claude-flow-novice 2.10.6 → 2.10.8

package/.claude/commands/cfn/CFN_LOOP_TASK_MODE.md

@@ -15,6 +15,23 @@ Task Mode: Main Chat spawns coordinator and agents via Task() tool with full con
 | **Provider** | All Anthropic | CLI uses Z.ai routing |
 | **Cost** | ~$0.150/iteration | ~$0.054/iteration (64% savings) |
 | **Use Case** | Debugging, prototyping, learning | Production, cost optimization |
+| **ACE Reflection** | Optional via `--ace-reflect` flag | Always enabled |
+
+### ACE Reflection Flag
+
+```bash
+# Enable ACE reflection after each sprint (captures lessons learned)
+/cfn-loop "Task description" --spawn-mode=task --ace-reflect
+
+# Without ACE reflection (default for backwards compatibility)
+/cfn-loop "Task description" --spawn-mode=task
+```
+
+**When to use `--ace-reflect`:**
+- Long-running epics (3+ sprints) where learning accumulates
+- Complex tasks with multiple iterations
+- Teams building organizational knowledge
+- Post-mortem analysis and continuous improvement
 
 ---
 
@@ -144,9 +161,30 @@ Iterations: Loop 3: ${L3}, Loop 2: ${L2} | Decision: PROCEED
 EOF
 ```
 
+### 5. ACE Reflection (Optional - If `--ace-reflect` flag enabled)
+```bash
+# Only run if --ace-reflect flag was passed to /cfn-loop command
+if [[ "$ACE_REFLECT_ENABLED" == "true" ]]; then
+  echo "📊 Capturing ACE reflection..."
+  ./.claude/skills/cfn-ace-system/invoke-context-reflect.sh \
+    --task-id "${TASK_ID}" \
+    --sprint-id "${SPRINT_NUM}" \
+    --consensus "${CONSENSUS}" \
+    --iterations-loop3 "${L3}" \
+    --iterations-loop2 "${L2}" \
+    --deliverables "$(git diff HEAD~1 --name-only | tr '\n' ',')"
+
+  # Output: Stores reflection in SQLite with tags, confidence, priority
+  # Categories: PATTERN, STRAT, ANTI, EDGE
+  # Automatic tag extraction and deduplication
+  echo "✅ ACE reflection captured: $(sqlite3 .claude/cfn-data/cfn-loop.db 'SELECT COUNT(*) FROM context_reflections WHERE task_id = \"'${TASK_ID}'\"') bullets"
+fi
+```
+
 **Checklist:**
 - [ ] Consensus ≥ threshold | [ ] Product Owner approved | [ ] Deliverables verified
 - [ ] Tests passing | [ ] Git committed | [ ] Git pushed | [ ] Summary generated
+- [ ] ACE reflection captured (if `--ace-reflect` enabled)
 
 ---
 
@@ -341,12 +379,68 @@ Complex/Enterprise (>5 files, >500 LOC): +code-analyzer
 
 ---
 
+## ACE System Integration
+
+### Reflection After Sprint
+After each sprint completion, Task Mode should capture lessons learned:
+
+```bash
+# Automatic reflection capture (called after git push)
+./.claude/skills/cfn-ace-system/invoke-context-reflect.sh \
+  --task-id "${TASK_ID}" \
+  --sprint-id "${SPRINT_NUM}" \
+  --consensus "${CONSENSUS}" \
+  --iterations-loop3 "${L3}" \
+  --iterations-loop2 "${L2}" \
+  --deliverables "$(git diff HEAD~1 --name-only | tr '\n' ',')"
+```
+
+**What Gets Captured:**
+- Patterns that worked well (consensus ≥0.90, low iterations)
+- Anti-patterns that caused issues (high iterations, deliverable failures)
+- Strategy patterns (agent selection, validator scaling effectiveness)
+- Edge cases (timeout scenarios, race conditions, blocking issues)
+
+**Storage:**
+- SQLite database: `.claude/cfn-data/cfn-loop.db`
+- Table: `context_reflections`
+- Automatic tagging, deduplication, confidence scoring
+
+**Benefits:**
+- Future sprints learn from past mistakes
+- Adaptive validator scaling improves over time
+- Pattern recognition across projects
+- Knowledge accumulation (not lost between sessions)
+
+### Optional: Context Injection (Future Enhancement)
+Before spawning agents, inject relevant lessons:
+```bash
+# Not yet implemented in Task Mode, but available:
+./.claude/skills/cfn-ace-system/invoke-context-inject.sh \
+  --task "${TASK_DESCRIPTION}" \
+  --phase "${PHASE_NAME}" \
+  --tags "validation,consensus,deliverables"
