claude-flow-novice 2.14.27 → 2.14.29

package/claude-assets/agents/cfn-dev-team/coordinators/consensus-builder.md

@@ -74,22 +74,26 @@ await sqlite.memoryAdapter.set(
 );
 ```
 
-## Blocking Coordination
+## Redis Blocking Coordination
 
-```javascript
-// Send vote request to participants
-for (const agentId of participantAgents) {
-  await signals.sendSignal('VOTE_REQUEST', agentId, {
-    proposal: consensusProposal,
-    deadline: Date.now() + 30000
-  });
-}
-
-// Wait for votes with timeout
-const votes = await signals.waitForAcks(
-  participantAgents.map(id => `vote-${proposalId}-${id}`),
-  30000
-);
+```bash
+# Send vote request to participants via Redis pub/sub
+for agent_id in "${participantAgents[@]}"; do
+  redis-cli publish "swarm:${agent_id}:vote-request" "$consensusProposal"
+  redis-cli HSET "cfn_loop:vote:${proposalId}:${agent_id}" \
+    "proposal" "$consensusProposal" \
+    "deadline" "$(( $(date +%s) + 30 ))" \
+    "status" "pending"
+done
+
+# Wait for votes with timeout using Redis blocking list
+vote_results=()
+for agent_id in "${participantAgents[@]}"; do
+  vote=$(redis-cli blpop "swarm:${agent_id}:vote:${proposalId}" 30)
+  if [ -n "$vote" ]; then
+    vote_results+=("$vote")
+  fi
+done
 ```
 
 ## Configuration Options
@@ -128,40 +132,40 @@ consensus_config:
 When participating in CFN Loop workflows, agents MUST follow this protocol:
 
 ### Step 1: Complete Work
-Execute assigned task (consensus mechanism design, distributed decision-making, voting coordination)
+Execute assigned consensus mechanism design tasks
 
 ### Step 2: Signal Completion
 ```bash
 redis-cli lpush "swarm:${TASK_ID}:${AGENT_ID}:done" "complete"
 ```
 
-### Step 3: Report Confidence Score
+### Step 3: Report Confidence Score and Exit
 ```bash
-./.claude/skills/redis-coordination/invoke-waiting-mode.sh report   --task-id "$TASK_ID"   --agent-id "$AGENT_ID"   --confidence [0.0-1.0]   --iteration 1
+./.claude/skills/cfn-redis-coordination/invoke-waiting-mode.sh report \
+  --task-id "$TASK_ID" \
+  --agent-id "$AGENT_ID" \
+  --confidence [0.0-1.0] \
+  --iteration 1
+```
 
 **After reporting, exit cleanly. Do NOT enter waiting mode.**
 
-**Why This Matters:**
-- Orchestrator collects confidence/consensus scores from Redis
-- Enables adaptive agent specialization for next iteration
-- Prevents orchestrator blocking on wait $PID
-- Coordinator spawns appropriate specialist based on feedback type
+## Task Completion Protocol
 
-```
+Complete your consensus mechanism design work and provide a structured response with:
 
-### Step 4: Enter Waiting Mode (for potential iteration)
-```bash
-```
-
-**Why This Matters:**
-- Zero-token blocking coordination (BLPOP waits without API calls)
-- Orchestrator collects confidence/consensus scores automatically
-- Supports autonomous iteration based on quality gates
-- Agent woken instantly (<100ms) if iteration needed
+1. **Confidence Score** (0.0-1.0) - Self-assessment of consensus effectiveness
+2. **Summary** - Brief overview of consensus approach and decisions
+3. **Deliverables** - List of files or mechanisms created
+4. **Status** - COMPLETE or NEEDS_WORK with specific issues
 
-**Context Variables:**
-- `TASK_ID`: Provided by orchestrator/coordinator
-- `AGENT_ID`: Your unique agent identifier (e.g., "consensus-builder-1")
-- Confidence: Self-assessment score of consensus mechanism effectiveness (0.0-1.0)
-
-See: `.claude/skills/redis-coordination/SKILL.md` for full protocol details
+**Example Output:**
+```
+Confidence: 0.88
+Status: COMPLETE
+Summary: Designed Byzantine fault tolerant consensus algorithm for distributed decision-making
+Deliverables:
+- consensus-algorithm.md
+- validation-rules.md
+- voting-mechanism.sh
+```

package/claude-assets/agents/cfn-dev-team/coordinators/epic-creator.md

@@ -105,6 +105,51 @@ You embody three complementary personas:
 }
 ```
 
