claude-flow-novice 2.18.23 → 2.18.25

package/config/skill-requirements.json

@@ -0,0 +1,341 @@
+{
+  "version": "1.0.0",
+  "description": "Skill requirements for MCP tools and servers",
+  "lastUpdated": "2025-11-05",
+  "tools": {
+    "take_screenshot": {
+      "displayName": "Take Screenshot",
+      "requiredSkills": [
+        "browser-automation",
+        "screenshot-capture"
+      ],
+      "optionalSkills": [
+        "ui-development",
+        "accessibility-testing"
+      ],
+      "allowedAgentTypes": [
+        "react-frontend-engineer",
+        "ui-designer",
+        "accessibility-validator",
+        "mobile-dev"
+      ],
+      "resourceImpact": {
+        "memoryMB": 256,
+        "cpuUnits": 2,
+        "durationSeconds": 10
+      },
+      "description": "Capture webpage screenshots with Playwright"
+    },
+    "search_google": {
+      "displayName": "Search Google",
+      "requiredSkills": [
+        "browser-automation",
+        "web-search"
+      ],
+      "optionalSkills": [
+        "seo-analysis",
+        "content-research"
+      ],
+      "allowedAgentTypes": [
+        "react-frontend-engineer",
+        "ui-designer",
+        "mobile-dev"
+      ],
+      "resourceImpact": {
+        "memoryMB": 512,
+        "cpuUnits": 3,
+        "durationSeconds": 15
+      },
+      "description": "Search Google and return results"
+    },
+    "navigate_and_interact": {
+      "displayName": "Navigate and Interact",
+      "requiredSkills": [
+        "browser-automation",
+        "web-interaction"
+      ],
+      "optionalSkills": [
+        "form-testing",
+        "user-journey-testing"
+      ],
+      "allowedAgentTypes": [
+        "react-frontend-engineer",
+        "ui-designer",
+        "accessibility-validator",
+        "mobile-dev"
+      ],
+      "resourceImpact": {
+        "memoryMB": 384,
+        "cpuUnits": 3,
+        "durationSeconds": 20
+      },
+      "description": "Navigate web pages and interact with elements"
+    },
+    "redis_get": {
+      "displayName": "Redis Get Operation",
+      "requiredSkills": [
+        "redis-operations"
+      ],
+      "optionalSkills": [
+        "cache-management",
+        "data-retrieval"
+      ],
+      "allowedAgentTypes": [
+        "backend-developer",
+        "database-architect",
+        "api-gateway-specialist",
+        "devops-engineer"
+      ],
+      "resourceImpact": {
+        "memoryMB": 64,
+        "cpuUnits": 1,
+        "durationSeconds": 2
+      },
+      "description": "Retrieve data from Redis cache"
+    },
+    "redis_set": {
+      "displayName": "Redis Set Operation",
+      "requiredSkills": [
+        "redis-operations"
+      ],
+      "optionalSkills": [
+        "cache-management",
+        "data-storage"
+      ],
+      "allowedAgentTypes": [
+        "backend-developer",
+        "database-architect",
+        "api-gateway-specialist",
+        "devops-engineer"
+      ],
+      "resourceImpact": {
+        "memoryMB": 64,
+        "cpuUnits": 1,
+        "durationSeconds": 2
+      },
+      "description": "Store data in Redis cache"
+    },
+    "postgres_query": {
+      "displayName": "PostgreSQL Query",
+      "requiredSkills": [
+        "database-design",
+        "sql-operations"
+      ],
+      "optionalSkills": [
+        "query-optimization",
+        "data-analysis"
+      ],
+      "allowedAgentTypes": [
+        "backend-developer",
+        "database-architect",
+        "api-gateway-specialist"
+      ],
+      "resourceImpact": {
+        "memoryMB": 128,
+        "cpuUnits": 2,
+        "durationSeconds": 5
+      },
+      "description": "Execute PostgreSQL queries"
+    },
+    "api_test_endpoint": {
+      "displayName": "API Endpoint Testing",
+      "requiredSkills": [
+        "api-development",
+        "api-testing"
+      ],
+      "optionalSkills": [
+        "load-testing",
+        "security-testing"
+      ],
+      "allowedAgentTypes": [
+        "backend-developer",
+        "api-gateway-specialist",
+        "security-specialist",
+        "performance-tester"
+      ],
+      "resourceImpact": {
+        "memoryMB": 192,
+        "cpuUnits": 2,
+        "durationSeconds": 8
+      },
+      "description": "Test API endpoints for functionality and performance"
+    },
+    "security_scan": {
+      "displayName": "Security Vulnerability Scan",
+      "requiredSkills": [
+        "security-auditing",
+        "vulnerability-scanning"
+      ],
+      "optionalSkills": [
