agent-capabilities
CommandMatrix of agent capabilities and their specializations.
Complete guide to managing pair programming sessions.
> /plugin marketplace add ruvnet/agentic-flow> /plugin install agentic-flow@agentic-flow
Complete guide to managing pair programming sessions.
claude-flow pair --start
claude-flow pair --end
During an active session, use these commands:
/help - Show all available commands /status - Current session status /metrics - View quality metrics /pause - Pause current session /resume - Resume paused session /end - End current session
/explain - Explain current code /suggest - Get improvement suggestions /refactor - Refactor selected code /optimize - Optimize for performance /document - Add documentation /comment - Add inline comments
/test - Run test suite /test-gen - Generate tests /coverage - Check test coverage /test-watch - Enable test watching /mock - Generate mocks
/review - Full code review /security - Security analysis /perf - Performance review /quality - Quality metrics /lint - Run linters
/goto <file> - Navigate to file /find <text> - Search in project /recent - Recent files /bookmark - Bookmark location /history - Command history
/switch - Switch driver/navigator /mode <type> - Change mode /role - Show current role /handoff - Prepare role handoff
/diff - Show changes /commit - Commit with verification /branch - Branch operations /stash - Stash changes /log - View git log
Check current session status:
claude-flow pair --status
Output:
👥 Pair Programming Session ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ Session ID: pair_1755021234567 Duration: 45 minutes Status: Active Partner: senior-dev Current Role: DRIVER (you) Mode: Switch (10m intervals) Next Switch: in 3 minutes 📊 Metrics: ├── Truth Score: 0.982 ✅ ├── Lines Changed: 234 ├── Files Modified: 5 ├── Tests Added: 12 ├── Coverage: 87% ↑3% └── Commits: 3 🎯 Focus: Implementation 📝 Current File: src/auth/login.js
View past sessions:
claude-flow pair --history
Output:
📚 Session History ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 1. 2024-01-15 14:30 - 16:45 (2h 15m) Partner: expert-coder Focus: Refactoring Truth Score: 0.975 Changes: +340 -125 lines 2. 2024-01-14 10:00 - 11:30 (1h 30m) Partner: tdd-specialist Focus: Testing Truth Score: 0.991 Tests Added: 24 3. 2024-01-13 15:00 - 17:00 (2h) Partner: debugger-expert Focus: Bug Fixing Truth Score: 0.968 Issues Fixed: 5
Real-time metrics during session:
Current: 0.982 ✅ Average: 0.975 Minimum: 0.951 Threshold: 0.950
Lines Changed: 234 Files Modified: 5 Functions Added: 8 Functions Refactored: 3
Test Coverage: 87% ↑3% Lint Issues: 0 Security Issues: 0 Performance Issues: 1 ⚠️
Suggestions Given: 45 Suggestions Accepted: 38 (84%) Reviews Completed: 12 Rollbacks: 1
claude-flow pair --save [--name <name>]
claude-flow pair --load <session-id>
claude-flow pair --export <session-id> [--format json|md]
Run pair programming in background:
claude-flow pair --start --background
claude-flow pair --monitor
claude-flow pair --attach <session-id>
{
"pair": {
"session": {
"autoSave": true,
"saveInterval": "5m",
"maxDuration": "4h",
"idleTimeout": "15m",
"metricsInterval": "1m"
}
}
}claude-flow pair --start \ --config custom-config.json
claude-flow pair --template refactor
claude-flow pair --template feature
claude-flow pair --template debug
claude-flow pair --template learn
Generate session report:
claude-flow pair --report <session-id>
Report includes:
claude-flow pair --list
claude-flow pair --switch <session-id>
claude-flow pair --merge <session-1> <session-2>
Sessions auto-save every 5 minutes with recovery points.
claude-flow pair --recover [--point <timestamp>]
claude-flow pair --crash-recovery
claude-flow pair --share <session-id> \ --team <team-id>
claude-flow pair --export-review <session-id>
claude-flow pai
Production-ready AI agent orchestration with 66 self-learning agents, 213 MCP tools, and autonomous multi-agent swarms.
Matrix of agent capabilities and their specializations.
Complete guide to all 54 available agent types in Claude Flow.
Reviewed all command files in `.claude/commands/analysis/` directory to ensure proper usage of: - `mcp__claude-flow__*` tools…
Analyze performance bottlenecks in swarm operations and suggest optimizations.
Implement tasks incrementally — build, test, verify, commit. Add "auto" to run the whole plan in one approved pass.