claude-flow-novice 2.14.11 → 2.14.12

package/.claude/commands/CFN_LOOP_TASK_MODE.md

@@ -6,11 +6,11 @@
 
 ## Overview
 
-Task Mode: Main Chat acts as coordinator and spawns agents directly via Task() tool with full context injection and visibility.
+Task Mode: Main Chat spawns coordinator and agents via Task() tool with full context injection and visibility.
 
 | Aspect | Task Mode | CLI Mode |
 |--------|-----------|----------|
-| **Spawning** | Main Chat spawns agents directly via Task() | Coordinator spawns agents via npx CLI |
+| **Spawning** | Main Chat via Task() | Coordinator via npx CLI |
 | **Visibility** | Full transparency in Main Chat | Background, Redis logs |
 | **Provider** | All Anthropic | CLI uses Z.ai routing |
 | **Cost** | ~$0.150/iteration | ~$0.054/iteration (64% savings) |
@@ -35,50 +35,6 @@ Task Mode: Main Chat acts as coordinator and spawns agents directly via Task() t
 
 ---
 
-## Task Mode Execution Pattern
-
-**Key Principle: Main Chat IS the coordinator**
-
-In Task Mode, Main Chat directly spawns all agents via Task() tool. No coordinator agent is used.
-
-### Example: Zone A React Router Migration
-
-```javascript
-// ✅ CORRECT - Main Chat spawns agents directly
-Task("backend-developer", `
-  Migrate React Router from v4 to v6 in Zone A components
-  Deliverables: Updated Routes, component fixes, tests
-  Directory: frontend/src/zone-a/
-`);
-
-Task("react-frontend-engineer", `
-  Review and fix any component issues after router migration
-  Focus on route parameters, navigation, and component integration
-`);
-
-Task("tester", `
-  Test React Router v6 migration in Zone A
-  Verify all routes work, navigation functions, no regressions
-`);
-
-// Later: Process outputs, collect confidence, decide next iteration
-```
-
-### What NOT to Do in Task Mode
-
-```javascript
-// ❌ INCORRECT - Don't spawn coordinator agent
-Task("cfn-v3-coordinator", "Coordinate React Router migration");
-
-// ❌ INCORRECT - Don't use CLI commands in Task Mode
-Bash("npx claude-flow-novice swarm 'task description'");
-
-// ❌ INCORRECT - Don't nest CFN Loop calls
-Task("reviewer", "/cfn-loop 'review this code'");  // Causes infinite loops
-```
-
----
-
 ## Agent Specialization
 
 ### Loop 3 (Implementation)
@@ -132,15 +88,15 @@ return validators.slice(0, 6); // Max 6
 ## Sprint Completion Workflow
 
 **Key Difference in Task Mode:**
-- Product Owner spawned via `Task()` by Main Chat acting as coordinator (NOT via `execute-decision.sh`)
+- Product Owner spawned via `Task()` by coordinator (NOT via `execute-decision.sh`)
 - Use helper scripts for parsing/validation: `parse-decision.sh`, `validate-deliverables.sh`
 - CLI Mode uses `execute-decision.sh` which handles spawning + all logic
 
 ### 1. Consensus Validation
 
-**Task Mode** - Main Chat (as coordinator) spawns Product Owner via Task():
+**Task Mode** - Coordinator spawns Product Owner via Task():
 ```javascript
-// Main Chat (as coordinator) builds context and spawns PO
+// Coordinator builds context and spawns PO
 const poContext = `
   CFN Loop iteration ${iteration} complete.
   Loop 2 Consensus: ${consensus} (threshold: ${threshold})
@@ -208,7 +164,7 @@ EOF
 ### 5. Execute Product Owner Suggested Next Steps
 
 **After PROCEED Decision:**
-Product Owner may suggest follow-up tasks (documentation, testing, refactoring). Main Chat (as coordinator) must proceed by spawning specialized agents to execute these tasks:
+Product Owner may suggest follow-up tasks (documentation, testing, refactoring). Coordinator (main chat) must proceed by spawning specialized agents to execute these tasks:
 
 ```javascript
 // Parse PO feedback for suggested next steps
@@ -349,7 +305,7 @@ threshold = Math.min(threshold, 0.98); // Cap at 0.98
 ## Background Backlog Worker
 
