feat: migrate all codex team skills from spawn_agents_on_csv to spawn_agent + wait_agent architecture

- Delete 21 old team skill directories using CSV-wave pipeline pattern (~100+ files)
- Delete old team-lifecycle (v3) and team-planex-v2
- Create generic team-worker.toml and team-supervisor.toml (replacing tlv4-specific TOMLs)
- Convert 19 team skills from Claude Code format (Agent/SendMessage/TaskCreate)
  to Codex format (spawn_agent/wait_agent/tasks.json/request_user_input)
- Update team-lifecycle-v4 to use generic agent types (team_worker/team_supervisor)
- Convert all coordinator role files: dispatch.md, monitor.md, role.md
- Convert all worker role files: remove run_in_background, fix Bash syntax
- Convert all specs/pipelines.md references
- Final state: 20 team skills, 217 .md files, zero Claude Code API residuals

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

.codex/skills/team-ux-improve/wisdom/anti-patterns/common-ux-pitfalls.md

@@ -0,0 +1,17 @@
+# Common UX Pitfalls
+
+## Interaction Issues
+- Buttons without loading states during async operations
+- Missing error handling with user feedback
+- State changes without visual updates
+- Double-click vulnerabilities
+
+## State Issues
+- Stale data after mutations
+- Race conditions in async operations
+- Missing rollback for failed optimistic updates
+
+## Feedback Issues
+- Silent failures without user notification
+- Generic error messages without actionable guidance
+- Missing confirmation for destructive actions

.codex/skills/team-ux-improve/wisdom/patterns/state-management.md

@@ -0,0 +1,14 @@
+# State Management Patterns
+
+## Local Component State
+- Use for UI-only state (open/closed, hover, focus)
+- Keep close to where it's used
+
+## Shared State
+- Lift state to lowest common ancestor
+- Use context or state management library for deep trees
+
+## Async State
+- Track loading, error, and success states
+- Handle race conditions with request cancellation
+- Implement retry logic with exponential backoff

.codex/skills/team-ux-improve/wisdom/patterns/ui-feedback.md

@@ -0,0 +1,16 @@
+# UI Feedback Patterns
+
+## Loading States
+- Use skeleton loaders for content areas
+- Disable buttons during async operations
+- Show progress indicators for long operations
+
+## Error Handling
+- Display errors inline when possible
+- Provide actionable error messages
+- Allow retry for transient failures
+
+## Success Feedback
+- Toast notifications for non-critical successes
+- Inline confirmation for critical actions
+- Auto-dismiss non-critical notifications

.codex/skills/team-ux-improve/wisdom/principles/general-ux.md

@@ -0,0 +1,16 @@
+# General UX Principles
+
+## Feedback & Responsiveness
+- Every user action should have immediate visual feedback
+- Loading states must be shown for operations >200ms
+- Success/error states should be clearly communicated
+
+## State Management
+- UI state should reflect the underlying data state
+- Optimistic updates should have rollback mechanisms
+- State changes should be atomic and predictable
+
+## Accessibility
+- Interactive elements must be keyboard accessible
+- Color should not be the only indicator of state
+- Focus states must be visible