claude-flow-novice 2.4.0 → 2.4.2

package/.claude/agents/core-agents/coordinator-hybrid.md

@@ -35,7 +35,7 @@ lifecycle:
 
 ```bash
 # Spawn workers with explicit typed agents
-node src/cli/hybrid-routing/spawn-workers.js \
+npx claude-flow-spawn \
   "Implement authentication system" \
   --agents=coder,security-specialist,coder \
   --provider zai --redis-channel swarm:auth
@@ -111,7 +111,7 @@ const tasks = decomposePhase(phaseObjective);
 const agentTypes = tasks.map(t => t.agentType).join(',');
 
 await Bash(`
-  node src/cli/hybrid-routing/spawn-workers.js
+  npx claude-flow-spawn
   "${taskDescription}"
   --agents=${agentTypes}
   --provider zai

package/.claude/agents/core-agents/coordinator.md

@@ -63,7 +63,7 @@ You are a senior project management and orchestration expert specializing in com
 
 ```bash
 # ✅ CORRECT: Production CLI spawning
-node src/cli/hybrid-routing/spawn-workers.js \
+npx claude-flow-spawn \
   "Remove forbidden patterns from /readme docs" \
   --agents=coder,coder,coder \
   --provider zai --redis-channel swarm:doc-cleanup
@@ -85,7 +85,7 @@ Remove forbidden patterns from documentation:
 `;
 
 // 3. Delegate via CLI
-await Bash(`node src/cli/hybrid-routing/spawn-workers.js "${taskDescription}" --max-agents 3 --provider zai`);
+await Bash(`npx claude-flow-spawn "${taskDescription}" --max-agents 3 --provider zai`);
 
 // 4. Monitor via Redis
 const results = await monitorRedisCompletions("swarm:*:complete", 3);

package/.claude/agents/examples/blocking-coordinator-example.md

@@ -663,10 +663,10 @@ See `scripts/validate-agent-hooks.js` for hook validation:
 
 ```bash
 # Validate all agent profiles
-node scripts/validate-agent-hooks.js --all
+npx claude-flow-validate-hooks --all
 
 # Validate specific profile
-node scripts/validate-agent-hooks.js .claude/agents/examples/blocking-coordinator-example.md
+npx claude-flow-validate-hooks .claude/agents/examples/blocking-coordinator-example.md
 ```
 
 ## Debugging Hooks

package/.claude/agents-ignore/cfn-coordinator-enterprise.md

@@ -105,13 +105,13 @@ Each phase follows the complete Loop 1 pattern:
 
 ```bash
 # Enterprise worker spawning with comprehensive validation (REQUIRED: --agents flag with explicit types)
-node src/cli/hybrid-routing/spawn-workers.js \
+npx claude-flow-spawn \
   "Implement [feature] for Enterprise: production-ready, security-hardened, compliance-validated" \
   --agents=analyst,architect,coder,coder,security-specialist,tester,reviewer,compliance-specialist \
   --provider zai --redis-channel swarm:enterprise-phase
 
 # Mission-critical spawning with security focus
-node src/cli/hybrid-routing/spawn-workers.js \
+npx claude-flow-spawn \
   "Build Enterprise version of [component] with zero-defect tolerance, compliance validation" \
   --agents=analyst,coder,coder,security-specialist,tester,reviewer \
   --provider zai --redis-channel swarm:enterprise-phase \

package/.claude/agents-ignore/cfn-coordinator-mvp.md

@@ -101,13 +101,13 @@ Each phase follows the complete Loop 1 pattern:
 
 ```bash
 # Basic MVP worker spawning (REQUIRED: --agents flag with explicit types)
-node src/cli/hybrid-routing/spawn-workers.js \
+npx claude-flow-spawn \
   "Implement [feature] for MVP: rapid development focus on core functionality" \
   --agents=coder,coder,tester \
   --provider zai --redis-channel swarm:mvp-phase
 