 ### Architecture
-- **Main Chat (as coordinator)**: Spawns Task() agents directly for Sprint N (foreground)
+- **Main Chat**: Spawns Task() agents for Sprint N (foreground)
 - **Background CLI**: Processes P3 backlog items (detached process)
 
 ### Launch Background Worker

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

@@ -149,7 +149,7 @@ Task("cfn-v3-coordinator", `
 
   1. INVOKE ORCHESTRATOR (CLI spawning):
 
-     TASK_ID="cfn-cli-$(date +%s%N | tail -c 7)-${RANDOM}"
+     TASK_ID="cfn-cli-$(date +%s)"
      MODE="${mode}"
      LOOP3_AGENTS="backend-dev,researcher,devops"  # Customize for task
      LOOP2_AGENTS="reviewer,tester,architect,security-specialist"  # Scale by complexity

package/.claude/skills/cfn-agent-selector/SKILL.md

@@ -17,7 +17,7 @@ AGENTS=$(./.claude/skills/cfn-agent-selector/select-agents.sh \
   --task-type "software-development" \
   --description "Implement JWT authentication with refresh tokens")
 
-echo "$AGENTS" | jq '.loop3[]'  # ["backend-developer", "security-specialist"]
+echo "$AGENTS" | jq '.loop3[]'  # ["backend-dev", "security-specialist"]
 echo "$AGENTS" | jq '.loop2[]'  # ["reviewer", "tester", "security-auditor"]
 ```
 
@@ -35,7 +35,7 @@ echo "$AGENTS" | jq '.loop2[]'  # ["reviewer", "tester", "security-auditor"]
 ## Agent Selection Rules
 
 ### Software Development
-**Base Loop 3:** backend-developer, coder
+**Base Loop 3:** backend-dev, coder
 **Add if keywords:**
 - "security", "authentication", "JWT" → security-specialist
 - "database", "SQL", "schema" → database-engineer (if exists)

package/.claude/skills/cfn-loop-orchestration/orchestrate.sh

@@ -66,19 +66,6 @@ LOOP3_FINAL_CONFIDENCE=0.0
 LOOP2_FINAL_CONSENSUS=0.0
 DELIVERABLES_VERIFIED=false
 
-# Cleanup Redis keys before exit
-cleanup_redis_keys() {
-  if [ -n "$TASK_ID" ]; then
-    echo "🧹 Cleaning up Redis keys for task $TASK_ID"
-    # Set TTL on remaining task keys (1 hour)
-    redis-cli keys "swarm:${TASK_ID}:*" 2>/dev/null | xargs -I {} redis-cli expire {} 3600 2>/dev/null || true
-    redis-cli keys "cfn_loop:task:${TASK_ID}:*" 2>/dev/null | xargs -I {} redis-cli expire {} 3600 2>/dev/null || true
-  fi
-}
-
-# Trap cleanup on script exit
-trap cleanup_redis_keys EXIT
-
 ##############################################################################
 # Argument Parsing
 ##############################################################################
@@ -707,17 +694,6 @@ EOF
 # Main CFN Loop
 ##############################################################################
 
-# Validate CLI environment before spawning agents
-echo "🔧 Validating CLI environment..."
-if [ -f "$PROJECT_ROOT/.claude/skills/cfn-cli-setup/validate-cli-environment.sh" ]; then
-  if ! bash "$PROJECT_ROOT/.claude/skills/cfn-cli-setup/validate-cli-environment.sh"; then
-    echo "❌ CLI environment validation failed. Agents may not have required tools."
-    echo "⚠️  Continuing anyway, but expect potential tool failures..."
-  fi
-else
-  echo "⚠️  CLI environment validation script not found. Skipping validation."
-fi
-
 # Store context in Redis
 store_context "$TASK_ID"
 
@@ -775,41 +751,11 @@ for ((ITERATION=1; ITERATION<=MAX_ITERATIONS; ITERATION++)); do
        --agents "$LOOP3_IDS" \
        --threshold "$GATE" \
        --min-quorum "$MIN_QUORUM_LOOP3"; then
-    # Gate passed - validate confidence based on deliverables
-    echo "🔍 Validating agent confidence scores against deliverables..."
-
-    # Re-calculate confidence based on actual deliverables
-    if [ -n "$EXPECTED_FILES" ] && [ -f "$PROJECT_ROOT/.claude/skills/cfn-deliverable-validation/confidence-calculator.sh" ]; then