+        "penetration-testing",
+        "compliance-checking"
+      ],
+      "allowedAgentTypes": [
+        "security-specialist",
+        "backend-developer",
+        "devops-engineer"
+      ],
+      "resourceImpact": {
+        "memoryMB": 512,
+        "cpuUnits": 4,
+        "durationSeconds": 30
+      },
+      "description": "Scan for security vulnerabilities"
+    },
+    "kubernetes_deploy": {
+      "displayName": "Kubernetes Deployment",
+      "requiredSkills": [
+        "kubernetes-management",
+        "container-orchestration"
+      ],
+      "optionalSkills": [
+        "helm-charts",
+        "service-mesh"
+      ],
+      "allowedAgentTypes": [
+        "kubernetes-specialist",
+        "devops-engineer"
+      ],
+      "resourceImpact": {
+        "memoryMB": 256,
+        "cpuUnits": 2,
+        "durationSeconds": 45
+      },
+      "description": "Deploy applications to Kubernetes cluster"
+    },
+    "monitoring_metrics": {
+      "displayName": "Monitoring Metrics Collection",
+      "requiredSkills": [
+        "metrics-collection",
+        "performance-monitoring"
+      ],
+      "optionalSkills": [
+        "alerting-systems",
+        "dashboard-creation"
+      ],
+      "allowedAgentTypes": [
+        "monitoring-specialist",
+        "devops-engineer",
+        "performance-tester",
+        "kubernetes-specialist"
+      ],
+      "resourceImpact": {
+        "memoryMB": 192,
+        "cpuUnits": 2,
+        "durationSeconds": 10
+      },
+      "description": "Collect and analyze monitoring metrics"
+    },
+    "log_analysis": {
+      "displayName": "Log Analysis",
+      "requiredSkills": [
+        "log-analysis",
+        "troubleshooting"
+      ],
+      "optionalSkills": [
+        "incident-response",
+        "pattern-matching"
+      ],
+      "allowedAgentTypes": [
+        "monitoring-specialist",
+        "devops-engineer",
+        "backend-developer",
+        "security-specialist"
+      ],
+      "resourceImpact": {
+        "memoryMB": 384,
+        "cpuUnits": 3,
+        "durationSeconds": 15
+      },
+      "description": "Analyze application and system logs"
+    },
+    "load_test": {
+      "displayName": "Load Testing",
+      "requiredSkills": [
+        "load-testing",
+        "performance-monitoring"
+      ],
+      "optionalSkills": [
+        "stress-testing",
+        "benchmarking"
+      ],
+      "allowedAgentTypes": [
+        "performance-tester",
+        "backend-developer",
+        "devops-engineer"
+      ],
+      "resourceImpact": {
+        "memoryMB": 1024,
+        "cpuUnits": 6,
+        "durationSeconds": 120
+      },
+      "description": "Perform load testing on applications"
+    },
+    "accessibility_audit": {
+      "displayName": "Accessibility Audit",
+      "requiredSkills": [
+        "accessibility-testing",
+        "wcag-compliance"
+      ],
+      "optionalSkills": [
+        "screen-reader-testing",
+        "color-contrast-analysis"
+      ],
+      "allowedAgentTypes": [
+        "accessibility-validator",
+        "ui-designer",
+        "react-frontend-engineer"
+      ],
+      "resourceImpact": {
+        "memoryMB": 384,
+        "cpuUnits": 3,
+        "durationSeconds": 25
+      },
+      "description": "Audit applications for accessibility compliance"
+    },
+    "responsive_test": {
+      "displayName": "Responsive Design Testing",
+      "requiredSkills": [
+        "responsive-testing",
+        "device-testing"
+      ],
+      "optionalSkills": [
+        "mobile-development",
+        "css-testing"
+      ],
+      "allowedAgentTypes": [
+        "mobile-dev",
+        "ui-designer",
+        "react-frontend-engineer"
+      ],
+      "resourceImpact": {
+        "memoryMB": 512,
+        "cpuUnits": 3,
+        "durationSeconds": 20
+      },
+      "description": "Test responsive design across different screen sizes"
+    },
+    "screenshot_analysis": {
+      "displayName": "Screenshot Analysis",
+      "requiredSkills": [
+        "screenshot-capture",
+        "visual-analysis"
+      ],
+      "optionalSkills": [
+        "ui-testing",
+        "regression-testing"
+      ],
+      "allowedAgentTypes": [
+        "ui-designer",
+        "react-frontend-engineer",
+        "accessibility-validator"
+      ],
+      "resourceImpact": {
+        "memoryMB": 768,
+        "cpuUnits": 4,
+        "durationSeconds": 15
+      },
+      "description": "Analyze screenshots for visual differences and issues"
+    }
+  }
+}

