Removed cognitive-memory MCP, timers, and symlink system references.
Replaced with kb-search MCP and /save-doc skill workflow.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Adds scheduled-tasks/CONTEXT.md documenting the implemented headless
Claude scheduled task system: runner.sh framework, custom dispatcher
scripts, active tasks, settings reference, auth, monitoring, and
cost safety guardrails.
Updates CLAUDE.md routing table to load CONTEXT.md alongside the
SKILL.md for all scheduled-task-related topics.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
Add mcp-tui-driver documentation with tool reference, workflow guide,
and correct MCP config location (~/.claude.json, not ~/.claude/.mcp.json).
Add context loading keyword entry for TUI testing topics.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Add fish functions/aliases section covering tls, tma, tmn, cc helpers
and config.fish abbreviations. Add fish/tmux keywords to CLAUDE.md
context loading table.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Document the new claude-scheduled system in CLAUDE.md keyword table
and add a comprehensive systemd user timers section to workstation
CONTEXT.md covering both cognitive-memory and claude-scheduled timers.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
New workstation/CONTEXT.md documents the ~/dotfiles symlink repo setup.
Added workstation keywords to context loading table.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
- Update monitoring CONTEXT.md with 6-server inventory table, per-server
SSH user support, and pre-escalation Discord notification docs
- Remove tdarr local monitoring scripts (decommissioned per prior decision)
- Update Proxmox upgrade plan with Phase 1 completion and Phase 2 prep
- Update vm-management CONTEXT.md with current PVE 8 state
- CLAUDE.md: auto-run /save-memories at 25% context instead of asking
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
- Trim keyword triggers to distinctive terms per topic
- Remove redundant loading convention, directory triggers, priority sections
- Remove documentation structure tree (discoverable from repo)
- Consolidate file extension triggers into special loads
- Shrink maintenance section to just the auto-prompts
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
CLAUDE.md optimization (329 → 104 lines):
- Compress repetitive loading rules into keyword table
- Remove 72 redundant "Note:" lines (info already in CONTEXT.md files)
- State loading convention once instead of repeating 13 times
- Preserve all functionality, special cases, and maintenance protocol
- 68% reduction in size, easier to scan and maintain
Gitea Actions Docker buildx fix:
- Remove conditional from Docker Hub login step
- Login now runs on all builds (PR and main), not just main
- Fixes "push access denied" on second build when writing cache layers
- Push flag still gates actual image publishing to main-only
Co-Authored-By: Claude Sonnet 4.5 <noreply@anthropic.com>
Document all 20 active monitors with targets and tags, Discord
notification configuration, and API access details for programmatic
management via uptime-kuma-api.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Deploy Uptime Kuma for centralized service uptime monitoring at
https://status.manticorum.com. Proxmox LXC 227 (10.10.0.227) running
Ubuntu 22.04 with Docker. Updated monitoring documentation, CLAUDE.md
context loading rules, and server-configs host inventory.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
- Document all 9 proxy hosts with SSL status and routing details
- Add NPM database access procedures and container management commands
- Include microservices routing patterns for SBA and PD applications
- Document SSL certificate management and expiration tracking
- Add operational procedures, troubleshooting guide, and maintenance schedules
- Update CLAUDE.md with NPM-specific keywords for automatic context loading
🤖 Generated with [Claude Code](https://claude.ai/code)
Co-Authored-By: Claude <noreply@anthropic.com>
- Add tdarr_monitor.py: Python-based API monitoring client with type-safe dataclasses
- ServerStatus, QueueStatus, NodeStatus, LibraryStatus, StatisticsStatus, HealthStatus
- Support for health checks, queue monitoring, node status, library scans
- JSON and pretty-print output formats with proper exit codes
- Integration with existing Discord monitoring system
- Create scripts/monitoring/README.md: Complete monitoring documentation
- Comprehensive usage examples and command-line options
- Integration patterns with gaming-aware scheduling
- Best practices for automated health monitoring
- Update CLAUDE.md: Enhanced Tdarr keyword triggers and documentation structure
- Add "monitoring" and "api" keywords to automatically load monitoring docs
- Reference new tdarr_monitor.py with dataclass-based status tracking
- Update documentation structure to show monitoring script location
🤖 Generated with [Claude Code](https://claude.ai/code)
Co-Authored-By: Claude <noreply@anthropic.com>
## Tdarr Plugin Stack Research & Configuration
- Research optimal H.265/HEVC plugin stacks for quality-focused transcoding
- Configure GPU threshold (95%) to prevent self-termination during transcoding
- Add Tdarr exception logic to distinguish transcoding from gaming GPU usage
- Update gaming detection to preserve active transcoding jobs
## Automated System Maintenance
- Add cron job for automatic cleanup of abandoned Tdarr temp directories
- Cleanup runs every 6 hours, preserves active jobs (< 6 hours old)
- Prevents /tmp filesystem bloat from interrupted transcoding jobs
- Safe cleanup only targets Tdarr-specific work directories
## Enhanced Documentation
- Add comprehensive Tdarr automation documentation in scripts/tdarr/README.md
- Document cleanup system and its relationship to main scheduler
- Update CLAUDE.md with Tdarr keyword triggers and context loading
- Add troubleshooting section for both scheduler and cleanup cron jobs
## System Architecture Improvements
- Organize Tdarr scripts under dedicated scripts/tdarr/ directory
- Maintain backwards compatibility with existing cron jobs
- Add gaming-aware scheduling with configurable time windows
- Implement robust GPU usage detection with Tdarr transcoding awareness
🤖 Generated with [Claude Code](https://claude.ai/code)
Co-Authored-By: Claude <noreply@anthropic.com>
- Add SSH key management patterns with dual-key strategy and NAS backup architecture
- Add complete SSH home lab setup implementation with scripts and configurations
- Add SSH troubleshooting reference with common issues and emergency procedures
- Update CLAUDE.md with SSH keyword triggers for automatic context loading
- Add .gitignore to exclude temporary files
🤖 Generated with [Claude Code](https://claude.ai/code)
Co-Authored-By: Claude <noreply@anthropic.com>
- Created structured documentation with /patterns/, /examples/, and /reference/ directories
- Implemented automatic context loading rules in CLAUDE.md based on file extensions, directories, and keywords
- Added technology-specific patterns for Docker, Python, Node.js, Vue.js, Bash, networking, databases, and VM management
- Included complete working examples for common workflows and troubleshooting references
- Designed for minimal context usage with precise loading triggers
🤖 Generated with [Claude Code](https://claude.ai/code)
Co-Authored-By: Claude <noreply@anthropic.com>