-      VALIDATED_CONFIDENCE=0
-
-      for agent_id in ${LOOP3_IDS//,/ }; do
-        # Get agent's reported confidence
-        agent_confidence=$(redis-cli get "swarm:${TASK_ID}:${agent_id}:confidence" 2>/dev/null || echo "0.5")
-
-        # Calculate deliverable-based confidence
-        deliverable_confidence=$("$PROJECT_ROOT/.claude/skills/cfn-deliverable-validation/confidence-calculator.sh" \
-          "$TASK_ID" "$agent_id" "$EXPECTED_FILES" "$PROJECT_ROOT")
-
-        echo "  Agent $agent_id: reported=$agent_confidence, deliverable-based=$deliverable_confidence"
-
-        # Use the lower of the two scores (inflation prevention)
-        if (( $(echo "$deliverable_confidence < $agent_confidence" | bc -l) )); then
-          echo "  ⚠️  Downgrading confidence for $agent_id (inflated score detected)"
-          VALIDATED_CONFIDENCE=$deliverable_confidence
-        else
-          VALIDATED_CONFIDENCE=$agent_confidence
-        fi
-      done
-
-      LOOP3_FINAL_CONFIDENCE=$VALIDATED_CONFIDENCE
-      echo "✅ Final validated Loop 3 confidence: $LOOP3_FINAL_CONFIDENCE"
-    else
-      # Store confidence (fallback method)
-      LOOP3_FINAL_CONFIDENCE=$("$REDIS_COORD_SKILL/invoke-waiting-mode.sh" collect \
-        --task-id "$TASK_ID" \
-        --agent-ids "$LOOP3_IDS" \
-        --min-quorum "$MIN_QUORUM_LOOP3")
-    fi
+    # Gate passed - store confidence
+    LOOP3_FINAL_CONFIDENCE=$("$REDIS_COORD_SKILL/invoke-waiting-mode.sh" collect \
+      --task-id "$TASK_ID" \
+      --agent-ids "$LOOP3_IDS" \
+      --min-quorum "$MIN_QUORUM_LOOP3")
   else
     # Gate failed - iterate Loop 3
     echo "❌ Gate check failed - iterating Loop 3"
@@ -932,19 +878,6 @@ EOF
   esac
 done
 
-# Cleanup Redis keys before exit
-cleanup_redis_keys() {
-  if [ -n "$TASK_ID" ]; then
-    echo "🧹 Cleaning up Redis keys for task $TASK_ID"
-    # Set TTL on remaining task keys (1 hour)
-    redis-cli keys "swarm:${TASK_ID}:*" 2>/dev/null | xargs -I {} redis-cli expire {} 3600 2>/dev/null || true
-    redis-cli keys "cfn_loop:task:${TASK_ID}:*" 2>/dev/null | xargs -I {} redis-cli expire {} 3600 2>/dev/null || true
-  fi
-}
-
-# Trap cleanup on script exit
-trap cleanup_redis_keys EXIT
-
 # Max iterations reached without success
 echo "❌ Max iterations ($MAX_ITERATIONS) reached without PROCEED decision"
 output_result "failed"

package/.claude/skills/cfn-redis-coordination/get-context.sh

@@ -0,0 +1,113 @@
+#!/bin/bash
+# Retrieve CFN Loop task context from Redis
+# Used by CLI-spawned agents to get structured context from orchestrator
+#
+# Usage:
+#   get-context.sh --task-id <id> [--namespace <ns>]
+#   get-context.sh --task-id <id> --key <key> [--namespace <ns>]
+#   get-context.sh <task_id> (legacy mode)
+
+set -euo pipefail
+
+# Initialize variables
+TASK_ID=""
+KEY=""
+NAMESPACE="swarm"
+FORMAT="json"  # json or raw
+
+# Parse arguments
+while [[ $# -gt 0 ]]; do
+  case $1 in
+    --task-id)
+      TASK_ID="$2"
+      shift 2
+      ;;
+    --key)
+      KEY="$2"
+      shift 2
+      ;;
+    --namespace)
+      NAMESPACE="$2"
+      shift 2
+      ;;
+    --format)
+      FORMAT="$2"
+      shift 2
+      ;;
+    *)
+      # Legacy mode: positional argument
+      if [ -z "$TASK_ID" ]; then
+        TASK_ID="$1"
+      fi
+      shift
+      ;;
+  esac
+done
+
+# Validate required arguments
+if [ -z "$TASK_ID" ]; then
+    echo "Error: --task-id or TASK_ID required" >&2
+    echo "Usage: $0 --task-id <id> [--key <key>] [--namespace <ns>] [--format <json|raw>]" >&2
