Prometheus + Alertmanager + Grafana**
+- GitOps repo: **Self-hosted Gitea/Forgejo**
+- Workflow triggers: **Scheduled + Event-driven (Alertmanager webhooks)**
+
+## Implementation Approach
+**Phase 1**: Claude Code skills + custom subagent types in `~/.claude/`
+**Phase 2 (later)**: Add SDK-based daemon for background automation
+
+## Subagents
+1. **k8s-diagnostician** - Cluster health, pod/node status, resource utilization, log analysis
+2. **argocd-operator** - App sync, deployments, rollbacks, GitOps operations
+3. **prometheus-analyst** - Query metrics, analyze trends, interpret alerts
+4. **git-operator** - Commit manifests, create PRs in Gitea, manage GitOps repo
+
+## Workflow Definitions
+- **YAML** - Complex workflows with branching, conditions, multi-step
+- **Markdown** - Simple workflows, prose-like descriptions
+
+## CLI Tools Available
+- kubectl
+- argocd CLI
+- k0sctl
+
+## Model Assignment
+- **Default**: Orchestrator = Opus, Subagents = Sonnet
+- **Override levels**:
+  1. Per-workflow: specify model in workflow YAML
+  2. Per-step: specify model for individual workflow steps
+  3. Dynamic: Orchestrator can downgrade/upgrade model per-delegation based on task complexity
+- **Cost optimization**: Orchestrator evaluates task complexity and selects appropriate model
+  - Simple queries (get status, list) → Haiku
+  - Standard operations (analyze, diagnose) → Sonnet
+  - Complex reasoning (root cause, multi-factor decisions) → Opus
--- a/docs/plans/2025-12-26-k8s-agent-orchestrator-design.md
+++ b/docs/plans/2025-12-26-k8s-agent-orchestrator-design.md
@@ -0,0 +1,482 @@
+# K8s Agent Orchestrator System - Design Document
+
+## Overview
+
+A user-level Claude Code agent system for autonomous Kubernetes cluster management. The system consists of an orchestrator agent that delegates to specialized subagents, with workflow definitions for common operations and a tiered autonomy model.
+
+**Location**: `~/.claude/`
+**Primary Domain**: DevOps/Infrastructure
+**Target**: Raspberry Pi k0s cluster
+
+---
+
+## Cluster Environment
+
+### Hardware
+
+| Node | Hardware | RAM | Role |
+|------|----------|-----|------|
+| Node 1 | Raspberry Pi 5 | 8GB | Control plane + Worker |
+| Node 2 | Raspberry Pi 5 | 8GB | Worker |
+| Node 3 | Raspberry Pi 3B+ | 1GB | Worker (tainted, tolerations required) |
+
+- **Architecture**: All nodes run arm64 (64-bit OS)
+- **Pi 3 node**: Reserved for lightweight workloads only
+
+### Stack
+
+| Component | Technology |
+|-----------|------------|
+| K8s Distribution | k0s |
+| GitOps | ArgoCD |
+| Git Hosting | Self-hosted Gitea/Forgejo |
+| Monitoring | Prometheus + Alertmanager + Grafana |
+
+### CLI Tools Available
+
+- `kubectl`
+- `argocd`
+- `k0sctl`
+
+---
+
+## Architecture
+
+### Three-Layer Design
+
+```
+┌─────────────────────────────────────────────────────────────┐
+│                     User Interface                          │
+│              Terminal (CLI)  |  Dashboard (Web)             │
+└─────────────────────┬───────────────────┬───────────────────┘
+                      │                   │
+┌─────────────────────▼───────────────────▼───────────────────┐
+│                   Orchestrator Layer                         │
+│                    k8s-orchestrator                          │
+│         (Opus - complex reasoning, task delegation)          │
+└─────────────────────┬───────────────────────────────────────┘
+                      │ delegates to
+┌─────────────────────▼───────────────────────────────────────┐
+│                   Specialist Layer                           │
+│  ┌─────────────┐ ┌─────────────┐ ┌─────────────┐ ┌─────────┐│
+│  │k8s-         │ │argocd-      │ │prometheus-  │ │git-     ││