 # Cost-optimized spawning (MVP priority)
-node src/cli/hybrid-routing/spawn-workers.js \
+npx claude-flow-spawn \
   "Build MVP version of [component] with essential features only" \
   --agents=coder,coder \
   --provider zai --redis-channel swarm:mvp-phase \

package/.claude/agents-ignore/cfn-coordinator-standard.md

@@ -101,13 +101,13 @@ Each phase follows the complete Loop 1 pattern:
 
 ```bash
 # Standard worker spawning with comprehensive testing (REQUIRED: --agents flag with explicit types)
-node src/cli/hybrid-routing/spawn-workers.js \
+npx claude-flow-spawn \
   "Implement [feature] for Standard: comprehensive testing, edge cases, documentation" \
   --agents=analyst,coder,coder,tester,reviewer \
   --provider zai --redis-channel swarm:standard-phase
 
 # Quality-focused spawning
-node src/cli/hybrid-routing/spawn-workers.js \
+npx claude-flow-spawn \
   "Build Standard version of [component] with full test suite and documentation" \
   --agents=coder,coder,tester,reviewer \
   --provider zai --redis-channel swarm:standard-phase \

package/.claude/cfn-mode-patterns.md

@@ -53,7 +53,7 @@ swarm:cfn:mvp:${PHASE_ID}:loop3:complete
 
 **Worker Spawn:**
 ```bash
-node src/cli/hybrid-routing/spawn-workers.js \
+npx claude-flow-spawn \
   "Implement [feature] for MVP - core functionality only" \
   --agents=coder,tester \
   --topology=sequential \
@@ -86,7 +86,7 @@ swarm:cfn:standard:${PHASE_ID}:loop3:complete
 
 **Worker Spawn:**
 ```bash
-node src/cli/hybrid-routing/spawn-workers.js \
+npx claude-flow-spawn \
   "Implement [feature] with balanced quality and speed" \
   --agents=architect,coder,coder,tester \
   --topology=collaborative \
@@ -120,7 +120,7 @@ swarm:cfn:enterprise:${PHASE_ID}:loop3:complete
 
 **Worker Spawn:**
 ```bash
-node src/cli/hybrid-routing/spawn-workers.js \
+npx claude-flow-spawn \
   "Implement [feature] with enterprise quality standards" \
   --agents=architect,architect,coder,coder,coder,tester,security-specialist,perf-analyzer \
   --topology=release-gate \
@@ -157,7 +157,7 @@ swarm:cfn:mvp:${PHASE_ID}:loop2:complete
 
 **Validator Spawn:**
 ```bash
-node src/cli/hybrid-routing/spawn-workers.js \
+npx claude-flow-spawn \
   "Validate MVP implementation - focus on core functionality" \
   --agents=code-quality-validator,security-specialist \
   --topology=sequential \
@@ -192,7 +192,7 @@ swarm:cfn:standard:${PHASE_ID}:loop2:complete
 
 **Validator Spawn:**
 ```bash
-node src/cli/hybrid-routing/spawn-workers.js \
+npx claude-flow-spawn \
   "Validate standard implementation - comprehensive review" \
   --agents=code-quality-validator,security-specialist,perf-analyzer,interaction-tester \
   --topology=collaborative \
@@ -227,7 +227,7 @@ swarm:cfn:enterprise:${PHASE_ID}:loop2:complete
 
 **Validator Spawn:**
 ```bash
-node src/cli/hybrid-routing/spawn-workers.js \
+npx claude-flow-spawn \
   "Validate enterprise implementation - full compliance audit" \
   --agents=code-quality-validator,security-specialist,perf-analyzer,interaction-tester,compliance-auditor \
   --topology=release-gate \
@@ -455,7 +455,7 @@ Total: $4.00-$6.50 per phase
 /cfn-loop "Add user registration endpoint" --mode=mvp
 
 # Coordinator spawns workers
-node src/cli/hybrid-routing/spawn-workers.js \
+npx claude-flow-spawn \
   "Implement user registration endpoint - core functionality only" \
   --agents=coder,tester \
   --topology=sequential \
@@ -473,7 +473,7 @@ node src/cli/hybrid-routing/spawn-workers.js \
 /cfn-loop "Implement payment processing system" --mode=standard
 
 # Coordinator spawns workers
-node src/cli/hybrid-routing/spawn-workers.js \
+npx claude-flow-spawn \
   "Implement payment processing system with balanced quality and speed" \
   --agents=architect,coder,coder,tester \
   --topology=collaborative \
@@ -491,7 +491,7 @@ node src/cli/hybrid-routing/spawn-workers.js \
 /cfn-loop "Deploy HIPAA-compliant patient data API" --mode=enterprise
 
 # Coordinator spawns workers
-node src/cli/hybrid-routing/spawn-workers.js \
+npx claude-flow-spawn \
   "Implement HIPAA-compliant patient data API with enterprise quality standards" \
   --agents=architect,architect,coder,coder,coder,tester,security-specialist,perf-analyzer \
   --topology=release-gate \

package/.claude/commands/cost-savings-off.md

@@ -25,7 +25,7 @@ Disable CLI cost-savings mode to use traditional Task-tool agent spawning.
 **Execute mode toggle:**
 
