📋 Add troubleshoot command and refine personality system

Adds autonomous error resolution system with `/troubleshoot` command
for production debugging. Refactors personality switching to automatically
manage Cursor's `alwaysApply` flags across all personality files instead
of requiring manual setup. Adds git collaboration and worktree task rules
to standardize autonomous development workflows. Activates Bob Ross
personality as default baseline.

Author: Nick Sullivan

.claude/commands/personality-change.md

@@ -57,11 +57,20 @@ d. If not removing (name != "none"):
 
 e. Write updated `.claude/context.md`
 
-### 3. Verify Cursor Setup
+### 3. Update Cursor Configuration
 
-a. Read `.cursor/rules/personalities/<name>.mdc` frontmatter b. Check if
-`alwaysApply: true` is set c. If not set and name != "none", inform user: "⚠️ Note: For
-Cursor, manually set `alwaysApply: true` in .cursor/rules/personalities/<name>.mdc"
+a. Find all personality files in `.cursor/rules/personalities/` (except
+`common-personality.mdc`)
+
+b. For each personality file:
+
+- Read the file content
+- Extract frontmatter (between `---` markers)
+- If this is the selected personality and name != "none": set `alwaysApply: true`
+- If this is NOT the selected personality OR name == "none": set `alwaysApply: false`
+- Write the updated file back
+
+c. Confirm updates were made
 
 ### 4. Report Results
 
@@ -71,7 +80,8 @@ Cursor, manually set `alwaysApply: true` in .cursor/rules/personalities/<name>.m
 ✓ Switched from <old-name> to <new-name> personality
 
 Claude Code: Updated .claude/context.md
-Cursor: Active at .cursor/rules/personalities/<name>.mdc
+Cursor: Set alwaysApply=true in .cursor/rules/personalities/<new-name>.mdc
+        Set alwaysApply=false in .cursor/rules/personalities/<old-name>.mdc
 ```
 
 **If activating (no previous):**
@@ -80,7 +90,7 @@ Cursor: Active at .cursor/rules/personalities/<name>.mdc
 ✓ Activated <name> personality
 
 Claude Code: Added to .claude/context.md
-Cursor: Active at .cursor/rules/personalities/<name>.mdc
+Cursor: Set alwaysApply=true in .cursor/rules/personalities/<name>.mdc
 ```
 
 **If removing:**
@@ -89,7 +99,7 @@ Cursor: Active at .cursor/rules/personalities/<name>.mdc
 ✓ Removed active personality
 
 Claude Code: Removed from .claude/context.md
-Cursor: Manually set alwaysApply: false if desired
+Cursor: Set alwaysApply=false for all personalities
 ```
 
 **If already active:**
@@ -111,5 +121,6 @@ Cursor: Manually set alwaysApply: false if desired
 - Only one personality active at a time (plus common-personality baseline)
 - Personality affects ALL future interactions in this project
 - `.cursor/rules/personalities/common-personality.mdc` is always applied as baseline
-- Cursor requires `alwaysApply: true` in frontmatter for auto-activation
+- Cursor frontmatter is automatically updated (`alwaysApply: true` for active, `false`
+  for others)
 - Claude Code reads from `.claude/context.md` which is always included

.claude/commands/troubleshoot-setup.md

@@ -0,0 +1,104 @@
+# Setting Up /troubleshoot Command
+
+## Quick Start
+
+### 1. Configure MCP Server
+
+Create `.mcp.json` in your project root:
+
+```json
+{
+  "mcpServers": {
+    "sentry": {
+      "url": "https://mcp.sentry.dev/mcp"
+    }
+  }
+}
+```
+
+(Or use `"honeybadger"` with `https://mcp.honeybadger.io/mcp`)
+
+### 2. Symlink for Cursor Compatibility
+
+If you use both Claude Code and Cursor:
+
+```bash
+ln -s ../.mcp.json .cursor/mcp.json
+```
+
+This ensures both tools share the same MCP configuration.
+
+### 3. Connect Error Monitoring Service
+
+- **Sentry:** https://mcphubby.ai/integrations/sentry
+- **HoneyBadger:** https://mcphubby.ai/integrations/honeybadger
+
+Click "Connect" and authorize MCP Hubby to access your account.
+
+### 4. Install the Command
+
+From ai-coding-config repo:
+
+```bash
+ln -s ../ai-coding-config/.claude/commands/troubleshoot.md .claude/commands/troubleshoot.md
+```
+
+### 5. Run It
+
+```bash
+/troubleshoot
+```
+
+The AI will autonomously fix production errors!
+
+## What Happens
+
+1. AI detects which error monitoring service is connected
+2. Fetches all unresolved errors
+3. Groups errors by root cause (cluster analysis)
+4. Calculates priority scores (recency + frequency + impact + blast radius)
+5. Fixes highest priority errors in isolated git worktrees
+6. Operates in parallel (multiple fixes simultaneously)
+7. Submits PRs with full context
+8. Monitors deployment and verifies fixes
+
+## Advanced Usage
+
+```bash
+/troubleshoot auto 5   # Fix top 5 bugs in parallel
+/troubleshoot watch    # Continuous monitoring mode
+/troubleshoot analyze  # Pattern analysis only
+/troubleshoot 3        # Fix specific bug by priority rank
+```
+
+## Architecture
+
+```
+Project Root/
+├── .mcp.json                          # MCP server config (source of truth)
+├── .cursor/
+│   └── mcp.json -> ../.mcp.json      # Symlink for Cursor
+├── .claude/
+│   └── commands/
+│       └── troubleshoot.md -> ...     # Command symlink
+└── .cursor/rules/
+    ├── git-worktree-task.mdc         # Worktree workflow
+    └── git-commit-message.md         # Commit standards
+```
+
+## Why This Approach
+
+**Unified Configuration:** `.mcp.json` is the single source. Both Claude Code and Cursor
+symlink to it.
+
+**AI-First Design:** The command trusts the AI to make intelligent decisions.
+Goal-focused, not prescriptive.
+
+**Parallel Workflows:** Multiple bugs fixed simultaneously in isolated worktrees. Much
+faster than sequential fixing.
+
+**Pattern Recognition:** AI clusters related errors and fixes root causes, not just
+symptoms.
+
+**Autonomous Operation:** No hand-holding needed. AI operates continuously until
+production is clean.