+│  │diagnostician│ │operator     │ │analyst      │ │operator ││
+│  │(Sonnet)     │ │(Sonnet)     │ │(Sonnet)     │ │(Sonnet) ││
+│  └─────────────┘ └─────────────┘ └─────────────┘ └─────────┘│
+└─────────────────────────────────────────────────────────────┘
+                      │ defined by
+┌─────────────────────▼───────────────────────────────────────┐
+│                   Workflow Layer                             │
+│            YAML (complex)  |  Markdown (simple)              │
+└─────────────────────────────────────────────────────────────┘
+```
+
+### Directory Structure
+
+```
+~/.claude/
+├── settings.json              # Agent definitions, autonomy rules
+├── agents/
+│   ├── k8s-orchestrator.md    # Orchestrator prompt
+│   ├── k8s-diagnostician.md   # Cluster diagnostics specialist
+│   ├── argocd-operator.md     # GitOps operations specialist
+│   ├── prometheus-analyst.md  # Metrics analysis specialist
+│   └── git-operator.md        # Git/Gitea operations specialist
+├── workflows/
+│   ├── health/
+│   │   ├── cluster-health-check.yaml
+│   │   └── node-pressure-response.yaml
+│   ├── deploy/
+│   │   ├── deploy-app.md
+│   │   └── rollback-app.yaml
+│   └── incidents/
+│       └── pod-crashloop.yaml
+├── skills/
+│   ├── cluster-status.md
+│   ├── deploy.md
+│   ├── diagnose.md
+│   ├── rollback.md
+│   └── workflow.md
+├── logs/
+│   ├── actions/               # Action audit trail
+│   └── workflows/             # Workflow execution logs
+└── docs/plans/
+```
+
+---
+
+## Subagent Definitions
+
+### settings.json
+
+```json
+{
+  "agents": {
+    "k8s-orchestrator": {
+      "model": "opus",
+      "promptFile": "agents/k8s-orchestrator.md"
+    },
+    "k8s-diagnostician": {
+      "model": "sonnet",
+      "promptFile": "agents/k8s-diagnostician.md"
+    },
+    "argocd-operator": {
+      "model": "sonnet",
+      "promptFile": "agents/argocd-operator.md"
+    },
+    "prometheus-analyst": {
+      "model": "sonnet",
+      "promptFile": "agents/prometheus-analyst.md"
+    },
+    "git-operator": {
+      "model": "sonnet",
+      "promptFile": "agents/git-operator.md"
+    }
+  },
+  "autonomy": {
+    "safe_actions": ["get", "describe", "logs", "list", "top", "diff"],
+    "confirm_actions": ["delete", "patch", "edit", "scale", "rollout", "apply"],
+    "forbidden_actions": ["drain", "cordon", "delete node", "reset"]
+  }
+}
+```
+
+### Subagent Responsibilities
+
+| Agent | Scope | Tools |
+|-------|-------|-------|
+| **k8s-orchestrator** | Task analysis, delegation, decision making | All (via delegation) |
+| **k8s-diagnostician** | Cluster health, pod/node status, logs | kubectl, log tools |
+| **argocd-operator** | App sync, deployments, rollbacks | argocd CLI, kubectl |
+| **prometheus-analyst** | Metrics, alerts, trends | PromQL, Prometheus API |
+| **git-operator** | Manifest commits, PRs, GitOps repo | git, Gitea API |
+
+---
+
+## Model Assignment
+
+### Defaults
+
+- **Orchestrator**: Opus (complex reasoning, task delegation)
+- **Subagents**: Sonnet (standard operations)
+
+### Override Levels
+
+1. **Per-workflow**: Specify in workflow YAML
+2. **Per-step**: Specify for individual workflow steps
+3. **Dynamic**: Orchestrator selects based on task complexity
+
+### Dynamic Model Selection (Orchestrator Logic)
+
+| Task Complexity | Model | Examples |
+|-----------------|-------|----------|
+| Simple | Haiku | Get status, list resources, log tail |
+| Standard | Sonnet | Analyze logs, diagnose issues, sync apps |
+| Complex | Opus | Root cause analysis, cascading failures, trade-off decisions |
+
+**Delegation syntax:**
+```markdown
+Delegate to k8s-diagnostician (haiku):
+  Task: Get current node status
+
+Delegate to prometheus-analyst (sonnet):
