claude-flow-novice 2.16.0 → 2.16.1

package/claude-assets/agents/project-only-agents/npm-package-specialist.md

@@ -1,6 +1,6 @@
 ---
 name: npm-package-specialist
-description: MUST BE USED for npm package creation, publishing, and maintenance. Use PROACTIVELY for package.json configuration, versioning, dependency management. ALWAYS delegate when user asks to "create package", "publish npm", "setup module", "package configuration". Keywords - npm, package, publish, module, versioning, dependencies, registry
+description: MUST BE USED for npm package development, publishing, dependency management. Use PROACTIVELY for package configuration. Keywords - npm, package, dependencies, publishing
 tools: [Read, Write, Edit, Bash, Grep, Glob, TodoWrite]
 model: haiku
 provider: zai

package/claude-assets/cfn-extras/skills/GOOGLE_SHEETS_SKILLS_README.md

@@ -371,7 +371,7 @@ find ./.claude/cfn-extras/skills/google-sheets-* -name "*.sh" \
 
 ## Related Documentation
 
-- **CFN Loop Guide**: `.claude/commands/cfn/CFN_LOOP_TASK_MODE.md`
+- **CFN Loop Guide**: `.claude/commands/CFN_LOOP_TASK_MODE.md`
 - **Progress Tracking**: `.claude/cfn-extras/skills/google-sheets-progress/SKILL.md`
 - **Validation Rules**: `.claude/cfn-extras/skills/google-sheets-validation/SKILL.md`
 - **Formula Templates**: `.claude/cfn-extras/skills/google-sheets-formula-builder/SKILL.md`

package/claude-assets/cfn-extras/skills/google-sheets-api-coordinator/SKILL.md

@@ -269,4 +269,4 @@ Rate limit state stored in: `.claude/cfn-extras/.gs-api-quota.json`
 - **Google Sheets API**: https://developers.google.com/sheets/api
 - **Rate Limiting Guide**: https://developers.google.com/sheets/api/guides/limits
 - **Quota Documentation**: `google-sheets-validation` skill
-- **CFN Loop Guide**: `.claude/commands/cfn/CFN_LOOP_TASK_MODE.md`
+- **CFN Loop Guide**: `.claude/commands/CFN_LOOP_TASK_MODE.md`

package/claude-assets/cfn-extras/skills/google-sheets-formula-builder/SKILL.md

@@ -234,4 +234,4 @@ fi
 
 - **Google Sheets API**: https://developers.google.com/sheets/api/reference/rest
 - **Formula Validation**: `google-sheets-validation` skill
-- **CFN Loop Guide**: `.claude/commands/cfn/CFN_LOOP_TASK_MODE.md`
+- **CFN Loop Guide**: `.claude/commands/CFN_LOOP_TASK_MODE.md`

package/claude-assets/cfn-extras/skills/google-sheets-progress/SKILL.md

@@ -281,7 +281,7 @@ The skill includes comprehensive test coverage:
 
 ## References
 
-- **CFN Loop Documentation**: `.claude/commands/cfn/CFN_LOOP_TASK_MODE.md`
+- **CFN Loop Documentation**: `.claude/commands/CFN_LOOP_TASK_MODE.md`
 - **State Management Pattern**: `.claude/skills/cfn-automatic-memory-persistence/SKILL.md`
 - **Coordination Protocols**: `.claude/skills/cfn-coordination/SKILL.md`
 - **Agent Output Standards**: `docs/AGENT_OUTPUT_STANDARDS.md`

package/claude-assets/commands/CFN_LOOP_FRONTEND.md

@@ -732,7 +732,7 @@ Not generic advice - specific fixes only.`
 
 ## Related Documentation
 
-- **Task Mode Guide**: `.claude/commands/cfn/CFN_LOOP_TASK_MODE.md`
+- **Task Mode Guide**: `.claude/commands/CFN_LOOP_TASK_MODE.md`
 - **Standard CFN Loop**: `.claude/commands/cfn/cfn-loop.md`
 - **Coordinator Parameters**: `.claude/commands/cfn/CFN_COORDINATOR_PARAMETERS.md`
 

package/claude-assets/commands/cfn-loop-cli.md

@@ -1,12 +1,12 @@
 ---
 description: "Execute CFN Loop in simplified CLI mode (Main Chat coordination, provider routing)"
-argument-hint: "<task description> [--mode=mvp|standard|enterprise] [--provider=zai|kimi|anthropic|openrouter] [--model=<model>]"
+argument-hint: "<task description> [--mode=mvp|standard|enterprise] [--provider=zai|kimi|anthropic|openrouter] [--model=<model>] [--agents=N] [--threshold=0.75]"
 allowed-tools: ["Task", "TodoWrite", "Read", "Bash", "SlashCommand"]
 ---
 