+    echo "   or: $0 <task_id> (legacy)" >&2
+    exit 1
+fi
+
+REDIS_KEY="${NAMESPACE}:${TASK_ID}:context"
+
+# Check if context exists
+if ! redis-cli EXISTS "$REDIS_KEY" >/dev/null 2>&1; then
+    echo "⚠️  No context found for task: $TASK_ID" >&2
+    exit 1
+fi
+
+# Handle specific key retrieval
+if [ -n "$KEY" ]; then
+  VALUE=$(redis-cli HGET "$REDIS_KEY" "$KEY" 2>/dev/null || echo "")
+  if [ -z "$VALUE" ]; then
+    echo "⚠️  Key '$KEY' not found in context for task: $TASK_ID" >&2
+    exit 1
+  fi
+
+  if [ "$FORMAT" = "raw" ]; then
+    echo "$VALUE"
+  else
+    echo "{\"$KEY\":$VALUE}"
+  fi
+  exit 0
+fi
+
+# Handle full context retrieval
+ALL_FIELDS=$(redis-cli HGETALL "$REDIS_KEY" 2>/dev/null || echo "")
+
+if [ -z "$ALL_FIELDS" ]; then
+    echo "⚠️  Empty context for task: $TASK_ID" >&2
+    exit 1
+fi
+
+# Format as JSON
+if [ "$FORMAT" = "json" ]; then
+  echo "{"
+  first=true
+  while IFS= read -r field; do
+    if [ -z "$field" ]; then continue; fi
+    if [ "$first" = true ]; then
+      first=false
+    else
+      echo ","
+    fi
+    # Skip empty lines and properly format JSON values
+    if [[ $field =~ ^[0-9]+$ ]]; then
+      # Numeric value
+      echo -n "  \"$field\": $(redis-cli HGET "$REDIS_KEY" "$field")"
+    else
+      # String value
+      value=$(redis-cli HGET "$REDIS_KEY" "$field" | sed 's/"/\\"/g')
+      echo -n "  \"$field\": \"$value\""
+    fi
+  done <<< "$ALL_FIELDS"
+  echo ""
+  echo "}"
+else
+  # Raw format
+  redis-cli HGETALL "$REDIS_KEY"
+fi

package/.claude/skills/cfn-redis-coordination/store-context.sh

@@ -1,34 +1,89 @@
 #!/bin/bash
 # Store CFN Loop task context in Redis
-# Used by orchestrator to pass context to CLI-spawned agents
+# Used by orchestrator to pass structured context to CLI-spawned agents
 #
-# Usage: store-context.sh <task_id> <context_json>
+# Usage:
+#   store-context.sh --task-id <id> --key <key> --value <value> [--namespace <ns>]
+#   store-context.sh <task_id> <context_json> (legacy mode)
 
 set -euo pipefail
 
-TASK_ID="${1:-}"
-CONTEXT="${2:-}"
+# Initialize variables
+TASK_ID=""
+KEY=""
+VALUE=""
+NAMESPACE="swarm"
+CONTEXT=""
 
+# Parse arguments
+while [[ $# -gt 0 ]]; do
+  case $1 in
+    --task-id)
+      TASK_ID="$2"
+      shift 2
+      ;;
+    --key)
+      KEY="$2"
+      shift 2
+      ;;
+    --value)
+      VALUE="$2"
+      shift 2
+      ;;
+    --namespace)
+      NAMESPACE="$2"
+      shift 2
+      ;;
+    *)
+      # Legacy mode: positional arguments
+      if [ -z "$TASK_ID" ]; then
+        TASK_ID="$1"
+      elif [ -z "$CONTEXT" ]; then
+        CONTEXT="$1"
+      fi
+      shift
+      ;;
+  esac
+done
+
+# Validate required arguments
 if [ -z "$TASK_ID" ]; then
-    echo "Error: TASK_ID required" >&2
-    echo "Usage: $0 <task_id> <context_json>" >&2
+    echo "Error: --task-id or TASK_ID required" >&2
+    echo "Usage: $0 --task-id <id> --key <key> --value <value> [--namespace <ns>]" >&2
+    echo "   or: $0 <task_id> <context_json> (legacy)" >&2
     exit 1
 fi
 
-if [ -z "$CONTEXT" ]; then
-    echo "Error: CONTEXT required" >&2
-    echo "Usage: $0 <task_id> <context_json>" >&2
-    exit 1
+# Handle structured mode (new)
+if [ -n "$KEY" ] && [ -n "$VALUE" ]; then
+  # Store structured context with specific key
+  REDIS_KEY="${NAMESPACE}:${TASK_ID}:context"
+
+  redis-cli HSET "$REDIS_KEY" \
+      "$KEY" "$VALUE" \
+      "updated_at" "$(date -u +%Y-%m-%dT%H:%M:%SZ)" \
+      > /dev/null
+
+  # Set TTL (24 hours)
+  redis-cli EXPIRE "$REDIS_KEY" 86400 > /dev/null
+
+  echo "✅ Context stored: $KEY for task: $TASK_ID"