+  Task: Analyze memory trends for namespace "prod" over last 24h
+
+Delegate to k8s-diagnostician (opus):
+  Task: Investigate cascading failure across multiple services
+```
+
+---
+
+## Workflow Definitions
+
+### YAML Workflows (Complex)
+
+```yaml
+name: cluster-health-check
+description: Comprehensive cluster health assessment
+model: sonnet  # optional default override
+trigger:
+  - schedule: "0 */6 * * *"  # every 6 hours
+  - manual: true
+
+steps:
+  - agent: k8s-diagnostician
+    model: haiku  # simple status check
+    task: Check node status and resource pressure
+
+  - agent: prometheus-analyst
+    task: Query for anomalies in last 6 hours
+
+  - agent: argocd-operator
+    model: haiku
+    task: Check all apps sync status
+
+  - agent: k8s-orchestrator
+    task: Summarize findings and recommend actions
+    confirm_if: actions_proposed
+```
+
+### Markdown Workflows (Simple)
+
+```markdown
+# Deploy New App
+
+When asked to deploy a new application:
+
+1. Ask git-operator to create the manifest structure in the GitOps repo
+2. Ask argocd-operator to create and sync the ArgoCD application
+3. Ask k8s-diagnostician to verify pods are running
+4. Report deployment status
+```
+
+### Incident Response Workflow Example
+
+```yaml
+name: pod-crashloop-remediation
+trigger:
+  type: alert
+  match:
+    alertname: KubePodCrashLooping
+
+steps:
+  - name: diagnose
+    agent: k8s-diagnostician
+    action: get-pod-status
+    inputs:
+      namespace: "{{ alert.labels.namespace }}"
+      pod: "{{ alert.labels.pod }}"
+
+  - name: check-logs
+    agent: k8s-diagnostician
+    action: analyze-logs
+    inputs:
+      pod: "{{ steps.diagnose.pod }}"
+      lines: 100
+
+  - name: decide-action
+    condition: "{{ steps.check-logs.cause == 'oom' }}"
+    branches:
+      true:
+        agent: argocd-operator
+        action: update-resources
+        confirm: true  # risky action
+      false:
+        agent: k8s-diagnostician
+        action: restart-pod
+        confirm: false  # safe action
+
+  - name: notify
+    action: report
+    outputs:
+      - summary
+      - actions-taken
+```
+
+---
+
+## Autonomy Model
+
+### Tiered Autonomy
+
+| Action Type | Behavior | Examples |
+|-------------|----------|----------|
+| **Safe** | Auto-execute, log action | get, describe, logs, list, restart pod |
+| **Confirm** | Require user approval | delete, patch, scale, apply, modify config |
+| **Forbidden** | Reject with explanation | drain, cordon, delete node |
+
+### Confirmation Flow
+
+```
+1. Agent proposes action with rationale
+2. System checks action against autonomy rules
+3. If safe → execute immediately, log action
+4. If confirm → present to user (CLI prompt or dashboard queue)
+5. If forbidden → reject with explanation
+```
+
+### Per-Workflow Overrides
+
+```yaml
+name: emergency-pod-restart
+autonomy:
+  auto_approve:
+    - restart_pod
+    - scale_replicas
+  always_confirm:
+    - delete_pvc
+```
+
+### Action Logging
+
+```
+~/.claude/logs/actions/2025-12-26-actions.jsonl
+```
+
+Each entry includes:
+- Timestamp
+- Agent
+- Action
+- Inputs
+- Outcome
+- Approval type (auto/user-confirmed)
+
+---
+
+## Skills (User Entry Points)
+
+| Skill | Command | Purpose |
+|-------|---------|---------|
+| cluster-status | `/cluster-status` | Quick health overview |
+| deploy | `/deploy <app>` | Deploy or update an app |
+| diagnose | `/diagnose <issue>` | Investigate a problem |
+| rollback | `/rollback <app>` | Revert to previous version |
+| workflow | `/workflow <name>` | Run a named workflow |
+
+### Example Skill: cluster-status.md
+
+```markdown
+# Cluster Status
+
+Invoke the k8s-orchestrator to provide a quick health overview.
