- OpenCode: use `opencode run -m MODEL "prompt"` syntax
- OpenCode: set correct binary path (/home/linuxbrew/.linuxbrew/bin/opencode)
- Gemini: route long-context to gemini-2.5-pro (gemini-3 not available yet)
Tested working:
- opencode/big-pickle
- github-copilot/claude-sonnet-4.5
- zai-coding-plan/glm-4.7
- gemini/gemini-2.5-pro
- gemini/gemini-2.5-flash
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- Add fc-047: Consider JSON minification for OpenCode instructions
- Add brainstorming plan for OpenCode Claude sync enhancements
- Add implementation status plan
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- New gtasks skill with thin wrapper around morning-report collector
- Register /tasks command with /todo, /todos aliases
- Design doc at docs/plans/2026-01-05-gtasks-skill-design.md
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- future-considerations: Pretty-print JSON, update fc-001 to pending status
- history/index: Add recent session entries
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Add new skill for semantic search across personal state files and
external documentation using ChromaDB and sentence-transformers.
Components:
- search.py: Main search interface (--index, --top-k flags)
- index_personal.py: Index ~/.claude/state files
- index_docs.py: Index external docs (git repos)
- add_doc_source.py: Manage doc sources
- test_rag.py: Test suite (5/5 passing)
Features:
- Two indexes: personal (116 chunks) and docs (k0s: 846 chunks)
- all-MiniLM-L6-v2 embeddings (384 dimensions)
- ChromaDB persistent storage
- JSON output with ranked results and metadata
Documentation:
- Added to component-registry.json with triggers
- Added /rag command alias
- Updated skills/README.md
- Resolved fc-013 (vector database for agent memory)
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Design for extending Claude agent system with semantic search:
- Two indexes: personal (state files) + external docs
- ChromaDB + sentence-transformers stack
- rag-search skill with search.py CLI
- Daily systemd timer for index refresh
- Ralph loop implementation with Haiku/Sonnet delegation
Added future considerations (fc-043 to fc-046):
- Auto-sync on tool version change
- Broad doc indexing
- K8s deployment
- Query caching
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- Creates gitea-merge.sh: rebase merge, delete branch, close PR
- Updates CLAUDE.md: simplified git workflow using new script
- Adds model selection reminder to general-instructions.json
- Documents Gitea API commands in CLAUDE.md
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- Create automation/gitea-pr.sh for auto-creating PRs via Gitea API
- Update CLAUDE.md with git workflow using the new script
- Deprecate redundant git instructions in PA general-instructions.json
- Token stored securely at ~/.config/gitea-token
Usage: gitea-pr.sh "PR Title" "Description"
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Injects contextual information when user submits a prompt:
- Current time with period (morning/afternoon/evening/night)
- Git branch if in a repository
- Relevant memory items based on prompt keywords (2+ matches)
- Pending decisions needing attention
Design:
- Skips short prompts (<10 chars) to not slow down commands
- 5s timeout to keep prompts responsive
- Lightweight keyword matching for memory relevance
Also updates general-instructions.json with git workflow notes.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- /diff command to compare config with backups
- Shows added/removed/changed files
- JSON-aware comparison for config files
- List available backups
- /template command for session templates
- Built-in templates: daily-standup, code-review, troubleshoot, deploy
- Each template includes checklist, initial commands, prompt
- Create custom templates interactively or non-interactively
- Updated shell completions with 21 aliases total
- Test suite now covers 29 tests
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- /workflow command to list and describe available workflows
- Filter by category (health, deploy, incidents, sysadmin)
- Show workflow steps and triggers
- /skill-info command for skill introspection
- List scripts, triggers, and allowed tools
- Show references and documentation
- /agent-info command with hierarchy visualization
- Tree view of agent relationships
- Model assignments (opus/sonnet/haiku) with visual indicators
- Supervisor and subordinate information
- Updated shell completions with 19 aliases total
- Test suite now covers 27 tests
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- /export command to export session data as Markdown or JSON
- Export for sharing with other Claude instances
- Include session details, topics, summary, and memory items
- /mcp-status command to check MCP integration health
- Gmail venv and credentials status
- Calendar API dependencies
- Delegation helpers presence
- MCP server configuration
- Updated shell completions with 15 aliases total
- Test suite now covers 23 tests
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- /log command to view and analyze automation logs
- Filter by pattern, date, or log type
- List available log files
- /debug command generates comprehensive debug report