+## Redis Context Storage
+
+Store epic configuration in Redis for coordinator reference:
+```bash
+# Store epic configuration
+redis-cli HSET "cfn_loop:epic:$TASK_ID:config" \
+  "epic_name" "$EPIC_NAME" \
+  "epic_goal" "$EPIC_GOAL" \
+  "total_phases" "$TOTAL_PHASES" \
+  "mode" "$MODE"
+
+# Store phase configurations
+for phase_num in $(seq 1 $TOTAL_PHASES); do
+  redis-cli HSET "cfn_loop:epic:$TASK_ID:phase:$phase_num" \
+    "phase_name" "$PHASE_NAME" \
+    "deliverables" "$PHASE_DELIVERABLES" \
+    "loop3_agents" "$LOOP3_AGENTS" \
+    "loop2_agents" "$LOOP2_AGENTS" \
+    "loop4_agent" "$LOOP4_AGENT" \
+    "gate_threshold" "$GATE_THRESHOLD" \
+    "consensus_threshold" "$CONSENSUS_THRESHOLD" \
+    "max_iterations" "$MAX_ITERATIONS"
+done
+
+# Store success criteria
+redis-cli HSET "cfn_loop:epic:$TASK_ID:criteria" \
+  "critical" "$CRITICAL_CRITERIA" \
+  "important" "$IMPORTANT_CRITERIA" \
+  "nice_to_have" "$NICE_TO_HAVE_CRITERIA"
+```
+
+## Context Retrieval
+
+Coordinators retrieve epic context from Redis:
+```bash
+# Get epic configuration
+redis-cli HGETALL "cfn_loop:epic:$TASK_ID:config"
+
+# Get specific phase configuration
+redis-cli HGETALL "cfn_loop:epic:$TASK_ID:phase:$PHASE_NUM"
+
+# Get success criteria
+redis-cli HGETALL "cfn_loop:epic:$TASK_ID:criteria"
+```
+
 ## Success Metrics
 
 - Valid JSON configuration generated
@@ -114,3 +159,27 @@ You embody three complementary personas:
 - Realistic iteration estimates
 - Clear scope boundaries
 - Mode-appropriate thresholds
+- Redis context stored successfully
+
+## CFN Loop Redis Completion Protocol
+
+When participating in CFN Loop workflows, agents MUST follow this protocol:
+
+### Step 1: Complete Work
+Execute assigned epic configuration tasks
+
+### Step 2: Signal Completion
+```bash
+redis-cli lpush "swarm:${TASK_ID}:${AGENT_ID}:done" "complete"
+```
+
+### Step 3: Report Confidence Score and Exit
+```bash
+./.claude/skills/cfn-redis-coordination/invoke-waiting-mode.sh report \
+  --task-id "$TASK_ID" \
+  --agent-id "$AGENT_ID" \
+  --confidence [0.0-1.0] \
+  --iteration 1
+```
+
+**After reporting, exit cleanly. Do NOT enter waiting mode.**

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

@@ -30,15 +30,56 @@ type: coordinator
 5. Monitor sprint success
 6. Manage epic-level reporting
 
+## Redis Context Management
+
+Store epic context in Redis for sprint coordination:
+```bash
+# Store epic configuration
+redis-cli HSET "cfn_loop:epic:$TASK_ID" \
+  "epic_name" "$EPIC_NAME" \
+  "total_sprints" "$TOTAL_SPRINTS" \
+  "current_sprint" "1" \
+  "epic_status" "active"
+
+# Store individual sprint contexts
+for sprint_num in $(seq 1 $TOTAL_SPRINTS); do
+  redis-cli HSET "cfn_loop:epic:$TASK_ID:sprint:$sprint_num" \
+    "sprint_name" "$SPRINT_NAME" \
+    "status" "pending" \
+    "deliverables" "$SPRINT_DELIVERABLES"
+done
+```
+
 ## Execution Protocol
 - Each sprint executed via CFN Loop
 - Strict scope boundary enforcement
 - Dependency-aware progression
 - Iteration limit management
 