+
+## Steps
+1. Delegate to k8s-diagnostician: get node status
+2. Delegate to prometheus-analyst: check for active alerts
+3. Delegate to argocd-operator: list out-of-sync apps
+4. Summarize in a concise table
+
+## Output Format
+- Node health: table
+- Active alerts: bullet list
+- ArgoCD status: table
+- Recommendations: if any issues found
+```
+
+---
+
+## Interaction Methods
+
+### Terminal/CLI
+
+- Primary interaction via Claude Code
+- Fallback when cluster is unavailable
+- Use skills to invoke workflows
+
+### Dashboard (Web UI)
+
+- Deployed on cluster (Pi 3 node)
+- Views: Status, Pending Confirmations, History, Workflows
+- Approve/reject risky actions
+
+### Push Notifications (Future)
+
+- Discord, Slack, or Telegram integration
+- Alert on issues requiring attention
+
+---
+
+## Dashboard Specification
+
+### Tech Stack
+
+- **Backend**: Go binary (single static binary, embedded assets)
+- **Storage**: SQLite or flat JSON files
+- **Resources**: Minimal footprint for Pi 3
+
+### Deployment
+
+```yaml
+apiVersion: apps/v1
+kind: Deployment
+metadata:
+  name: k8s-agent-dashboard
+spec:
+  replicas: 1
+  template:
+    spec:
+      containers:
+        - name: dashboard
+          image: k8s-agent-dashboard:latest
+          resources:
+            requests:
+              memory: "32Mi"
+              cpu: "10m"
+            limits:
+              memory: "64Mi"
+              cpu: "100m"
+      tolerations:
+        - key: "node-type"
+          operator: "Equal"
+          value: "pi3"
+          effect: "NoSchedule"
+      nodeSelector:
+        kubernetes.io/arch: arm64
+```
+
+### Views
+
+| View | Description |
+|------|-------------|
+| Status | Current cluster health, active alerts, ArgoCD sync state |
+| Pending | Actions awaiting confirmation with approve/reject buttons |
+| History | Recent actions taken, filterable by agent/workflow |
+| Workflows | List of defined workflows, manual trigger capability |
+
+---
+
+## Implementation Phases
+
+### Phase 1: Core Agent System
+
+**Deliverables:**
+- `~/.claude/` directory structure
+- Orchestrator and 4 subagent prompt files
+- `settings.json` with agent configurations
+- 3-4 essential workflows (cluster-health, deploy, diagnose)
+- Core skills (/cluster-status, /deploy, /diagnose)
+
+**Validation:**
+- Manual CLI invocation
+- Test each subagent independently
+- Run health check workflow end-to-end
+
+### Phase 2: Dashboard
+
+**Deliverables:**
+- Go-based dashboard application
+- Kubernetes manifests for Pi 3 deployment
+- Pending confirmations queue
+- Action history view
+- Approval flow integration
+
+### Phase 3: Automation
+
+**Deliverables:**
+- Scheduled workflow execution
+- Alertmanager webhook integration
+- Expanded incident response workflows
+
+### Phase 4: Expansion (Future)
+
+**Potential additions:**
+- Push notifications (Discord/Telegram)
+- Additional domains (development, research, productivity)
+- SDK-based background daemon for true autonomy
+
+---
+
+## Future Domain Expansion
+
+The system is designed to expand beyond DevOps:
+
+| Domain | Use Cases |
+|--------|-----------|
+| Software Development | Code generation, refactoring, testing across repos |
+| Research & Analysis | Information gathering, summarizing, recommendations |
+| Personal Productivity | File management, notes, task tracking |
+
+New domains would add:
+- Additional subagents with specialized prompts
+- Domain-specific workflows
+- New skills for user invocation
--- a/plans/cosmic-frolicking-compass.md
+++ b/plans/cosmic-frolicking-compass.md
@@ -0,0 +1,142 @@
+# Plan: Fix Zed Slow Launch and Performance on Hyprland
+
+## Problem Analysis
+
+**Original Request:** Compile Zed with OpenGL support instead of Vulkan for Intel HD Graphics 4000
+
+**Actual Issue Discovered:** Zed is using X11/XWayland instead of native Wayland on Hyprland, causing:
+- 15+ second launch times
+- Sluggish runtime performance
+- The hardware (Intel HD Graphics 4000) is properly supported and works fine on Gnome
+
+**System Information:**
+- Binary: `/usr/lib/zed/zed-editor` (Arch package v0.213.4-1)
+- Command: `zeditor`
+- Hyprland version: 0.52.1
+- Mesa version: 25.2.7-arch1.1
+- Environment: Both `WAYLAND_DISPLAY=wayland-1` and `DISPLAY=:1` are set
+
+**Evidence from logs** (`~/.local/share/zed/logs/Zed.log`):
+```
+2025-12-12T22:12:02-08:00 INFO  [gpui::platform::linux::x11::window] Using Visual { id: 112, colormap: 0, depth: 32 }
+2025-12-12T22:12:02-08:00 INFO  [gpui::platform::linux::x11::window] x11: no compositor present, falling back to server-side window decorations
+2025-12-12T22:12:02-08:00 ERROR [gpui::platform::linux::x11::client] XIMClientError: Can't read xim message: Invalid Data ErrorCode: 0
+```
+
+## Root Cause
+
+**Mystery Identified:** Despite both environment variables being correctly set (`WAYLAND_DISPLAY=wayland-1` and `DISPLAY=:1`), Zed is still choosing X11.