-# CFN Loop CLI Mode - Simplified Main Chat Coordination
+# CFN Loop CLI Mode - Parallel Agent Coordination
 
-🚨 **NEW ARCHITECTURE:** Main Chat directly coordinates CLI agents via Redis BLPOP signaling
+🚨 **v2.0 ARCHITECTURE:** Main Chat spawns parallel CLI agents with threshold-based completion
 
 ---
 
@@ -18,6 +18,8 @@ TASK_DESCRIPTION: $ARGUMENTS (extract task, remove flags)
 MODE: Parse from --mode flag or default to "standard"
 PROVIDER: Parse from --provider flag or use Main Chat setting
 MODEL: Parse from --model flag or use provider default
+AGENTS: Parse from --agents flag or default to 4
+THRESHOLD: Parse from --threshold flag or default to 0.75 (3/4 agents)
 ```
 
 **Step 2: Set Environment Variables**
@@ -27,6 +29,7 @@ TASK_ID="cfn-cli-$(date +%s%N | tail -c 7)-${RANDOM}"
 echo "📋 Task ID: $TASK_ID"
 echo "🎯 Mode: $MODE"
 echo "🤖 Provider: $PROVIDER (from --provider or Main Chat setting)"
+echo "👥 Agents: $AGENTS (threshold: $THRESHOLD)"
 if [ -n "$MODEL" ]; then
   echo "🧠 Model: $MODEL"
 fi
@@ -53,55 +56,88 @@ fi
 echo "✅ Redis available for Main Chat coordination"
 ```
 