package/config/sla-definitions.test.yml

@@ -0,0 +1,66 @@
+# SLA Definitions for Performance Monitoring
+# Test Configuration - Used for unit tests
+#
+# Each SLA definition specifies performance targets and baseline percentiles
+# Used to track and alert on performance degradation
+#
+# SLA Target: <X>ms = P50 should be below X ms
+# Baseline P95: Performance threshold for 95th percentile
+# Baseline P99: Performance threshold for 99th percentile
+#
+# See docs/PERFORMANCE_MONITORING_GUIDE.md for detailed configuration
+
+slas:
+  # Agent Startup SLA
+  # Target: Initialize new agent in <2s
+  agent_startup:
+    target: 2000           # ms - median response time target
+    p95: 2000              # 95th percentile
+    p99: 5000              # 99th percentile
+    enabled: true
+    alert_threshold: 1.2   # Alert if performance degrades >20%
+
+  # Query Execution SLA
+  # Target: Execute database queries in <5s
+  query_execution:
+    target: 5000           # ms - median response time target
+    p95: 5000              # 95th percentile
+    p99: 10000             # 99th percentile
+    enabled: true
+    alert_threshold: 1.2   # Alert if performance degrades >20%
+
+  # Skill Execution SLA
+  # Target: Complete skill execution in <30s
+  skill_execution:
+    target: 30000          # ms - median response time target
+    p95: 30000             # 95th percentile
+    p99: 60000             # 99th percentile
+    enabled: true
+    alert_threshold: 1.2   # Alert if performance degrades >20%
+
+  # Transaction Commit SLA
+  # Target: Commit database transaction in <5s
+  transaction_commit:
+    target: 5000           # ms - median response time target
+    p95: 5000              # 95th percentile
+    p99: 10000             # 99th percentile
+    enabled: true
+    alert_threshold: 1.2   # Alert if performance degrades >20%
+
+# Global SLA Configuration
+global:
+  # Monthly SLA violation threshold (target <5%)
+  monthly_violation_target: 0.05
+
+  # Degradation detection parameters
+  degradation_window_minutes: 5      # Evaluate last 5 minutes
+  degradation_threshold_percent: 20  # Alert if >20% degradation
+  degradation_consecutive_samples: 5 # Require 5+ samples
+
+  # Alert configuration
+  alert_resolution_hours: 24         # Auto-resolve alerts after 24h
+
+  # Retention policy
+  metrics_retention_days: 90          # Keep metrics for 90 days
+  alerts_retention_days: 365          # Keep alert history for 1 year
+  baseline_calculation_days: 30       # Default baseline window