+
+Based on the code in `crates/gpui/src/platform.rs` (lines 139-164), Zed should prioritize Wayland when `WAYLAND_DISPLAY` is set. The fact that it's using X11 despite this suggests:
+
+**Most Likely:** The Arch package (v0.213.4-1) was compiled **without the `wayland` Cargo feature enabled**, causing the binary to only support X11 even when Wayland is available.
+
+This is supported by:
+- The platform selection code has `#[cfg(feature = "wayland")]` guards
+- If Wayland feature is disabled at compile time, `guess_compositor()` will always return "X11"
+- A similar issue was documented in Arch forums ([thread](https://bbs.archlinux.org/viewtopic.php?id=299290))
+
+## Recommended Solution
+
+**Compile Zed from source with Wayland support enabled.** The Arch package appears to lack Wayland support at compile time.
+
+### Step 1: Build Zed with Wayland Support
+
+From the repository root (`/home/will/repo/zed`):
+
+```bash
+# Clean any previous builds (optional)
+cargo clean
+
+# Build with Wayland feature explicitly enabled
+cargo build --release --features gpui/wayland
+
+# Or build the full zed binary with default features (which includes wayland)
+cargo build --release -p zed
+```
+
+**Build time estimate:** 20-40 minutes on first build (depending on CPU)
+
+### Step 2: Install the Binary
+
+```bash
+# Create installation directory if needed
+mkdir -p ~/.local/bin
+
+# Copy the binary
+cp target/release/zed ~/.local/bin/zed-wayland
+
+# Or replace the system zeditor
+sudo cp target/release/zed /usr/local/bin/zeditor
+```
+
+### Step 3: Verify Wayland Support
+
+```bash
+# Launch and check logs
+~/.local/bin/zed-wayland
+grep -E "wayland|x11" ~/.local/share/zed/logs/Zed.log | tail -5
+```
+
+Expected output should show Wayland initialization, NOT X11 messages.
+
+## Alternative: Install from AUR or Use Different Package
+
+If you don't want to compile from source, consider:
+
+1. **Install `zed-git` from AUR** (may have Wayland support):
+   ```bash
+   paru -S zed-git  # or yay -S zed-git
+   ```
+
+2. **File a bug report with Arch** to request Wayland support in the official package
+
+3. **Wait for official Arch package update** to include Wayland support
+
+## Why NOT OpenGL/GLES?
+
+The original request was to compile with OpenGL instead of Vulkan. **This is unnecessary** because:
+- Your Intel HD Graphics 4000 supports Vulkan (working fine on Gnome)
+- The slowness is from X11/XWayland overhead, NOT the graphics backend
+- Mesa drivers are properly installed (Vulkan, OpenGL 4.2, OpenGL ES 3.0 all working)
+- Switching to GLES won't fix the X11 vs Wayland issue
+
+**GLES compilation would only be needed if:**
+- Vulkan completely fails (`vkcube` doesn't work)
+- Zed shows "NoSupportedDeviceFound" error
+- You get GPU-related crashes
+
+## Expected Outcome
+
+After compiling with Wayland support and running the new binary:
+- **Launch time:** Should match Gnome performance (~2 seconds)
+- **Runtime performance:** Smooth, no sluggishness
+- **Logs:** Will show Wayland client initialization instead of X11
+
+## Build Requirements
+
+The system already has all necessary dependencies:
+- Rust toolchain (rustup)
+- Wayland development libraries (installed)
+- Build tools (gcc, clang, cmake, etc.)
+- Vulkan and Mesa drivers (working)
+
+From `crates/gpui/Cargo.toml` (lines 40-59), the `wayland` feature depends on:
+- `wayland-client`, `wayland-cursor`, `wayland-protocols` (all available on Arch)
+- `blade-graphics` (already in use for Vulkan)
+- Font libraries (cosmic-text, font-kit) - already installed
+
+## Critical Files for Reference
+
+- `crates/gpui/Cargo.toml:20` - Default features include "wayland" and "x11"
+- `crates/gpui/Cargo.toml:40-59` - Wayland feature dependencies
+- `crates/gpui/src/platform.rs:101-164` - Platform selection logic
+- `crates/gpui/src/platform/linux/wayland/client.rs` - Wayland client implementation
+- `crates/gpui/src/platform/linux/x11/client.rs` - X11 client implementation
+
+## Implementation Steps
+
+1. **Build from source** with Wayland support (20-40 min)
+2. **Install the binary** to ~/.local/bin or /usr/local/bin
+3. **Test launch** and verify Wayland is being used via logs
+4. **Confirm performance** matches Gnome experience
--- a/plans/elegant-prancing-allen.md
+++ b/plans/elegant-prancing-allen.md
@@ -0,0 +1,108 @@
+# Vulkan Installation Verification Plan
+
+## Goal
+Verify that Vulkan is correctly installed and functional on the system, and determine whether the Mesa warning about incomplete Ivy Bridge support is a concern.