+  exit 0
 fi
 
-# Store context in Redis
-redis-cli HSET "cfn_loop:task:${TASK_ID}:context" \
-    "task_description" "$CONTEXT" \
-    "stored_at" "$(date -u +%Y-%m-%dT%H:%M:%SZ)" \
-    > /dev/null
+# Handle legacy mode
+if [ -n "$CONTEXT" ]; then
+  redis-cli HSET "swarm:${TASK_ID}:context" \
+      "task_description" "$CONTEXT" \
+      "stored_at" "$(date -u +%Y-%m-%dT%H:%M:%SZ)" \
+      > /dev/null
+
+  # Set TTL (24 hours)
+  redis-cli EXPIRE "swarm:${TASK_ID}:context" 86400 > /dev/null
 
-# Set TTL (24 hours)
-redis-cli EXPIRE "cfn_loop:task:${TASK_ID}:context" 86400 > /dev/null
+  echo "✅ Context stored for task: $TASK_ID"
+  exit 0
+fi
 
-echo "✅ Context stored for task: $TASK_ID"
-exit 0
+echo "Error: Either --key/--value or <context_json> required" >&2
+exit 1

package/claude-assets/agents/cfn-dev-team/CLAUDE.md

@@ -112,7 +112,7 @@ npx claude-flow-novice agent-spawn my-first-agent --task-id test-1
 │   ├── tester.md               # Testing & validation
 │   └── coordinator.md          # Multi-agent coordination
 ├── development/                 # Development-focused agents
-│   ├── backend-developer.md
+│   ├── backend-dev.md
 │   ├── react-frontend-engineer.md
 │   └── devops-engineer.md
 ├── security/                    # Security-focused agents
@@ -613,7 +613,7 @@ Agents can work together using Redis pub/sub and CLI spawning:
 ### Agent Spawning Pattern
 ```bash
 # Spawn agents via CLI (coordinators only)
-npx claude-flow-novice agent-spawn backend-developer --task-id "${TASK_ID}"
+npx claude-flow-novice agent-spawn backend-dev --task-id "${TASK_ID}"
 npx claude-flow-novice agent-spawn reviewer --task-id "${TASK_ID}"
 ```
 
@@ -948,7 +948,7 @@ acl_level: 1
 - `.claude/agents/core-agents/coder.md` - Code implementation
 - `.claude/agents/core-agents/reviewer.md` - Code review
 - `.claude/agents/core-agents/tester.md` - Testing & validation
-- `.claude/agents/development/backend-developer.md` - Backend development
+- `.claude/agents/development/backend-dev.md` - Backend development
 - `.claude/agents/security/security-specialist.md` - Security analysis
 
 ### Documentation

package/claude-assets/agents/cfn-dev-team/README.md

@@ -15,7 +15,7 @@ The CFN (Claude Flow Novice) development team comprises 23 production agents org
 - **Purpose**: Core implementation and creative problem-solving
 - **Key Agents**:
   - `coder`: Production code implementation
-  - `backend-developer`: Backend system design and implementation
+  - `backend-dev`: Backend system design and implementation
   - `researcher`: Technical research and solution exploration
   - `architect`: System design and architectural planning
   - `agent-builder`: Agent template and workflow design

package/claude-assets/agents/cfn-dev-team/coordinators/cfn-v3-coordinator.md

@@ -149,7 +149,7 @@ LOOP2_AGENTS=("${VERIFIED_LOOP2_AGENTS[@]:-default_loop2_agent}")
 **Agent Selection Rules (Enhanced):**
 
 **Software Development:**
-- Base Loop 3: `backend-developer`, `coder`, `devops-engineer`
+- Base Loop 3: `backend-dev`, `coder`, `devops-engineer`
 - If security keywords → add `security-specialist`
 - If database keywords → add `database-engineer`
 - Base Loop 2: `reviewer`, `tester`, `security-auditor`
@@ -388,7 +388,7 @@ Mode: task
 ```json
 {
   "task_type": "software-development",
-  "loop3_agents": ["backend-developer", "security-specialist"],
+  "loop3_agents": ["backend-dev", "security-specialist"],
   "loop2_agents": ["reviewer", "tester", "security-auditor"],
   "loop4_agent": "product-owner",
   "validation_criteria": {