package/config/sla-definitions.yml

@@ -0,0 +1,150 @@
+# SLA Definitions for Performance Monitoring
+# Production Configuration
+#
+# Each SLA definition specifies performance targets and baseline percentiles
+# Used to track and alert on performance degradation
+#
+# SLA Target: <X>ms = P50 should be below X ms
+# Baseline P95: Performance threshold for 95th percentile
+# Baseline P99: Performance threshold for 99th percentile
+#
+# See docs/PERFORMANCE_MONITORING_GUIDE.md for detailed configuration
+
+slas:
+  # Agent Startup SLA
+  # Target: Initialize new agent in <2s
+  # Used for: Agent spawning, initialization
+  agent_startup:
+    target: 2000           # ms - median response time target
+    p95: 2000              # 95th percentile - 95% of startups should be <2s
+    p99: 5000              # 99th percentile - 99% of startups should be <5s
+    enabled: true
+    alert_threshold: 1.2   # Alert if performance degrades >20%
+
+  # Query Execution SLA
+  # Target: Execute database queries in <5s
+  # Used for: Database queries, API calls
+  query_execution:
+    target: 5000           # ms - median response time target
+    p95: 5000              # 95th percentile - 95% of queries should be <5s
+    p99: 10000             # 99th percentile - 99% of queries should be <10s
+    enabled: true
+    alert_threshold: 1.2   # Alert if performance degrades >20%
+
+  # Skill Execution SLA
+  # Target: Complete skill execution in <30s
+  # Used for: Skill runs, custom operations
+  skill_execution:
+    target: 30000          # ms - median response time target
+    p95: 30000             # 95th percentile - 95% of skills should complete in <30s
+    p99: 60000             # 99th percentile - 99% of skills should complete in <60s
+    enabled: true
+    alert_threshold: 1.2   # Alert if performance degrades >20%
+
+  # Transaction Commit SLA
+  # Target: Commit database transaction in <5s
+  # Used for: Database transactions, writes
+  transaction_commit:
+    target: 5000           # ms - median response time target
+    p95: 5000              # 95th percentile - 95% of commits should be <5s
+    p99: 10000             # 99th percentile - 99% of commits should be <10s
+    enabled: true
+    alert_threshold: 1.2   # Alert if performance degrades >20%
+
+  # Log Shipment SLA
+  # Target: Ship logs in <1s
+  # Used for: Log aggregation, metrics export
+  log_shipment:
+    target: 1000           # ms - median shipment time
+    p95: 1000              # 95th percentile
+    p99: 2000              # 99th percentile
+    enabled: true
+    alert_threshold: 1.2   # Alert if performance degrades >20%
+
+  # Checkpoint Save SLA
+  # Target: Save checkpoint in <5s
+  # Used for: State management, distributed coordination
+  checkpoint_save:
+    target: 5000           # ms - median save time
+    p95: 5000              # 95th percentile
+    p99: 10000             # 99th percentile
+    enabled: true
+    alert_threshold: 1.2   # Alert if performance degrades >20%
+
+  # Cache Lookup SLA
+  # Target: Cache lookup in <100ms
+  # Used for: In-memory cache, rapid access patterns
+  cache_lookup:
+    target: 100            # ms - median lookup time
+    p95: 100               # 95th percentile
+    p99: 500               # 99th percentile
+    enabled: true
+    alert_threshold: 1.2   # Alert if performance degrades >20%
+
+# Global SLA Configuration
+global:
+  # Monthly SLA violation threshold (target <5%)
+  # This means we aim for >95% compliance monthly
+  monthly_violation_target: 0.05
+
+  # Degradation detection parameters
+  degradation_window_minutes: 5      # Evaluate last 5 minutes of data
+  degradation_threshold_percent: 20  # Alert if >20% degradation from baseline
+  degradation_consecutive_samples: 5 # Require 5+ samples to declare degradation
+
+  # Alert configuration
+  alert_resolution_hours: 24         # Auto-resolve alerts after 24h if not re-triggered
+  alert_batch_window_minutes: 5      # Batch similar alerts within 5 minute window
+  alert_max_frequency_per_hour: 10   # Max 10 alerts per operation per hour
+
+  # Retention policy
+  metrics_retention_days: 90          # Keep detailed metrics for 90 days
+  alerts_retention_days: 365          # Keep alert history for 1 year
+  baseline_calculation_days: 30       # Default baseline window (30 days of history)
+  baseline_cache_ttl_minutes: 5       # Cache baseline calculations for 5 minutes
+
+  # Performance targets for monitoring service itself
+  metric_recording_overhead_ms: 10    # Recording should add <10ms overhead
+  baseline_calculation_target_ms: 5000 # Calculation should complete in <5s
+  sla_check_target_ms: 50             # SLA checks should complete in <50ms
+
+# Alerting thresholds
+alerting:
+  # SLA violation alert conditions
+  violation_alert:
+    enabled: true
+    level: warning                    # Alert level for SLA violations
+    threshold: 1                       # Alert on every violation
+
+  # Degradation alert conditions
+  degradation_alert:
+    enabled: true
+    level: warning                    # Alert level for degradation
+    threshold: 1.2                    # Alert if >20% degradation
+
+  # Critical threshold alerts
+  critical_alert:
+    enabled: true
+    level: critical                   # Alert level for critical threshold
+    threshold: 1.5                    # Alert if >50% degradation
+
+# Notification channels
+notifications:
+  # Email notifications for critical alerts
+  email:
+    enabled: true
+    critical_only: false
+    recipients: []                    # Configure in environment or secrets
+
+  # Slack notifications for performance issues
+  slack:
+    enabled: true
+    critical_only: true
+    channel: '#performance-alerts'
+    webhook_url: "${SLACK_WEBHOOK_PERFORMANCE}"  # Set via environment variable
+
+  # PagerDuty for critical incidents
+  pagerduty:
+    enabled: false
+    critical_only: true
+    api_key: "${PAGERDUTY_API_KEY}"   # Set via environment variable