+
+## Background Context
+
+**Hardware**: Intel HD Graphics 4000 (Ivy Bridge) - circa 2012
+**Current Status**:
+- Vulkan 1.4.328 is installed
+- `vulkaninfo` runs successfully
+- Mesa driver shows warning: "MESA-INTEL: warning: Ivy Bridge Vulkan support is incomplete"
+- Zed editor launches successfully despite the warning
+
+## Understanding the Warning
+
+The "Ivy Bridge Vulkan support is incomplete" warning is **expected behavior** for your hardware:
+
+1. **Why it appears**: Intel HD Graphics 4000 is a 3rd-generation (Ivy Bridge) GPU from 2012, before Vulkan was standardized
+2. **What it means**: Mesa provides best-effort Vulkan support through a compatibility layer, but not all Vulkan features are hardware-accelerated
+3. **Is it a problem?**: Generally no - applications will either:
+   - Use the incomplete Vulkan support (works for most tasks)
+   - Fall back to OpenGL automatically
+   - Use the software renderer (llvmpipe) as a last resort
+
+## Verification Approach
+
+### Step 1: Verify Vulkan Device Detection ✅
+Diagnostic results confirm:
+- ✅ Vulkan loader is installed (`vulkaninfo` successful)
+- ✅ GPU is detected (Intel HD Graphics 4000 IVB GT2)
+- ✅ Both hardware and software renderers available:
+  - Hardware: Intel HD Graphics 4000 (using intel_icd.x86_64.json)
+  - Software fallback: llvmpipe (LLVM 21.1.5, 256 bits)
+- ✅ Vulkan ICD files present:
+  - intel_icd.x86_64.json (for Ivy Bridge/Broadwell)
+  - intel_hasvk_icd.x86_64.json (for Haswell+)
+  - lvp_icd.x86_64.json (lavapipe software renderer)
+  - nouveau_icd.x86_64.json (Nouveau open-source driver)
+  - nvidia_icd.json (NVIDIA proprietary driver)
+
+### Step 2: Test Vulkan Functionality
+Run simple Vulkan test applications to verify:
+- Basic rendering works
+- Applications can create Vulkan instances and devices
+- The warning doesn't prevent normal operation
+
+Commands to run:
+```bash
+# Verify Vulkan ICD (Installable Client Driver) files
+ls -la /usr/share/vulkan/icd.d/
+
+# Check which Vulkan layers are available
+vulkaninfo --summary | grep -A 5 "Layer"
+
+# Test with a simple Vulkan application (if vkcube is installed)
+vkcube || echo "vkcube not installed, will try alternative"
+
+# Check if Zed can actually use Vulkan
+VK_ICD_FILENAMES=/usr/share/vulkan/icd.d/intel_icd.x86_64.json /usr/lib/zed/zed-editor --version
+```
+
+### Step 3: Verify Mesa Driver Status
+Confirm Mesa drivers are up to date:
+```bash
+# Check Mesa version
+glxinfo | grep "OpenGL version"
+
+# Verify Intel driver is loaded
+lsmod | grep i915
+
+# Check Vulkan driver info
+vulkaninfo | grep -A 10 "GPU id.*Intel"
+```
+
+### Step 4: Document Findings
+
+Create a summary report showing:
+1. Vulkan is installed: ✅ (version 1.4.328)
+2. GPU is detected: ✅ (Intel HD Graphics 4000 + llvmpipe fallback)
+3. Warning is expected: ✅ (Ivy Bridge has incomplete Vulkan support by design)
+4. Applications work: ✅/❌ (to be verified)
+
+## Expected Outcome
+
+**Vulkan is correctly installed** if:
+- `vulkaninfo` runs without errors (✅ confirmed)
+- At least one Vulkan device is available (✅ Intel HD 4000 + llvmpipe)
+- Applications launch and run (✅ Zed editor works)
+
+**The warning is harmless** because:
+- It's informational, not an error
+- Applications handle this gracefully by:
+  - Using available Vulkan features
+  - Falling back to OpenGL/software rendering
+  - Automatically selecting the best available renderer
+
+## Recommendations
+
+1. **No action needed** - Vulkan is working as well as it can on Ivy Bridge hardware
+2. **Optional**: Set environment variable to suppress the warning if it's annoying:
+   ```bash
+   export INTEL_DEBUG=nowarn
+   ```
+3. **Optional**: For better graphics performance, consider using OpenGL mode in applications when available (Ivy Bridge's OpenGL support is more mature than Vulkan)
+
+## Files to Review
+None - this is a system-level verification task, not a code modification.
