odd-flow 1.0.0

package/.claude/skills/worker-benchmarks/SKILL.md

@@ -0,0 +1,129 @@
+---
+name: worker-benchmarks
+description: Run comprehensive worker system benchmarks and performance analysis
+user-invocable: true
+---
+
+# Worker Benchmarks Skill
+
+Run comprehensive performance benchmarks for the agentic-flow worker system.
+
+## Quick Start
+
+```bash
+# Run full benchmark suite
+npx agentic-flow workers benchmark
+
+# Run specific benchmark
+npx agentic-flow workers benchmark --type trigger-detection
+npx agentic-flow workers benchmark --type registry
+npx agentic-flow workers benchmark --type agent-selection
+npx agentic-flow workers benchmark --type concurrent
+```
+
+## Benchmark Types
+
+### 1. Trigger Detection (`trigger-detection`)
+Tests keyword detection speed across 12 worker triggers.
+- **Target**: p95 < 5ms
+- **Iterations**: 1000
+- **Metrics**: latency, throughput, histogram
+
+### 2. Worker Registry (`registry`)
+Tests CRUD operations on worker entries.
+- **Target**: p95 < 10ms
+- **Iterations**: 500 creates, gets, updates
+- **Metrics**: per-operation latency breakdown
+
+### 3. Agent Selection (`agent-selection`)
+Tests performance-based agent selection.
+- **Target**: p95 < 1ms
+- **Iterations**: 1000
+- **Metrics**: selection confidence, agent scores
+
+### 4. Model Cache (`cache`)
+Tests model caching performance.
+- **Target**: p95 < 0.5ms
+- **Metrics**: hit rate, cache size, eviction stats
+
+### 5. Concurrent Workers (`concurrent`)
+Tests parallel worker creation and updates.
+- **Target**: < 1000ms for 10 workers
+- **Metrics**: per-worker latency, memory usage
+
+### 6. Memory Key Generation (`memory-keys`)
+Tests memory pattern key generation.
+- **Target**: p95 < 0.1ms
+- **Iterations**: 5000
+- **Metrics**: unique patterns, throughput
+
+## Output Format
+
+```
+═══════════════════════════════════════════════════════════
+📈 BENCHMARK RESULTS
+═══════════════════════════════════════════════════════════
+
+✅ Trigger Detection
+   Operation: detect
+   Count: 1,000
+   Avg: 0.045ms | p95: 0.120ms (target: 5ms)
+   Throughput: 22,222 ops/s
+   Memory Δ: 0.12MB
+
+✅ Worker Registry
+   Operation: crud
+   Count: 1,500
+   Avg: 1.234ms | p95: 3.456ms (target: 10ms)
+   Throughput: 810 ops/s
+   Memory Δ: 2.34MB
+
+───────────────────────────────────────────────────────────
+📊 SUMMARY
+───────────────────────────────────────────────────────────
+Total Tests: 6
+Passed: 6 | Failed: 0
+Avg Latency: 0.567ms
+Total Duration: 2345ms
+Peak Memory: 8.90MB
+═══════════════════════════════════════════════════════════
+```
+
+## Integration with Settings
+
+Benchmark thresholds are configured in `.claude/settings.json`:
+
+```json
+{
+  "performance": {
+    "benchmarkThresholds": {
+      "triggerDetection": { "p95Ms": 5 },
+      "workerRegistry": { "p95Ms": 10 },
+      "agentSelection": { "p95Ms": 1 },
+      "memoryKeyGeneration": { "p95Ms": 0.1 },
+      "concurrentWorkers": { "totalMs": 1000 }
+    }
+  }
+}
+```
+
+## Programmatic Usage
+
+```typescript
+import { workerBenchmarks, runBenchmarks } from 'agentic-flow/workers/worker-benchmarks';
+
+// Run full suite
+const suite = await runBenchmarks();
+console.log(suite.summary);
+
+// Run individual benchmarks
+const triggerResult = await workerBenchmarks.benchmarkTriggerDetection(1000);
+const registryResult = await workerBenchmarks.benchmarkRegistryOperations(500);
+```
+
+## Performance Optimization Tips
+
+1. **Model Cache**: Enable with `CLAUDE_FLOW_MODEL_CACHE_MB=512`
+2. **Parallel Workers**: Enable with `CLAUDE_FLOW_WORKER_PARALLEL=true`
+3. **Warning Suppression**: Enable with `CLAUDE_FLOW_SUPPRESS_WARNINGS=true`
+4. **SQLite WAL Mode**: Automatic for better concurrent performance

package/.claude/skills/worker-integration/SKILL.md

@@ -0,0 +1,147 @@
+---
+name: worker-integration
+description: Worker-Agent integration for intelligent task dispatch and performance tracking
+user-invocable: true
+---
+
+# Worker-Agent Integration Skill
+
+Intelligent coordination between background workers and specialized agents.