package/claude-assets/agents/cfn-dev-team/developers/README.md

@@ -5,7 +5,7 @@ Implementation agents focused on building features and components.
 ## Active Agents (7)
 
 **Backend Development:**
-- `backend-developer.md` - Backend services, APIs, server-side logic
+- `backend-dev.md` - Backend services, APIs, server-side logic
 - `dev-backend-api.md` - Specialized REST/GraphQL API development
 
 **Frontend Development:**
@@ -42,12 +42,12 @@ All developers follow:
 Automatically spawned by orchestrator in Loop 3:
 ```bash
 ./.claude/skills/cfn-loop-orchestration/orchestrate.sh \
-  --loop3-agents "backend-developer,react-frontend-engineer"
+  --loop3-agents "backend-dev,react-frontend-engineer"
 ```
 
 **Standalone Implementation:**
 ```bash
-npx claude-flow-novice agent-spawn backend-developer --task-id "$TASK_ID"
+npx claude-flow-novice agent-spawn backend-dev --task-id "$TASK_ID"
 ```
 
 ## Deliverables

package/claude-assets/agents/cfn-dev-team/documentation/agent-type-guidelines.md

@@ -453,7 +453,7 @@ Deployment Process:
 ## Agent Selection Guide
 
 **Core Development**: coder, tester, reviewer
-**Backend**: backend-developer, api-docs, system-architect
+**Backend**: backend-dev, api-docs, system-architect
 **Frontend**: coder (specialized), mobile-dev
 **Quality**: tester, reviewer, security-specialist, perf-analyzer
 **Planning**: researcher, planner, architect

package/claude-assets/agents/cfn-dev-team/test-agent.md

@@ -19,7 +19,7 @@ The `epic-creator.md` coordinator agent kept getting deleted from `.claude/agent
 ### Why It Happened
 