--- a/plugins/install-counts-cache.json
+++ b/plugins/install-counts-cache.json
@@ -0,0 +1,186 @@
+{
+  "version": 1,
+  "fetchedAt": "2025-12-26T18:14:58.883Z",
+  "counts": [
+    {
+      "plugin": "context7@claude-plugins-official",
+      "unique_installs": 42693
+    },
+    {
+      "plugin": "frontend-design@claude-plugins-official",
+      "unique_installs": 42607
+    },
+    {
+      "plugin": "github@claude-plugins-official",
+      "unique_installs": 24946
+    },
+    {
+      "plugin": "serena@claude-plugins-official",
+      "unique_installs": 24069
+    },
+    {
+      "plugin": "feature-dev@claude-plugins-official",
+      "unique_installs": 21182
+    },
+    {
+      "plugin": "code-review@claude-plugins-official",
+      "unique_installs": 18350
+    },
+    {
+      "plugin": "commit-commands@claude-plugins-official",
+      "unique_installs": 14203
+    },
+    {
+      "plugin": "atlassian@claude-plugins-official",
+      "unique_installs": 13865
+    },
+    {
+      "plugin": "supabase@claude-plugins-official",
+      "unique_installs": 13573
+    },
+    {
+      "plugin": "security-guidance@claude-plugins-official",
+      "unique_installs": 11942
+    },
+    {
+      "plugin": "agent-sdk-dev@claude-plugins-official",
+      "unique_installs": 10940
+    },
+    {
+      "plugin": "figma@claude-plugins-official",
+      "unique_installs": 10505
+    },
+    {
+      "plugin": "pr-review-toolkit@claude-plugins-official",
+      "unique_installs": 10481
+    },
+    {
+      "plugin": "playwright@claude-plugins-official",
+      "unique_installs": 8098
+    },
+    {
+      "plugin": "Notion@claude-plugins-official",
+      "unique_installs": 6541
+    },
+    {
+      "plugin": "explanatory-output-style@claude-plugins-official",
+      "unique_installs": 6504
+    },
+    {
+      "plugin": "typescript-lsp@claude-plugins-official",
+      "unique_installs": 6463
+    },
+    {
+      "plugin": "ralph-wiggum@claude-plugins-official",
+      "unique_installs": 5526
+    },
+    {
+      "plugin": "linear@claude-plugins-official",
+      "unique_installs": 5384
+    },
+    {
+      "plugin": "plugin-dev@claude-plugins-official",
+      "unique_installs": 5202
+    },
+    {
+      "plugin": "laravel-boost@claude-plugins-official",
+      "unique_installs": 5100
+    },
+    {
+      "plugin": "hookify@claude-plugins-official",
+      "unique_installs": 4831
+    },
+    {
+      "plugin": "learning-output-style@claude-plugins-official",
+      "unique_installs": 4567
+    },
+    {
+      "plugin": "sentry@claude-plugins-official",
+      "unique_installs": 4012
+    },
+    {
+      "plugin": "greptile@claude-plugins-official",
+      "unique_installs": 3812
+    },
+    {
+      "plugin": "pyright-lsp@claude-plugins-official",
+      "unique_installs": 3413
+    },
+    {
+      "plugin": "gitlab@claude-plugins-official",
+      "unique_installs": 3280
+    },
+    {
+      "plugin": "slack@claude-plugins-official",
+      "unique_installs": 3153
+    },
+    {
+      "plugin": "vercel@claude-plugins-official",
+      "unique_installs": 2748
+    },
+    {
+      "plugin": "gopls-lsp@claude-plugins-official",
+      "unique_installs": 1539
+    },
+    {
+      "plugin": "firebase@claude-plugins-official",
+      "unique_installs": 1379
+    },
+    {
+      "plugin": "rust-analyzer-lsp@claude-plugins-official",
+      "unique_installs": 1264
+    },
+    {
+      "plugin": "csharp-lsp@claude-plugins-official",
+      "unique_installs": 1138
+    },
+    {
+      "plugin": "php-lsp@claude-plugins-official",
+      "unique_installs": 1031
+    },
+    {
+      "plugin": "stripe@claude-plugins-official",
+      "unique_installs": 999
+    },
+    {
+      "plugin": "swift-lsp@claude-plugins-official",