+
+## Quick Start
+
+```bash
+# View agent recommendations for a trigger
+npx agentic-flow workers agents ultralearn
+npx agentic-flow workers agents optimize
+
+# View performance metrics
+npx agentic-flow workers metrics
+
+# View integration stats
+npx agentic-flow workers stats --integration
+```
+
+## Agent Mappings
+
+Workers automatically dispatch to optimal agents based on trigger type:
+
+| Trigger | Primary Agents | Fallback | Pipeline Phases |
+|---------|---------------|----------|-----------------|
+| `ultralearn` | researcher, coder | planner | discovery → patterns → vectorization → summary |
+| `optimize` | performance-analyzer, coder | researcher | static-analysis → performance → patterns |
+| `audit` | security-analyst, tester | reviewer | security → secrets → vulnerability-scan |
+| `benchmark` | performance-analyzer | coder, tester | performance → metrics → report |
+| `testgaps` | tester | coder | discovery → coverage → gaps |
+| `document` | documenter, researcher | coder | api-discovery → patterns → indexing |
+| `deepdive` | researcher, security-analyst | coder | call-graph → deps → trace |
+| `refactor` | coder, reviewer | researcher | complexity → smells → patterns |
+
+## Performance-Based Selection
+
+The system learns from execution history to improve agent selection:
+
+```typescript
+// Agent selection considers:
+// 1. Quality score (0-1)
+// 2. Success rate
+// 3. Average latency
+// 4. Execution count
+
+const { agent, confidence, reasoning } = selectBestAgent('optimize');
+// agent: "performance-analyzer"
+// confidence: 0.87
+// reasoning: "Selected based on 45 executions with 94.2% success"
+```
+
+## Memory Key Patterns
+
+Workers store results using consistent patterns:
+
+```
+{trigger}/{topic}/{phase}
+
+Examples:
+- ultralearn/auth-module/analysis
+- optimize/database/performance
+- audit/payment/vulnerabilities
+- benchmark/api/metrics
+```
+
+## Benchmark Thresholds
+
+Agents are monitored against performance thresholds:
+
+```json
+{
+  "researcher": {
+    "p95_latency": "<500ms",
+    "memory_mb": "<256MB"
+  },
+  "coder": {
+    "p95_latency": "<300ms",
+    "quality_score": ">0.85"
+  },
+  "security-analyst": {
+    "scan_coverage": ">95%",
+    "p95_latency": "<1000ms"
+  }
+}
+```
+
+## Feedback Loop
+
+Workers provide feedback for continuous improvement:
+
+```typescript
+import { workerAgentIntegration } from 'agentic-flow/workers/worker-agent-integration';
+
+// Record execution feedback
+workerAgentIntegration.recordFeedback(
+  'optimize',           // trigger
+  'coder',              // agent
+  true,                 // success
+  245,                  // latency ms
+  0.92                  // quality score
+);
+
+// Check compliance
+const { compliant, violations } = workerAgentIntegration.checkBenchmarkCompliance('coder');
+```
+
+## Integration Statistics
+
+```bash
+$ npx agentic-flow workers stats --integration
+
+Worker-Agent Integration Stats
+══════════════════════════════
+Total Agents:       6
+Tracked Agents:     4
+Total Feedback:     156
+Avg Quality Score:  0.89
+
+Model Cache Stats
+─────────────────
+Hits:     1,234