 1. `package.json` has `"postinstall": "node scripts/init-project.js"`
-2. Running `npx claude-flow-novice agent backend-developer` triggers postinstall
+2. Running `npx claude-flow-novice agent backend-dev` triggers postinstall
 3. `init-project.js` ran `cfn-init` unconditionally
 4. cfn-init copied package version of cfn-dev-team/, overwriting local files
 5. epic-creator.md (and other local customizations) got deleted
@@ -28,7 +28,7 @@ The `epic-creator.md` coordinator agent kept getting deleted from `.claude/agent
 
 ```bash
 # Each of these triggered cfn-init:
-npx claude-flow-novice agent backend-developer
+npx claude-flow-novice agent backend-dev
 npx claude-flow-novice agent reviewer
 npx claude-flow-novice agent epic-creator
 

package/claude-assets/commands/CFN_LOOP_TASK_MODE.md

@@ -6,11 +6,11 @@
 
 ## Overview
 
-Task Mode: Main Chat acts as coordinator and spawns agents directly via Task() tool with full context injection and visibility.
+Task Mode: Main Chat spawns coordinator and agents via Task() tool with full context injection and visibility.
 
 | Aspect | Task Mode | CLI Mode |
 |--------|-----------|----------|
-| **Spawning** | Main Chat spawns agents directly via Task() | Coordinator spawns agents via npx CLI |
+| **Spawning** | Main Chat via Task() | Coordinator via npx CLI |
 | **Visibility** | Full transparency in Main Chat | Background, Redis logs |
 | **Provider** | All Anthropic | CLI uses Z.ai routing |
 | **Cost** | ~$0.150/iteration | ~$0.054/iteration (64% savings) |
@@ -35,50 +35,6 @@ Task Mode: Main Chat acts as coordinator and spawns agents directly via Task() t
 
 ---
 
-## Task Mode Execution Pattern
-
-**Key Principle: Main Chat IS the coordinator**
-
-In Task Mode, Main Chat directly spawns all agents via Task() tool. No coordinator agent is used.
-
-### Example: Zone A React Router Migration
-
-```javascript
-// ✅ CORRECT - Main Chat spawns agents directly
-Task("backend-developer", `
-  Migrate React Router from v4 to v6 in Zone A components
-  Deliverables: Updated Routes, component fixes, tests
-  Directory: frontend/src/zone-a/
-`);
-
-Task("react-frontend-engineer", `
-  Review and fix any component issues after router migration
-  Focus on route parameters, navigation, and component integration
-`);
-
-Task("tester", `
-  Test React Router v6 migration in Zone A
-  Verify all routes work, navigation functions, no regressions
-`);
-
-// Later: Process outputs, collect confidence, decide next iteration
-```
-
-### What NOT to Do in Task Mode
-
-```javascript
-// ❌ INCORRECT - Don't spawn coordinator agent
-Task("cfn-v3-coordinator", "Coordinate React Router migration");
-
-// ❌ INCORRECT - Don't use CLI commands in Task Mode
-Bash("npx claude-flow-novice swarm 'task description'");
-
-// ❌ INCORRECT - Don't nest CFN Loop calls
-Task("reviewer", "/cfn-loop 'review this code'");  // Causes infinite loops
-```
-
----
-
 ## Agent Specialization
 
 ### Loop 3 (Implementation)
@@ -132,15 +88,15 @@ return validators.slice(0, 6); // Max 6
 ## Sprint Completion Workflow
 
 **Key Difference in Task Mode:**
-- Product Owner spawned via `Task()` by Main Chat acting as coordinator (NOT via `execute-decision.sh`)
+- Product Owner spawned via `Task()` by coordinator (NOT via `execute-decision.sh`)
 - Use helper scripts for parsing/validation: `parse-decision.sh`, `validate-deliverables.sh`
 - CLI Mode uses `execute-decision.sh` which handles spawning + all logic
 
 ### 1. Consensus Validation
 
-**Task Mode** - Main Chat (as coordinator) spawns Product Owner via Task():
+**Task Mode** - Coordinator spawns Product Owner via Task():
 ```javascript
-// Main Chat (as coordinator) builds context and spawns PO
+// Coordinator builds context and spawns PO
 const poContext = `
   CFN Loop iteration ${iteration} complete.
   Loop 2 Consensus: ${consensus} (threshold: ${threshold})
@@ -208,7 +164,7 @@ EOF
 ### 5. Execute Product Owner Suggested Next Steps
 
 **After PROCEED Decision:**
-Product Owner may suggest follow-up tasks (documentation, testing, refactoring). Main Chat (as coordinator) must proceed by spawning specialized agents to execute these tasks:
+Product Owner may suggest follow-up tasks (documentation, testing, refactoring). Coordinator (main chat) must proceed by spawning specialized agents to execute these tasks:
 
 ```javascript
 // Parse PO feedback for suggested next steps
@@ -349,7 +305,7 @@ threshold = Math.min(threshold, 0.98); // Cap at 0.98
 ## Background Backlog Worker
 
 ### Architecture
-- **Main Chat (as coordinator)**: Spawns Task() agents directly for Sprint N (foreground)
+- **Main Chat**: Spawns Task() agents for Sprint N (foreground)
 - **Background CLI**: Processes P3 backlog items (detached process)
 
 ### Launch Background Worker