+# Returns: Top N relevant bullets from past reflections
+```
+
+### Optional: Context Curation (Periodic Maintenance)
+Merge and deduplicate reflection data:
+```bash
+# Run monthly or after major epics:
+./.claude/skills/cfn-ace-system/invoke-context-curate.sh \
+  --confidence-threshold 0.85 \
+  --merge-similar-patterns
+```
+
+---
+
 ## Related Documentation
 
 - **CFN Coordinator Parameters**: `.claude/commands/cfn/CFN_COORDINATOR_PARAMETERS.md`
 - **Redis Coordination**: `.claude/skills/cfn-redis-coordination/SKILL.md`
 - **Product Owner Decision**: `.claude/skills/cfn-product-owner-decision/SKILL.md`
 - **Agent Output Standards**: `docs/AGENT_OUTPUT_STANDARDS.md`
+- **ACE System**: `.claude/skills/cfn-ace-system/SKILL.md`
 
 ---
 

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

@@ -1,6 +1,6 @@
 ---
 description: "Execute autonomous 3-loop self-correcting CFN workflow with automatic retry and consensus validation"
-argument-hint: "<task description> [--phase=name] [--mode=mvp|standard|enterprise] [--spawn-mode=cli|task] [--max-loop2=10] [--max-loop3=10]"
+argument-hint: "<task description> [--phase=name] [--mode=mvp|standard|enterprise] [--spawn-mode=cli|task] [--max-loop2=10] [--max-loop3=10] [--ace-reflect]"
 allowed-tools: ["Task", "TodoWrite", "Read", "Write", "Edit", "Bash", "Glob", "Grep"]
 ---
 
@@ -38,10 +38,11 @@ LOOP 3: Primary Swarm Execution with subtask iterations
 - `--phase=<name>`: Optional phase name for tracking
 - `--mode=<mvp|standard|enterprise>`: Coordinator mode (default: standard)
 - `--spawn-mode=<cli|task>`: Agent spawning method (default: cli)
-  - **cli**: Cost-optimized (95-98% savings), background execution, Redis monitoring
-  - **task**: Full visibility in Main Chat, direct spawning, debugging
+  - **cli**: Cost-optimized (95-98% savings), background execution, Redis monitoring, ACE always enabled
+  - **task**: Full visibility in Main Chat, direct spawning, debugging, ACE optional via flag
 - `--max-loop2=<n>`: Max consensus iterations (default: 10)
 - `--max-loop3=<n>`: Max primary swarm iterations (default: 10)
+- `--ace-reflect`: Enable ACE reflection after each sprint (Task mode only, captures lessons learned)
 
 ## Coordinator Modes
 

package/.claude/hooks/cfn-invoke-security-validation.sh

@@ -0,0 +1,70 @@
+#!/bin/bash
+# Security Validation Hook for Docker Hybrid Routing
+
+set -euo pipefail
+
+# Validate secret management configurations
+validate_secret_management() {
+    local file_path="$1"
+
+    # Check for hardcoded secrets
+    if grep -qE '(sk-ant-|token-|api_key=)' "$file_path"; then
+        echo "❌ SECURITY RISK: Potential secret exposure in $file_path"
+        return 1
+    fi
+
+    # Check for proper environment variable naming
+    if grep -qE 'API_KEY=|SECRET=|TOKEN=' "$file_path"; then
+        echo "⚠️ NAMING RISK: Inconsistent secret variable names in $file_path"
+        return 2
+    fi
+
+    return 0
+}
+
+# Validate Docker network configurations
+validate_docker_network() {
+    local compose_file="$1"
+
+    # Check for overly permissive network configurations
+    if ! grep -qE 'driver_opts:\n\s*encrypted:\s*"true"' "$compose_file"; then
+        echo "❌ NETWORK RISK: Network encryption not enabled"
+        return 1
+    fi
+
+    if ! grep -qE 'driver:\s*overlay' "$compose_file"; then
+        echo "⚠️ NETWORK CONFIG: Recommended to use overlay network for better isolation"
+        return 2
+    fi
+
+    return 0
+}
+
+# Main validation function
+main() {
+    local file_path="$1"
+    local file_name=$(basename "$file_path")
+    local exit_code=0
+
+    echo "🔒 Running security validation for $file_name"
+
+    case "$file_name" in
+        docker-compose.yml|docker-compose.*.yml)
+            validate_docker_network "$file_path" || exit_code=$?