+Misses:   45
+Hit Rate: 96.5%
+```
+
+## Configuration
+
+Enable integration features in `.claude/settings.json`:
+
+```json
+{
+  "workers": {
+    "enabled": true,
+    "parallel": true,
+    "memoryDepositEnabled": true,
+    "agentMappings": {
+      "ultralearn": ["researcher", "coder"],
+      "optimize": ["performance-analyzer", "coder"]
+    }
+  }
+}
+```

package/.claude/statusline-command.sh

@@ -0,0 +1,176 @@
+
+#!/bin/bash
+
+# Read JSON input from stdin
+INPUT=$(cat)
+MODEL=$(echo "$INPUT" | jq -r '.model.display_name // "Claude"')
+CWD=$(echo "$INPUT" | jq -r '.workspace.current_dir // .cwd')
+DIR=$(basename "$CWD")
+
+# Replace claude-code-flow with branded name
+if [ "$DIR" = "claude-code-flow" ]; then
+  DIR="🌊 Claude Flow"
+fi
+
+# Get git branch
+BRANCH=$(cd "$CWD" 2>/dev/null && git branch --show-current 2>/dev/null)
+
+# Start building statusline
+printf "\033[1m$MODEL\033[0m in \033[36m$DIR\033[0m"
+[ -n "$BRANCH" ] && printf " on \033[33m⎇ $BRANCH\033[0m"
+
+# Claude-Flow integration
+FLOW_DIR="$CWD/.claude-flow"
+
+if [ -d "$FLOW_DIR" ]; then
+  printf " │"
+
+  # 1. Swarm Configuration & Topology
+  if [ -f "$FLOW_DIR/swarm-config.json" ]; then
+    STRATEGY=$(jq -r '.defaultStrategy // empty' "$FLOW_DIR/swarm-config.json" 2>/dev/null)
+    if [ -n "$STRATEGY" ]; then
+      # Map strategy to topology icon
+      case "$STRATEGY" in
+        "balanced") TOPO_ICON="⚡mesh" ;;
+        "conservative") TOPO_ICON="⚡hier" ;;
+        "aggressive") TOPO_ICON="⚡ring" ;;
+        *) TOPO_ICON="⚡$STRATEGY" ;;
+      esac
+      printf " \033[35m$TOPO_ICON\033[0m"
+
+      # Count agent profiles as "configured agents"
+      AGENT_COUNT=$(jq -r '.agentProfiles | length' "$FLOW_DIR/swarm-config.json" 2>/dev/null)
+      if [ -n "$AGENT_COUNT" ] && [ "$AGENT_COUNT" != "null" ] && [ "$AGENT_COUNT" -gt 0 ]; then
+        printf "  \033[35m🤖 $AGENT_COUNT\033[0m"
+      fi
+    fi
+  fi
+
+  # 2. Real-time System Metrics
+  if [ -f "$FLOW_DIR/metrics/system-metrics.json" ]; then
+    # Get latest metrics (last entry in array)
+    LATEST=$(jq -r '.[-1]' "$FLOW_DIR/metrics/system-metrics.json" 2>/dev/null)
+
+    if [ -n "$LATEST" ] && [ "$LATEST" != "null" ]; then
+      # Memory usage
+      MEM_PERCENT=$(echo "$LATEST" | jq -r '.memoryUsagePercent // 0' | awk '{printf "%.0f", $1}')
+      if [ -n "$MEM_PERCENT" ] && [ "$MEM_PERCENT" != "null" ]; then
+        # Color-coded memory (green <60%, yellow 60-80%, red >80%)
+        if [ "$MEM_PERCENT" -lt 60 ]; then
+          MEM_COLOR="\033[32m"  # Green
+        elif [ "$MEM_PERCENT" -lt 80 ]; then
+          MEM_COLOR="\033[33m"  # Yellow
+        else
+          MEM_COLOR="\033[31m"  # Red
+        fi
+        printf "  ${MEM_COLOR}💾 ${MEM_PERCENT}%\033[0m"
+      fi
+
+      # CPU load
+      CPU_LOAD=$(echo "$LATEST" | jq -r '.cpuLoad // 0' | awk '{printf "%.0f", $1 * 100}')
+      if [ -n "$CPU_LOAD" ] && [ "$CPU_LOAD" != "null" ]; then
+        # Color-coded CPU (green <50%, yellow 50-75%, red >75%)
+        if [ "$CPU_LOAD" -lt 50 ]; then
+          CPU_COLOR="\033[32m"  # Green
+        elif [ "$CPU_LOAD" -lt 75 ]; then
