New sections added:
- Rule 2.1: Shared Supabase pattern for all Vercel web apps
- Same Supabase project (qnatchrjlpehiijwtreh)
- Table naming: <projectName>_tableName
- Copy .env.local from existing projects
- Specialized Agent Profiles section
- List of all available agents
- When to use each
- How to spawn them
- Key benefit: auto-loaded skills
Now documented in both agent configs and curated memory
Added to web-dev agent:
- firebase-auth-basics and firebase-firestore-basics skills
- Supabase-specific rules and patterns
- SSR auth, server components, RLS policies guidance
- Service role key security practices
Updated SPECIALIZED_AGENTS.md documentation
New specialized agents:
- ios-dev: iOS/Swift/SwiftUI development
- web-dev: Next.js/React/web development
- research: Research and analysis tasks
Each agent has:
- Own agent.json config with specialized system prompt
- Auto-loaded relevant skills
- Domain-specific best practices and rules
- Proper model configuration
Also added:
- SPECIALIZED_AGENTS.md documentation
- CLI_README_TEMPLATE.md for reference
- Rule 2.5: CLI must stay in sync with Web UI
- Added audit-cli-coverage.sh template to workspace scripts
- Documented monthly audit process
- Reference implementation in gantt-board
- New mandatory rule: Every web API endpoint must have matching CLI
- Added verification process for API-to-CLI coverage
- Added ongoing maintenance checklist
- Added coverage matrix template
- Removed duplicate monitoring scripts (4 versions consolidated to 1)
- Moved gantt-specific scripts to gantt-board project repo
- Moved create_ios_project.sh into scripts/
- Moved monitor-processes.sh into scripts/ as resource-monitor.sh
- Deleted monitor-restart.sh (duplicate)
- Created README.md documenting what's left and why
- Created daily-backup.sh script for all 3 web apps
- Backs up data/ directories to Git daily at 11:00 PM CST
- Commits and pushes to Gitea automatically
- Logs to memory/backup.log
- Cron job created for automated daily runs
- Analyzed system limits, memory usage, process status
- Identified primary suspect: Next.js dev server memory leaks
- Secondary suspects: macOS power mgmt, SSH timeout, OOM killer
- Created monitoring script for CPU/memory/file descriptors
- Documented recommendations: production builds, PM2, nohup
- Created monitor-restart.sh script for manual or cron-based monitoring
- Script checks all 3 sites and auto-restarts if down
- Includes proper process cleanup with pkill
- Logs to /tmp/web-monitor.log
- Document distinction between my projects and user's projects
- Add step-by-step instructions for switching git identity
- List specific projects for each owner
- Add visual reminders and quick check commands
- Updated cron job payload to require [headline](url) markdown format
- Updated documentation to emphasize clickable links requirement
- Posted new sample digest with proper link formatting
- Every item now includes full URL to source article
- Added new Heartbeat Monitor dashboard at port 3005
- Documented all features: uptime tracking, sparklines, add app UI
- Updated all three projects in the monitoring list
- Added instructions for adding new apps dynamically
- Created memory/web-apps-monitoring.md with status and restart instructions
- Set up cron job to check both sites every 10 minutes
- Auto-restarts any site that returns non-200 or times out
- Sends Telegram notification if restart occurs
- Created memory/digest-topics.json for customizing search topics
- Each topic has id, name, enabled flag, and searchQueries array
- Easy to add/remove/modify topics without code changes
- Updated documentation with customization instructions
- Created memory/daily-digest-system.md with full system overview
- Documented API endpoints and cron schedule
- Added instructions for AI continuity if agent is replaced
- Documented mobile-first responsive design as REQUIRED standard
- Added web development tech preferences (Next.js, Tailwind, etc.)
- Created memory/project-standards.md for coding guidelines