 ```bash
-node scripts/toggle-cost-savings.cjs off
+npx claude-flow-cost-savings off
 ```
 
 **After disabling:**

package/.claude/commands/cost-savings-on.md

@@ -18,14 +18,14 @@ Enable cost-savings mode to use CLI-based agent spawning with spawn-workers.js f
 **Mode Details:**
 - **Coordinator**: Runs in main chat (Claude Max, $0)
 - **Workers**: Spawned via CLI with z.ai provider
-- **Spawning**: Uses `node src/cli/hybrid-routing/spawn-workers.js --agents=type1,type2 --provider zai`
+- **Spawning**: Uses `npx claude-flow-spawn --agents=type1,type2 --provider zai`
 - **Coordination**: Redis pub/sub messaging
 - **State**: SQLite persistence with ACL
 
 **Execute mode toggle:**
 
 ```bash
-node scripts/toggle-cost-savings.cjs on
+npx claude-flow-cost-savings on
 ```
 
 **After enabling:**

package/.claude/commands/cost-savings-status.md

@@ -22,7 +22,7 @@ Display current cost-savings mode status and coordinator configuration.
 **Execute status check:**
 
 ```bash
-node scripts/toggle-cost-savings.cjs status
+npx claude-flow-cost-savings status
 ```
 
 **Output includes:**

package/.claude/commands/launch-web-dashboard.md

@@ -243,7 +243,7 @@ npm run build
 /launch-web-dashboard
 
 # Spawn workers (dashboard monitors them)
-node src/cli/hybrid-routing/spawn-workers.js "Task" --max-agents 5
+npx claude-flow-spawn "Task" --max-agents 5
 ```
 
 ### With Swarm Coordination

package/.claude/commands/list-agents-rebuild.md

@@ -34,7 +34,7 @@ Regenerate `src/cli/hybrid-routing/AVAILABLE-AGENTS.md` from live agent discover
 
 ```bash
 # Regenerate agent list
-node src/cli/hybrid-routing/spawn-workers.js --agents-by-category > src/cli/hybrid-routing/AVAILABLE-AGENTS.md.tmp
+npx claude-flow-spawn --agents-by-category > src/cli/hybrid-routing/AVAILABLE-AGENTS.md.tmp
 
 # Parse and format into markdown document
 node << 'EOF'
@@ -126,9 +126,9 @@ markdown += '## Usage\n\n';
 markdown += '### CLI Commands\n\n';
 markdown += '```bash\n';
 markdown += '# List all agents (flat view)\n';
-markdown += 'node src/cli/hybrid-routing/spawn-workers.js --list-agents\n\n';
+markdown += 'npx claude-flow-spawn --list-agents\n\n';
 markdown += '# List agents by category\n';
-markdown += 'node src/cli/hybrid-routing/spawn-workers.js --agents-by-category\n\n';
+markdown += 'npx claude-flow-spawn --agents-by-category\n\n';
 markdown += '# Regenerate this documentation file\n';
 markdown += '/list-agents-rebuild\n';
 markdown += '```\n\n';
@@ -136,12 +136,12 @@ markdown += '```\n\n';
 markdown += '### Coordinator Usage\n\n';
 markdown += '```bash\n';
 markdown += '# Automatic selection (keyword-based)\n';
-markdown += 'node src/cli/hybrid-routing/spawn-workers.js "Build auth" --max-agents=3\n\n';
+markdown += 'npx claude-flow-spawn "Build auth" --max-agents=3\n\n';
 markdown += '# Coordinator override (manual agent types)\n';
-markdown += 'node src/cli/hybrid-routing/spawn-workers.js "Task" \\\n';
+markdown += 'npx claude-flow-spawn "Task" \\\n';
 markdown += '  --agents=architect,coder,tester\n\n';
 markdown += '# Full override (custom agents + subtasks)\n';
-markdown += 'node src/cli/hybrid-routing/spawn-workers.js "Task" \\\n';
+markdown += 'npx claude-flow-spawn "Task" \\\n';
 markdown += '  --agents=coder,security-specialist \\\n';
 markdown += '  --subtasks="Subtask 1|Subtask 2"\n';
 markdown += '```\n\n';

package/.claude/coordinator-feedback-pattern.md

@@ -180,7 +180,7 @@ Add feedback monitoring right after worker spawning:
 (... feedback monitor code ...)
 
 # Step 2: Spawn workers
-node src/cli/hybrid-routing/spawn-workers.js ...
+npx claude-flow-spawn ...
 
 # Step 3: Monitor workers AND feedback simultaneously
 while [ $(redis-cli llen "swarm:cfn:${MODE}:${PHASE_ID}:loop3:complete") -eq 0 ]; do

package/.claude/templates/agent-optimization-plan.md

@@ -282,7 +282,7 @@ type: coordinator
 ## Worker Spawning Pattern
 