+          CPU_COLOR="\033[33m"  # Yellow
+        else
+          CPU_COLOR="\033[31m"  # Red
+        fi
+        printf "  ${CPU_COLOR}⚙ ${CPU_LOAD}%\033[0m"
+      fi
+    fi
+  fi
+
+  # 3. Session State
+  if [ -f "$FLOW_DIR/session-state.json" ]; then
+    SESSION_ID=$(jq -r '.sessionId // empty' "$FLOW_DIR/session-state.json" 2>/dev/null)
+    ACTIVE=$(jq -r '.active // false' "$FLOW_DIR/session-state.json" 2>/dev/null)
+
+    if [ "$ACTIVE" = "true" ] && [ -n "$SESSION_ID" ]; then
+      # Show abbreviated session ID
+      SHORT_ID=$(echo "$SESSION_ID" | cut -d'-' -f1)
+      printf "  \033[34m🔄 $SHORT_ID\033[0m"
+    fi
+  fi
+
+  # 4. Performance Metrics from task-metrics.json
+  if [ -f "$FLOW_DIR/metrics/task-metrics.json" ]; then
+    # Parse task metrics for success rate, avg time, and streak
+    METRICS=$(jq -r '
+      # Calculate metrics
+      (map(select(.success == true)) | length) as $successful |
+      (length) as $total |
+      (if $total > 0 then ($successful / $total * 100) else 0 end) as $success_rate |
+      (map(.duration // 0) | add / length) as $avg_duration |
+      # Calculate streak (consecutive successes from end)
+      (reverse |
+        reduce .[] as $task (0;
+          if $task.success == true then . + 1 else 0 end
+        )
+      ) as $streak |
+      {
+        success_rate: $success_rate,
+        avg_duration: $avg_duration,
+        streak: $streak,
+        total: $total
+      } | @json
+    ' "$FLOW_DIR/metrics/task-metrics.json" 2>/dev/null)
+
+    if [ -n "$METRICS" ] && [ "$METRICS" != "null" ]; then
+      # Success Rate
+      SUCCESS_RATE=$(echo "$METRICS" | jq -r '.success_rate // 0' | awk '{printf "%.0f", $1}')
+      TOTAL_TASKS=$(echo "$METRICS" | jq -r '.total // 0')
+
+      if [ -n "$SUCCESS_RATE" ] && [ "$TOTAL_TASKS" -gt 0 ]; then
+        # Color-code: Green (>80%), Yellow (60-80%), Red (<60%)
+        if [ "$SUCCESS_RATE" -gt 80 ]; then
+          SUCCESS_COLOR="\033[32m"  # Green
+        elif [ "$SUCCESS_RATE" -ge 60 ]; then
+          SUCCESS_COLOR="\033[33m"  # Yellow
+        else
+          SUCCESS_COLOR="\033[31m"  # Red
+        fi
+        printf "  ${SUCCESS_COLOR}🎯 ${SUCCESS_RATE}%\033[0m"
+      fi
+
+      # Average Time
+      AVG_TIME=$(echo "$METRICS" | jq -r '.avg_duration // 0')
+      if [ -n "$AVG_TIME" ] && [ "$TOTAL_TASKS" -gt 0 ]; then
+        # Format smartly: seconds, minutes, or hours
+        if [ $(echo "$AVG_TIME < 60" | bc -l 2>/dev/null || echo 0) -eq 1 ]; then
+          TIME_STR=$(echo "$AVG_TIME" | awk '{printf "%.1fs", $1}')
+        elif [ $(echo "$AVG_TIME < 3600" | bc -l 2>/dev/null || echo 0) -eq 1 ]; then
+          TIME_STR=$(echo "$AVG_TIME" | awk '{printf "%.1fm", $1/60}')
+        else
+          TIME_STR=$(echo "$AVG_TIME" | awk '{printf "%.1fh", $1/3600}')
+        fi
+        printf "  \033[36m⏱️  $TIME_STR\033[0m"
+      fi
+
+      # Streak (only show if > 0)
+      STREAK=$(echo "$METRICS" | jq -r '.streak // 0')
+      if [ -n "$STREAK" ] && [ "$STREAK" -gt 0 ]; then
+        printf "  \033[91m🔥 $STREAK\033[0m"
+      fi
+    fi
+  fi
+
+  # 5. Active Tasks (check for task files)