-**Step 4: Spawn Initial CLI Agent (Main Chat Coordination Pattern)**
+**Step 4: Spawn Parallel CLI Agents**
 ```bash
-# Determine first agent type based on task
-# This is a simplified selection - could be enhanced with task classification
-AGENT_TYPE="backend-developer"
+# Define agent types based on task complexity
+# For comprehensive tasks, spawn multiple specialized agents
+AGENT_TYPES=("backend-developer" "tester" "code-reviewer" "security-specialist")
 
-# Spawn first CLI agent with provider routing
-echo "🚀 Spawning CLI agent: $AGENT_TYPE"
+echo "🚀 Spawning $AGENTS parallel CLI agents..."
 
-npx tsx src/cli/spawn-agent-cli.ts "$AGENT_TYPE" \
-  --task-id "$TASK_ID" \
-  --mode "$MODE" \
-  ${PROVIDER:+--provider "$PROVIDER"} \
-  ${MODEL:+--model "$MODEL"} \
-  --background
+# Spawn agents in BACKGROUND (use & to allow Main Chat to continue)
+for i in $(seq 1 $AGENTS); do
+  AGENT_TYPE="${AGENT_TYPES[$((i-1)) % ${#AGENT_TYPES[@]}]}"
+  AGENT_ID="${AGENT_TYPE}-${TASK_ID}-${i}"
 
-echo "✅ CLI agent spawned with Task ID: $TASK_ID"
-```
-
-**Step 5: Wait for Agent Completion (Main Chat BLPOP Pattern)**
-```bash
-# Main Chat waits for completion signal via Redis BLPOP
-echo "⏳ Waiting for CLI agent completion..."
+  echo "  → Spawning agent $i: $AGENT_TYPE ($AGENT_ID)"
 
-SIGNAL_KEY="cfn:mainchat:signal:$TASK_ID"
-TIMEOUT_SECONDS=120
+  npx claude-flow-novice agent "$AGENT_TYPE" \
+    --task-id "$TASK_ID" \
+    --mode "$MODE" \
+    --provider "$PROVIDER" \
+    --context "$TASK_DESCRIPTION" \
+    </dev/null >/tmp/agent-${AGENT_ID}.log 2>&1 &
+done
 
-# Wait for completion signal with timeout
-COMPLETION_SIGNAL=$(timeout $TIMEOUT_SECONDS redis-cli BLPOP "$SIGNAL_KEY" $((TIMEOUT_SECONDS + 10)))
+echo "✅ All $AGENTS CLI agents spawned with Task ID: $TASK_ID"
+```
 
-if [ $? -eq 0 ] && [ -n "$COMPLETION_SIGNAL" ]; then
-  echo "✅ CLI agent completed successfully"
-  echo "📊 Completion signal received via Redis"
+**Step 5: Wait for Threshold Completion (FOREGROUND - Required for Main Chat)**
+```bash
+# CRITICAL: Run monitor in FOREGROUND so Main Chat receives completion signal
+# DO NOT use run_in_background for this monitoring loop
+
+COMPLETION_QUEUE="cfn:cli:${TASK_ID}:completion"
+REQUIRED=$(echo "$AGENTS * $THRESHOLD" | bc | cut -d. -f1)
+
+echo "⏳ Monitoring for completion (${REQUIRED}/$AGENTS agents)..."
+echo "📊 Queue: $COMPLETION_QUEUE"
+echo ""
+
+COMPLETED=0
+END_TIME=$(($(date +%s) + 300))  # 5 minute timeout
+
+while [ $(date +%s) -lt $END_TIME ] && [ $COMPLETED -lt $REQUIRED ]; do
+  QUEUE_LEN=$(redis-cli LLEN "$COMPLETION_QUEUE" 2>/dev/null || echo "0")
+
+  if [ "$QUEUE_LEN" -gt 0 ]; then
+    SIGNAL=$(redis-cli LPOP "$COMPLETION_QUEUE")
+    if [ -n "$SIGNAL" ] && [ "$SIGNAL" != "(nil)" ]; then
+      COMPLETED=$((COMPLETED + 1))
+      AGENT_ID=$(echo "$SIGNAL" | jq -r '.agentId' 2>/dev/null || echo "unknown")
+      CONFIDENCE=$(echo "$SIGNAL" | jq -r '.confidence' 2>/dev/null || echo "N/A")
+      PROVIDER=$(echo "$SIGNAL" | jq -r '.provider' 2>/dev/null || echo "N/A")
+
+      echo "✅ Agent $COMPLETED completed: $AGENT_ID"
+      echo "   Confidence: $CONFIDENCE, Provider: $PROVIDER"
+      echo ""
+
+      if [ $COMPLETED -ge $REQUIRED ]; then
+        echo "🎉 THRESHOLD MET! ($COMPLETED/$AGENTS agents)"
+        echo "✅ CFN Loop CLI task completed"
+        exit 0
+      fi
+    fi
+  fi
+
+  sleep 3
+done
+
+echo "⏰ Timeout: Only $COMPLETED/$AGENTS agents completed"
+exit 1
+```
 
-  # Parse completion signal (second line contains JSON)
-  SIGNAL_DATA=$(echo "$COMPLETION_SIGNAL" | tail -n 1)
-  echo "🔍 Agent signal: $SIGNAL_DATA"
+**Step 6: Query Agent Status (Optional - Interactive)**
+```bash
+# Main Chat can query individual agent status during execution
+# Example: npx tsx src/cli/coordination/agent-messaging.ts status --task-id "$TASK_ID" --agent-id <agent-id>
 
-  # Could spawn additional agents here based on signal content
-  # For now, we'll consider the task complete
-  echo "🎉 CFN Loop CLI task completed"
-else
-  echo "⚠️  CLI agent did not complete within timeout ($TIMEOUT_SECONDS seconds)"
-  echo "💡 Check agent logs or increase timeout if needed"
-fi
+# Or send commands to running agents:
+# npx tsx src/cli/coordination/agent-messaging.ts send --task-id "$TASK_ID" --agent-id <agent-id> --command status
 ```
 
-**Step 6: Inform User**
-Report completion status and any additional information.
+**Step 7: Inform User**
+Report completion status, which agents completed, and any additional information.
 
 ---
 
@@ -111,13 +147,55 @@ Report completion status and any additional information.
 