 ```bash
-node src/cli/hybrid-routing/spawn-workers.js \
+npx claude-flow-spawn \
   "Task description" \
   --agents=analyst,architect,coder \
   --provider zai

package/SYNC_USAGE.md

@@ -20,6 +20,20 @@ npx claude-flow-sync --backup
 node node_modules/claude-flow-novice/scripts/sync-from-package.js --backup
 ```
 
+### 3. Available CLI Commands
+
+The package provides additional commands for agent coordination:
+
+```bash
+# Spawn agents via CLI (cost-optimized coordination)
+npx claude-flow-spawn "Build auth system" --agents=coder,tester --provider zai
+
+# Toggle cost-savings mode
+npx claude-flow-cost-savings on      # Enable CLI spawning
+npx claude-flow-cost-savings off     # Disable CLI spawning
+npx claude-flow-cost-savings status  # Check current mode
+```
+
 ## Sync Options
 
 ### Sync Everything (Recommended for first time)

package/package.json

@@ -1,11 +1,14 @@
 {
   "name": "claude-flow-novice",
-  "version": "2.4.0",
+  "version": "2.4.2",
   "description": "AI Agent Orchestration CLI",
   "main": "src/index.ts",
   "bin": {
     "claude-flow-novice": "./src/cli/index.ts",
-    "claude-flow-sync": "./scripts/sync-from-package.js"
+    "claude-flow-sync": "./scripts/sync-from-package.js",
+    "claude-flow-spawn": "./src/cli/hybrid-routing/spawn-workers.js",
+    "claude-flow-cost-savings": "./scripts/toggle-cost-savings.cjs",
+    "claude-flow-validate-hooks": "./scripts/validate-agent-hooks.js"
   },
   "files": [
     "src",

package/src/cli/simple-commands/init/templates/CLAUDE.md

@@ -1,5 +1,7 @@
 # Claude Flow Novice — AI Agent Orchestration
 
+**🚀 Production Status:** Redis coordination system fully deployed (Phase 7 - 2025-10-17)
+
 ---
 
 ## 1) Critical Rules (Single Source of Truth)
@@ -11,12 +13,13 @@
 * Agents communicate via Redis pub/sub with explicit dependencies (see `.claude/redis-agent-dependencies.md`)
 
 **Core Principles:**
-* Use agents for all non-trivial work (≥4 steps or multi-file/research/testing/architecture/security)
+* Use agents for all non-trivial work (≥3 steps or multi-file/research/testing/architecture/security)
 * **PRIMARY COORDINATOR: Use coordinator-hybrid for all multi-agent coordination** (cost-optimized CLI spawning with typed agents)
 * Initialize swarm before multi-agent work
 * Batch operations: spawn ALL agents (coordinator + workers) in single message
 * Run post-edit hook after every file edit
 * **REQUIRED: All CLI agent spawning must use explicit --agents flag with typed agents**
+* **Context continuity:** Redis/SQLite persistence enables unlimited continuation — never stop due to context/token concerns
 
 **Prohibited Patterns:**
 * Main chat orchestrating agents directly — spawn coordinator to handle orchestration
@@ -25,11 +28,12 @@
 * Using generic "coordinator" fallback when coordinator-hybrid available
 * Spawning agents without explicit --agents flag (must specify types from AVAILABLE-AGENTS.md)
 * Agent coordination without Redis pub/sub messaging — ALL agents must use Redis