+  if [ -d "$FLOW_DIR/tasks" ]; then
+    TASK_COUNT=$(find "$FLOW_DIR/tasks" -name "*.json" -type f 2>/dev/null | wc -l)
+    if [ "$TASK_COUNT" -gt 0 ]; then
+      printf "  \033[36m📋 $TASK_COUNT\033[0m"
+    fi
+  fi
+
+  # 6. Check for hooks activity
+  if [ -f "$FLOW_DIR/hooks-state.json" ]; then
+    HOOKS_ACTIVE=$(jq -r '.enabled // false' "$FLOW_DIR/hooks-state.json" 2>/dev/null)
+    if [ "$HOOKS_ACTIVE" = "true" ]; then
+      printf " \033[35m🔗\033[0m"
+    fi
+  fi
+fi
+
+echo

package/.claude/statusline.mjs

@@ -0,0 +1,109 @@
+/**
+ * Agentic Flow Statusline for Claude Code
+ * Shows model, tokens, cost, swarm status, and memory usage
+ */
+
+import { execSync } from 'child_process';
+
+// Cache for expensive operations
+let lastSwarmCheck = 0;
+let cachedSwarmStatus = null;
+const CACHE_TTL = 5000; // 5 seconds
+
+/**
+ * Get swarm status (cached)
+ */
+function getSwarmStatus() {
+  const now = Date.now();
+  if (cachedSwarmStatus && (now - lastSwarmCheck) < CACHE_TTL) {
+    return cachedSwarmStatus;
+  }
+
+  try {
+    const result = execSync('npx agentic-flow@alpha mcp status 2>/dev/null || echo "idle"', {
+      encoding: 'utf-8',
+      timeout: 2000
+    }).trim();
+
+    cachedSwarmStatus = result.includes('running') ? '🐝' : '⚡';
+    lastSwarmCheck = now;
+    return cachedSwarmStatus;
+  } catch {
+    cachedSwarmStatus = '⚡';
+    lastSwarmCheck = now;
+    return cachedSwarmStatus;
+  }
+}
+
+/**
+ * Format token count
+ */
+function formatTokens(tokens) {
+  if (tokens >= 1000000) {
+    return `${(tokens / 1000000).toFixed(1)}M`;
+  }
+  if (tokens >= 1000) {
+    return `${(tokens / 1000).toFixed(1)}K`;
+  }
+  return String(tokens);
+}
+
+/**
+ * Format cost
+ */
+function formatCost(cost) {
+  if (cost >= 1) {
+    return `$${cost.toFixed(2)}`;
+  }
+  return `$${cost.toFixed(4)}`;
+}
+
+/**
+ * Main statusline export
+ */
+export default function statusline(context) {
+  const parts = [];
+
+  // Agentic Flow indicator
+  parts.push('🤖');
+
+  // Model name (shortened)
+  if (context.model) {
+    const model = context.model
+      .replace('claude-', '')
+      .replace('-20250514', '')
+      .replace('sonnet-4', 'S4')
+      .replace('opus-4', 'O4')
+      .replace('haiku-3.5', 'H3.5');
+    parts.push(model);
+  }
+
+  // Token usage
+  if (context.inputTokens !== undefined || context.outputTokens !== undefined) {
+    const input = formatTokens(context.inputTokens || 0);
+    const output = formatTokens(context.outputTokens || 0);
+    parts.push(`↑${input} ↓${output}`);
+  }
+
+  // Cost
+  if (context.totalCost !== undefined && context.totalCost > 0) {
+    parts.push(formatCost(context.totalCost));
+  }
+
+  // Swarm/MCP status indicator
+  parts.push(getSwarmStatus());
+
+  // Session time
+  if (context.sessionStartTime) {
+    const elapsed = Math.floor((Date.now() - context.sessionStartTime) / 1000);
+    const mins = Math.floor(elapsed / 60);
+    const secs = elapsed % 60;
+    if (mins > 0) {
+      parts.push(`${mins}m${secs}s`);
+    } else {
+      parts.push(`${secs}s`);
+    }
+  }
+
+  return parts.join(' │ ');
+}