 ## What is CLI Mode?
 
-**NEW CLI Mode Architecture (Simplified):**
-- **Main Chat** directly spawns CLI agents with provider routing
+**v2.0 CLI Mode Architecture (Parallel + Messaging):**
+- **Main Chat** spawns multiple CLI agents in parallel
 - **CLI agents** execute tasks and send Redis completion signals
-- **Main Chat** waits via Redis BLPOP for agent completion
-- **2-layer coordination** (Main Chat → CLI agents)
+- **Main Chat** waits for threshold completion (e.g., 3/4 agents)
+- **Bidirectional messaging** - Main Chat can send commands to running agents
 - **Provider routing** via `--provider` and `--model` flags
-- **Fallback behavior** to Z.ai glm-4.6 if no provider specified
+- **Graceful degradation** - continues when threshold met, doesn't wait for stragglers
+
+## New Features (v2.0)
+
+### Parallel Agent Spawning
+- Spawn multiple agents simultaneously (default: 4)
+- Each agent works independently on the task
+- Different agent types for comprehensive coverage
+
+### Threshold-Based Completion
+- Exit when N/M agents complete (default: 75%)
+- Don't wait for slow/stuck agents
+- Configurable via `--threshold` flag
+
+### Bidirectional Messaging
+Main Chat can communicate with running agents:
+
+**Query agent status:**
+```bash
+npx tsx src/cli/coordination/agent-messaging.ts status \
+  --task-id "$TASK_ID" --agent-id <agent-id>
+```
+
+**Send commands to agents:**
+```bash
+# Request status update
+npx tsx src/cli/coordination/agent-messaging.ts send \
+  --task-id "$TASK_ID" --agent-id <agent-id> --command status
+
+# Redirect agent to new task
+npx tsx src/cli/coordination/agent-messaging.ts send \
+  --task-id "$TASK_ID" --agent-id <agent-id> --command redirect \
+  --payload '{"newTask": "Focus on security tests"}'
+
+# Abort agent
+npx tsx src/cli/coordination/agent-messaging.ts send \
+  --task-id "$TASK_ID" --agent-id <agent-id> --command abort
+
+# Pause agent
+npx tsx src/cli/coordination/agent-messaging.ts send \
+  --task-id "$TASK_ID" --agent-id <agent-id> --command pause \
+  --payload '{"seconds": 30}'
+```
 
 ## Prerequisites
 

package/claude-assets/commands/cfn-loop-frontend.md

@@ -561,7 +561,7 @@ Before running frontend CFN Loop:
 
 - Guide: `.claude/commands/cfn/CFN_LOOP_FRONTEND.md` (742 lines, complete workflow)
 - Coordinator: `.claude/agents/cfn-dev-team/coordinators/cfn-frontend-coordinator.md`
-- Task Mode: `.claude/commands/cfn/CFN_LOOP_TASK_MODE.md`
+- Task Mode: `.claude/commands/CFN_LOOP_TASK_MODE.md`
 - Standard CFN Loop: `.claude/commands/cfn/cfn-loop.md`
 
 ---

package/claude-assets/commands/cfn-loop-task.md

@@ -106,7 +106,7 @@ You must execute this CFN Loop directly using the Task() tool to spawn agents.
 Read the complete Task Mode guide for detailed workflow:
 
 ```
-Read('.claude/commands/cfn/CFN_LOOP_TASK_MODE.md')
+Read('.claude/commands/CFN_LOOP_TASK_MODE.md')
 ```
 
 **Expected output:** Complete guide with agent selection, workflow steps, helper scripts
@@ -450,7 +450,7 @@ parse-decision.sh --output "$PO_OUTPUT"
 
 ## Related Documentation
 
-- **Task Mode Guide**: `.claude/commands/cfn/CFN_LOOP_TASK_MODE.md` (complete reference)
+- **Task Mode Guide**: `.claude/commands/CFN_LOOP_TASK_MODE.md` (complete reference)
 - Coordinator Parameters: `.claude/commands/cfn/CFN_COORDINATOR_PARAMETERS.md`
 - Agent Output Standards: `docs/AGENT_OUTPUT_STANDARDS.md`
 - ACE System: `.claude/skills/cfn-ace-system/SKILL.md`

package/claude-assets/commands/deprecated/cfn-loop.md

@@ -95,7 +95,7 @@ Extract parameters from command:
 
 ```javascript
 // Read Task Mode guide for agent specialization and workflow
-const taskModeGuide = await Read('.claude/commands/cfn/CFN_LOOP_TASK_MODE.md');
+const taskModeGuide = await Read('.claude/commands/CFN_LOOP_TASK_MODE.md');
 
 // Guide provides:
 // - Agent specialization (Loop 3: implementers, Loop 2: validators, Loop 4: PO)
@@ -274,7 +274,7 @@ Main Chat does NOT spawn a coordinator. Instead, it coordinates directly followi
 