+      "unique_installs": 942
+    },
+    {
+      "plugin": "jdtls-lsp@claude-plugins-official",
+      "unique_installs": 911
+    },
+    {
+      "plugin": "clangd-lsp@claude-plugins-official",
+      "unique_installs": 880
+    },
+    {
+      "plugin": "asana@claude-plugins-official",
+      "unique_installs": 712
+    },
+    {
+      "plugin": "lua-lsp@claude-plugins-official",
+      "unique_installs": 500
+    },
+    {
+      "plugin": "figma-mcp@claude-plugins-official",
+      "unique_installs": 90
+    },
+    {
+      "plugin": "example-plugin@claude-plugins-official",
+      "unique_installs": 29
+    },
+    {
+      "plugin": "typescript-native-lsp@claude-plugins-official",
+      "unique_installs": 1
+    },
+    {
+      "plugin": "bun-typescript@claude-plugins-official",
+      "unique_installs": 1
+    },
+    {
+      "plugin": "document-skills@claude-plugins-official",
+      "unique_installs": 1
+    }
+  ]
+}
--- a/plugins/installed_plugins.json
+++ b/plugins/installed_plugins.json
@@ -0,0 +1,48 @@
+{
+  "version": 2,
+  "plugins": {
+    "frontend-design@claude-plugins-official": [
+      {
+        "scope": "user",
+        "installPath": "/home/will/.claude/plugins/cache/claude-plugins-official/frontend-design/6d3752c000e2",
+        "version": "6d3752c000e2",
+        "installedAt": "2025-12-24T19:08:12.422Z",
+        "lastUpdated": "2025-12-24T19:08:12.422Z",
+        "gitCommitSha": "6d3752c000e2b3d0e6137bd7adb04895d6f40f14",
+        "isLocal": true
+      }
+    ],
+    "typescript-lsp@claude-plugins-official": [
+      {
+        "scope": "user",
+        "installPath": "/home/will/.claude/plugins/cache/claude-plugins-official/typescript-lsp/1.0.0",
+        "version": "1.0.0",
+        "installedAt": "2025-12-24T19:08:12.422Z",
+        "lastUpdated": "2025-12-24T19:08:12.422Z",
+        "gitCommitSha": "6d3752c000e2b3d0e6137bd7adb04895d6f40f14",
+        "isLocal": true
+      }
+    ],
+    "commit-commands@claude-plugins-official": [
+      {
+        "scope": "user",
+        "installPath": "/home/will/.claude/plugins/cache/claude-plugins-official/commit-commands/6d3752c000e2",
+        "version": "6d3752c000e2",
+        "installedAt": "2025-12-24T19:10:05.451Z",
+        "lastUpdated": "2025-12-24T19:10:36.843Z",
+        "isLocal": true
+      }
+    ],
+    "superpowers@superpowers-marketplace": [
+      {
+        "scope": "user",
+        "installPath": "/home/will/.claude/plugins/cache/superpowers-marketplace/superpowers/4.0.2",
+        "version": "4.0.2",
+        "installedAt": "2025-12-26T18:15:13.657Z",
+        "lastUpdated": "2025-12-26T18:15:13.657Z",
+        "gitCommitSha": "131c1f189f75a14faad4227089841d1deee73e2a",
+        "isLocal": false
+      }
+    ]
+  }
+}
--- a/plugins/known_marketplaces.json
+++ b/plugins/known_marketplaces.json
@@ -0,0 +1,18 @@
+{
+  "claude-plugins-official": {
+    "source": {
+      "source": "github",
+      "repo": "anthropics/claude-plugins-official"
+    },
+    "installLocation": "/home/will/.claude/plugins/marketplaces/claude-plugins-official",
+    "lastUpdated": "2025-12-26T18:15:48.383Z"
+  },
+  "superpowers-marketplace": {
+    "source": {
+      "source": "github",
+      "repo": "obra/superpowers-marketplace"
+    },
+    "installLocation": "/home/will/.claude/plugins/marketplaces/superpowers-marketplace",
+    "lastUpdated": "2025-12-26T18:14:47.747Z"
+  }
+}
--- a/settings.json
+++ b/settings.json
@@ -0,0 +1,10 @@
+{
+  "enabledPlugins": {
+    "frontend-design@claude-plugins-official": true,
+    "typescript-lsp@claude-plugins-official": true,
+    "commit-commands@claude-plugins-official": true,
+    "superpowers@superpowers-marketplace": true
+  },
+  "alwaysThinkingEnabled": true,
+  "model": "opus"
+}