+            ;;
+        .env|*.env)
+            validate_secret_management "$file_path" || exit_code=$?
+            ;;
+    esac
+
+    if [ $exit_code -eq 0 ]; then
+        echo "✅ Security validation passed for $file_name"
+    else
+        echo "🚨 Security validation failed for $file_name (Error code: $exit_code)"
+    fi
+
+    return $exit_code
+}
+
+# Execute main validation
+main "$@"

package/.claude/skills/cfn-hybrid-routing/spawn-worker.sh

@@ -1,44 +1,44 @@
-#!/usr/bin/env bash
-set -euo pipefail
-
-# Hybrid Routing Worker Spawner
-# Dynamically configures and launches routing workers
-
-CONFIG_PATH="$(dirname "$0")/config.json"
-
-# Load configuration
-SKILL_NAME=$(jq -r '.skill_name' "$CONFIG_PATH")
-PRIMARY_CHANNEL=$(jq -r '.routing_strategies.primary.type' "$CONFIG_PATH")
-SECONDARY_CHANNEL=$(jq -r '.routing_strategies.secondary.type' "$CONFIG_PATH")
-
-# Worker spawning function
-spawn_routing_worker() {
-    local channel_type="$1"
-    local worker_id="$2"
-
-    case "$channel_type" in
-        "redis-pubsub")
-            ./.claude/skills/cfn-redis-coordination/spawn-agent.sh \
-                --skill-id "$SKILL_NAME" \
-                --agent-id "routing-worker-$worker_id" \
-                --strategy "$channel_type"
-            ;;
-        "websocket")
-            ./.claude/skills/cfn-agent-spawning/spawn-agent.sh \
-                --skill-id "$SKILL_NAME" \
-                --agent-id "routing-worker-$worker_id" \
-                --strategy "$channel_type"
-            ;;
-        *)
-            echo "Unsupported channel type: $channel_type"
-            exit 1
-            ;;
-    esac
-}
-
-# Spawn primary and secondary workers
-spawn_routing_worker "$PRIMARY_CHANNEL" "primary"
-spawn_routing_worker "$SECONDARY_CHANNEL" "secondary"
-
-# Final status report
+#!/usr/bin/env bash
+set -euo pipefail
+
+# Hybrid Routing Worker Spawner
+# Dynamically configures and launches routing workers
+
+CONFIG_PATH="$(dirname "$0")/config.json"
+
+# Load configuration
+SKILL_NAME=$(jq -r '.skill_name' "$CONFIG_PATH")
+PRIMARY_CHANNEL=$(jq -r '.routing_strategies.primary.type' "$CONFIG_PATH")
+SECONDARY_CHANNEL=$(jq -r '.routing_strategies.secondary.type' "$CONFIG_PATH")
+
+# Worker spawning function
+spawn_routing_worker() {
+    local channel_type="$1"
+    local worker_id="$2"
+
+    case "$channel_type" in
+        "redis-pubsub")
+            ./.claude/skills/cfn-redis-coordination/spawn-agent.sh \
+                --skill-id "$SKILL_NAME" \
+                --agent-id "routing-worker-$worker_id" \
+                --strategy "$channel_type"
+            ;;
+        "websocket")
+            ./.claude/skills/cfn-agent-spawning/spawn-agent.sh \
+                --skill-id "$SKILL_NAME" \
+                --agent-id "routing-worker-$worker_id" \
+                --strategy "$channel_type"
+            ;;
+        *)
+            echo "Unsupported channel type: $channel_type"
+            exit 1
+            ;;
+    esac
+}
+
+# Spawn primary and secondary workers
+spawn_routing_worker "$PRIMARY_CHANNEL" "primary"
+spawn_routing_worker "$SECONDARY_CHANNEL" "secondary"
+
+# Final status report
 echo "Hybrid Routing Workers Spawned Successfully"