-* Running tests inside agents — execute once; agents read results
+* Running tests inside agents — coordinator runs tests ONCE; workers read cached results from test-results.json
 * Concurrent test runs — terminate previous runs first
 * **Saving to project root — check `.artifacts/logs/post-edit-pipeline.log` after writes; move files if ROOT_WARNING**
 * Creating guides/summaries/reports unless explicitly asked
-* Asking permission to retry/advance when criteria/iterations allow. Instead relaunch agents
+* Asking permission to retry/advance when criteria/iterations allow — **relaunch agents immediately when consensus <threshold and iterations <max**
+* Stopping work due to context/token concerns — Redis/SQLite persistence handles continuation automatically
 
 **Communication:**
 * Use spartan language
@@ -121,15 +125,28 @@ If file created in root, hook returns `status: "ROOT_WARNING"` with `rootWarning
 
 ### 3.3 Safe Test Execution
 
+**Pattern: Coordinator runs tests ONCE before spawning workers**
+
 ```bash
-# Run once, save results
+# 1. Coordinator terminates any existing test runs
+pkill -f vitest; pkill -f "npm test"
+
+# 2. Coordinator runs tests once and caches results
 npm test -- --run --reporter=json > test-results.json 2>&1
-# Agents read results only
+
+# 3. Workers read cached results only (no test execution)
 cat test-results.json
-# Cleanup
+
+# 4. Cleanup after all work complete
 pkill -f vitest; pkill -f "npm test"
 ```
 
+**Rules:**
+* Coordinator executes tests before worker spawn
+* Workers ONLY read test-results.json (never run tests)
+* Single test execution prevents concurrent run conflicts
+* Cache results in test-results.json for worker consumption
+
 ### 3.4 Batching (One message = all related ops)
 
 * Spawn all agents with Task tool in one message
@@ -197,6 +214,47 @@ mv test.txt src/test.txt  # Move to suggested location
 
 **→ Pattern: `.claude/coordinator-feedback-pattern.md`**
 
+### 6.3 Dashboard Integration (Phase 5)
+
+**Real-time Dashboard:**
+- URL: http://localhost:3001 (RealtimeServer)
+- WebSocket: ws://localhost:3001/ws
+- Components: RedisCoordinationMonitor.tsx
+
+**REST API Endpoints:**
+| Endpoint | Method | Description |
+|----------|--------|-------------|
+| /api/redis/feedback | GET | Recent feedback (limit=100) |
+| /api/redis/metrics | GET | Current metrics snapshot |
+| /api/swarm/status | GET | Current swarm coordination status |
+
+**CLI Monitoring Commands:**
+```bash
+# Monitor feedback
+./scripts/monitor-swarm-redis.sh feedback
+
+# Monitor CFN Loop
+./scripts/monitor-swarm-redis.sh coordination
+
+# Realtime dashboard launch
+npx claude-flow-novice dashboard --port 3001
+```
+
+**Post-Spawn Validation:**
+```bash
+# Validate CLI agent
+node config/hooks/post-spawn-validation.js coder-1
+
+# Validate Task agent
+node config/hooks/post-spawn-validation.js task_abc123 --coordinator-id coordinator-cfn
+```
+
+**WebSocket Event Types:**
+- `swarm:coordination`
+- `agent:feedback`
+- `system:metrics`
+- `dashboard:status`
+
 ---
 
 ## 7) Commands & Setup