- Version, core files, state, memory, scripts status
- Environment info (Python, kubectl)
- Disk usage by directory
- JSON output mode for scripting
- Updated shell completions with 13 aliases total
- Test suite now covers 21 tests
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- /search command to search across memory, history, and configuration
- history-browser.py for browsing and analyzing session history
- install.sh for first-time setup with directory creation and validation
- daily-maintenance.sh for scheduled backup, cleanup, and validation
- systemd timer units for automated daily maintenance at 6 AM
- Updated shell completions with 11 aliases
- Test suite now covers 19 tests
- Bump version to 1.1.0
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
New commands:
- /remember: Quick shortcut to save to memory (auto-categorizes)
- /config: View and manage configuration settings
New automation scripts:
- memory-add.py: Add items to PA memory with auto-categorization
- memory-list.py: List memory items by category
The /remember command provides a quick way to save:
- "Always use X" → preferences
- "Decided to use X" → decisions
- "Project at ~/path" → projects
- Other → facts
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- /help: Shows available commands and skills with descriptions
- /status: Quick dashboard overview across all domains
- System health (disk, memory, updates)
- Kubernetes status (nodes, pods, alerts)
- Email summary (unread, urgent)
- Calendar (today's events, next meeting)
Both commands added to component-registry.json with aliases:
- /help: /commands, /skills
- /status: /overview, /dashboard
Updated commands/README.md with new entries.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- mcp/README.md: Document Gmail setup, delegation helpers, MCP patterns
- state/README.md: Document state files, ownership, and subdirectories
Completes documentation coverage for all major directories.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- Bump version to 1.1
- Add script paths for skills (for quick reference)
- Expand trigger phrases for better matching
- Keep consistent formatting throughout
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- Add pyright-lsp for Python language server support
- Add superpowers-developing-for-claude-code for plugin development guidance
- Enable superpowers-developing-for-claude-code in settings
- Update PA history index
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Components:
- state/component-registry.json: Registry with all skills, commands, agents, workflows
- automation/generate-registry.py: Auto-generate from directory scan
- automation/validate-registry.py: Check for drift and TODO placeholders
- system-instructions.json: Added component-lifecycle process
Registry includes:
- 6 skills with routing triggers
- 10 commands with aliases
- 12 agents with model info
- 10 workflows with triggers
- 2 delegation helpers
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- Updated design document status to Implemented
- Marked all checklist items complete
- Updated fc-005 in future-considerations.json
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
New items (fc-018 to fc-023):
- Custom date range query (medium)
- Natural language date parsing (medium)
- Configurable timezone (low)
- Month subcommand (low)
- Free/busy check (medium)
- Write operations (low, deferred)
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Implements cost-efficient gmail operations by delegating to appropriate
model tiers via Claude CLI subprocess. Simple fetches use no LLM,
summarization and triage delegate to Sonnet, complex reasoning stays
with Opus (PA). Uses subscription instead of API key.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Programmer Agent System:
- Add programmer-orchestrator (Opus) for workflow coordination
- Add code-planner (Sonnet) for design and planning
- Add code-implementer (Sonnet) for writing code
- Add code-reviewer (Sonnet) for quality review
- Add /programmer command and project registration skill
- Add state files for preferences and project context
Agent Infrastructure:
- Add master-orchestrator and linux-sysadmin agents
- Restructure skills to use SKILL.md subdirectory format
- Convert workflows from markdown to YAML format
- Add commands for k8s and sysadmin domains
- Add shared state files (model-policy, autonomy-levels, system-instructions)
- Add PA memory system (decisions, preferences, projects, facts)
Cleanup:
- Remove deprecated markdown skills and workflows
- Remove crontab example (moved to workflows)
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- Design doc: two-KB architecture (shared + PA-private)
- Lazy-load with session caching
- Minified JSON format for all state files
- Hybrid learning (explicit + implicit with confirmation)
- Handoff doc for next session implementation
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Implement canonical /pa entrypoint for user requests with:
- Context-aware request routing via master-orchestrator
- Session and persistent context level overrides
- Memory system with UUID-based general-instructions.json
- State files for session context and preferences
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