 ```javascript
 // Step 1: Read Task Mode Guide
-const guide = await Read('.claude/commands/cfn/CFN_LOOP_TASK_MODE.md');
+const guide = await Read('.claude/commands/CFN_LOOP_TASK_MODE.md');
 
 // Step 2: Analyze Task Complexity (from guide)
 const complexity = analyzeComplexity({

package/claude-assets/hooks/GIT-HOOKS-USAGE-EXAMPLES.md

@@ -0,0 +1,116 @@
+# Git Hooks: Usage Examples
+
+Real-world examples of the pre-commit credential detection system in action.
+
+## Example 1: Developer Accidentally Commits API Key
+
+Developer edits a configuration file and forgets to redact their Anthropic API key.
+
+```bash
+$ git add config.ts
+$ git commit -m "feat: add anthropic integration"
+
+Pre-Commit Hook: Scanning for credential exposure...
+
+COMMIT BLOCKED: 1 credential(s) detected
+
+CREDENTIAL DETECTED:
+   File: config.ts
+   Line: 1
+   Match: ANTHROPIC_API_KEY=[CREDENTIAL_REDACTED]
+```
+
+Resolution: Replace with placeholder, move to .env, use environment variable.
+
+## Example 2: Database Password in Connection String
+
+Hardcoded PostgreSQL password in database configuration.
+
+```bash
+$ git commit -m "chore: database configuration"
+
+COMMIT BLOCKED: 1 credential(s) detected
+
+CREDENTIAL DETECTED:
+   File: database.ts
+   Line: 4
+   Match: password: [CREDENTIAL_REDACTED]
+```
+
+Resolution: Replace with process.env.DB_PASSWORD.
+
+## Example 3: Test File with Mock Credentials (Whitelisted)
+
+Tests with legitimate test credentials that are whitelisted.
+
+```bash
+$ git add auth.test.ts
+$ git commit -m "test: add API key format validation"
+
+No credentials detected - proceeding with commit
+
+# Success! 'sk-ant-mock' and 'npm_MockTestKey'
+# are whitelisted patterns for testing
+```
+
+## Example 4: Documentation with [REDACTED] Placeholder
+
+Documentation showing API setup with redacted values.
+
+```bash
+$ git add API_SETUP.md
+$ git commit -m "docs: add API setup instructions"
+
+No credentials detected - proceeding with commit
+
+# Success! [REDACTED] is a whitelisted pattern
+```
+
+## Example 5: Multiple Files Scanned
+
+Multiple files scanned before commit.
+
+```bash
+$ git add src/auth.ts src/config.ts docs/SETUP.md tests/auth.test.ts
+$ git commit -m "feat: complete authentication setup"
+
+Pre-Commit Hook: Scanning for credential exposure...
+
+   Scanning: src/auth.ts
+   Scanning: src/config.ts
+   Scanning: docs/SETUP.md
+   Scanning: tests/auth.test.ts
+
+   Scanned: 4 files
+
+No credentials detected - proceeding with commit
+```
+
+## Example 6: Bypassing the Hook (Emergency Only)
+
+Emergency override when absolutely necessary.
+
+```bash
+$ git commit --no-verify -m "emergency: temporary workaround"
+
+# WARNING: CI/CD will still catch credentials!
+# This should only be used in true emergencies
+```
+
+## Example 7: Audit Trail Review
+
+Security team reviewing credential detection history.
+
+```bash
+$ cat .artifacts/logs/git-hooks.log
+
+2025-11-23T10:30:45Z | PRE-COMMIT BLOCKED | CREDENTIALS:1 | FILES_SCANNED:1
+2025-11-23T10:31:12Z | PRE-COMMIT SUCCESS | FILES_SCANNED:2
+2025-11-23T10:32:15Z | PRE-COMMIT SUCCESS | FILES_SCANNED:4
+```
+
+## Related Documentation
+
+- Complete Guide: `.claude/hooks/README-GIT-HOOKS.md`
+- Installation: `.claude/hooks/install-git-hooks.sh`
+- Pre-Commit Hook: `.git/hooks/pre-commit`