package/docs/CFN_LOOP_CLI_MODE.md

@@ -0,0 +1,134 @@
+# CFN Loop CLI Mode Reference
+
+**Purpose:** Detailed documentation for CLI mode execution of CFN Loops.
+
+---
+
+## Overview
+
+CLI Mode is the production-default execution method for CFN Loops, optimized for cost and provider routing.
+
+**Command:** `/cfn-loop-cli "Task description" --mode=standard --provider kimi`
+
+**Best for:** Production workflows, provider routing, cost-sensitive work.
+
+---
+
+## Execution Flow
+
+### Slash Command Execution Rules
+
+1. Expand slash command
+2. Immediately execute coordinator spawn via Bash tool using the exact command
+3. Do not merely show commands; run them
+4. Inform user after spawn with task ID
+
+**Anti-patterns:**
+- Pausing to ask what next
+- Manual Task() spawning for CLI workflows
+- Skipping execution
+
+### CLI Mode Execution Steps
+
+1. **Expand & Validate:** Parse slash command, validate required parameters (mode, optional provider)
+2. **Spawn Coordinator:** Execute orchestration script; confirm task ID
+3. **Loop 3 Implementation:** Agents implement and run tests; orchestration monitors via Redis
+4. **Gate Check:** Compare pass rate to mode threshold; if failing, iterate Loop 3
+5. **Loop 2 Validation:** If gate passes, validators review and score
+6. **Product Owner Decision:** PROCEED/ITERATE/ABORT; orchestrator enforces
+7. **Report & Cleanup:** Final status, code paths, test results; stop agents cleanly
+
+---
+
+## Provider Routing
+
+### Enable Custom Routing
+
+Set `CFN_CUSTOM_ROUTING=true` in `.env`.
+
+### Provider Options
+
+| Provider | Use Case | Notes |
+|----------|----------|-------|
+| `zai` | Cost-sensitive | Default when custom routing enabled |
+| `kimi` | Balanced quality/cost | Good general choice |
+| `openrouter` | Broad access | Multiple models available |
+| `max` / `anthropic` | Premium quality | Highest safety/quality |
+| `gemini` | Google ecosystem | |
+| `xai` | Grok-style responses | |
+
+### Provider Selection
+
+- **Cost sensitive:** `zai` or low-tier `openrouter`
+- **Balanced:** `kimi`
+- **Quality critical:** `max` or `anthropic`
+- **Google tools:** `gemini`
+- **Mixed providers:** Set per-agent profile; otherwise inherit main chat provider
+
+### Example Flow
+
+```bash
+/switch-api kimi
+/cfn-loop-cli "Implement feature" --provider kimi
+```
+
+**Full guide:** `docs/CUSTOM_PROVIDER_ROUTING.md`
+
+---
+
+## Mode Thresholds
+
+### Test Gate Thresholds
+
+| Mode | Gate Pass Rate | Consensus | Max Iterations | Validators |
+|------|----------------|-----------|----------------|------------|
+| MVP | >= 0.70 | >= 0.80 | 5 | 2 |
+| Standard | >= 0.95 | >= 0.90 | 10 | 3-5 |
+| Enterprise | >= 0.98 | >= 0.95 | 15 | 5-7 |
+
+### Mode Selection
+
+- **MVP:** Fast prototyping, demos, non-critical work
+- **Standard:** Production default, most features
+- **Enterprise:** Compliance-sensitive, security-critical work
+
+---
+
+## Redis Coordination
+
+CLI mode uses Redis BLPOP for agent coordination:
+
+- Agents signal completion via Redis
+- Orchestrator monitors progress via polling
+- Context validation and metadata tracking
+- Health monitoring for stuck agents
+
+**Key patterns:** `.claude/skills/cfn-coordination/SKILL.md`
+
+---
+
+## Deprecated Patterns
+
+- Manual `Task()` spawning for CLI workflows
+- Ad-hoc file coordination (use Redis protocols)
+- Host-side iteration scripts (use self-contained coordinator)
+
+---
+
+## Quick Reference
+
+```bash
+# Standard CLI mode execution
+/cfn-loop-cli "Implement feature X" --mode=standard
+
+# With provider routing
+/cfn-loop-cli "Fix bug Y" --mode=standard --provider kimi
+
+# Enterprise mode for compliance
+/cfn-loop-cli "Security audit" --mode=enterprise --provider anthropic
+```
+
+**See also:**
+- Root `CLAUDE.md` for Task Mode (debugging/learning)
+- `docs/CFN_LOOP_ARCHITECTURE.md` for architecture details
+- `.claude/agents/custom/cfn-loops-cli-expert.md` for CLI expert agent

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "claude-flow-novice",
-  "version": "2.18.23",
+  "version": "2.18.25",
   "description": "Claude Flow Novice - Advanced orchestration platform for multi-agent AI workflows with CFN Loop architecture\n\nIncludes Local RuVector Accelerator and all CFN skills for complete functionality.",
   "main": "index.js",
   "type": "module",