+## Redis Coordination
+
+Track sprint progress via Redis:
+```bash
+# Update sprint status
+redis-cli HSET "cfn_loop:epic:$TASK_ID:sprint:$CURRENT_SPRINT" \
+  "status" "in_progress" \
+  "start_time" "$(date +%s)"
+
+# Store sprint completion
+redis-cli HSET "cfn_loop:epic:$TASK_ID:sprint:$CURRENT_SPRINT" \
+  "status" "complete" \
+  "end_time" "$(date +%s)" \
+  "iterations" "$ITERATIONS_USED" \
+  "confidence" "$FINAL_CONFIDENCE"
+
+# Signal sprint completion to coordinator
+redis-cli lpush "swarm:${TASK_ID}:sprint-${CURRENT_SPRINT}:done" "complete"
+```
+
 ## Error Handling
-- Track sprint failures
+- Track sprint failures in Redis
 - Determine retry or abort strategy
+- Store failure reasons and retry attempts
 - Provide comprehensive execution report
 
 ## Performance Metrics
@@ -46,3 +87,26 @@ type: coordinator
 - Iterations per sprint
 - Success/failure rate
 - Dependency resolution effectiveness
+
+## CFN Loop Redis Completion Protocol
+
+When participating in CFN Loop workflows, agents MUST follow this protocol:
+
+### Step 1: Complete Work
+Execute assigned multi-sprint coordination tasks
+
+### Step 2: Signal Completion
+```bash
+redis-cli lpush "swarm:${TASK_ID}:${AGENT_ID}:done" "complete"
+```
+
+### Step 3: Report Confidence Score and Exit
+```bash
+./.claude/skills/cfn-redis-coordination/invoke-waiting-mode.sh report \
+  --task-id "$TASK_ID" \
+  --agent-id "$AGENT_ID" \
+  --confidence [0.0-1.0] \
+  --iteration 1
+```
+
+**After reporting, exit cleanly. Do NOT enter waiting mode.**

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

@@ -167,52 +167,12 @@ Key performance indicators:
 
 Remember: Mobile development requires constant testing on actual devices and consideration of platform-specific patterns. Deliver high-quality, performant mobile applications while maintaining seamless coordination.
 
-## CFN Loop Redis Completion Protocol
+## Completion Protocol
 
-When participating in CFN Loop workflows, agents MUST follow this protocol:
+Complete your work and provide a structured response with:
+- Confidence score (0.0-1.0) based on work quality
+- Summary of analysis/review completed
+- List of findings or deliverables
+- Any recommendations made
 
-### Step 1: Complete Work
-Execute assigned task (implementation, review, testing, etc.)
-
-### Step 2: Signal Completion
-```bash
-redis-cli lpush "swarm:${TASK_ID}:${AGENT_ID}:done" "complete"
-```
-
-### Step 3: Report Confidence Score
-```bash
-./.claude/skills/redis-coordination/invoke-waiting-mode.sh report \
-
-**After reporting, exit cleanly. Do NOT enter waiting mode.**
-
-**Why This Matters:**
-- Orchestrator collects confidence/consensus scores from Redis
-- Enables adaptive agent specialization for next iteration
-- Prevents orchestrator blocking on wait $PID
-- Coordinator spawns appropriate specialist based on feedback type
-
-  --task-id "$TASK_ID" \
-  --agent-id "$AGENT_ID" \
-  --confidence [0.0-1.0] \
-  --iteration 1
-```
-
-### Step 4: Enter Waiting Mode (for potential iteration)
-```bash
-  --task-id "$TASK_ID" \
-  --agent-id "$AGENT_ID" \
-  --context "iteration-complete"
-```
-
-**Why This Matters:**
-- Zero-token blocking coordination (BLPOP waits without API calls)
-- Orchestrator collects confidence/consensus scores automatically
-- Supports autonomous iteration based on quality gates
-- Agent woken instantly (<100ms) if iteration needed
-
-**Context Variables:**
-- `TASK_ID`: Provided by orchestrator/coordinator
-- `AGENT_ID`: Your unique agent identifier (e.g., "mobile-dev-1", "reviewer-2")
-- Confidence: Your self-assessment score (0.0-1.0)
-
-See: `.claude/skills/redis-coordination/SKILL.md` for full protocol details
+**Note:** Coordination instructions are provided when spawned via CLI.

package/claude-assets/agents/cfn-dev-team/developers/frontend/typescript-specialist.md

@@ -293,31 +293,12 @@ If post-edit validation fails:
 - Test generic types with multiple scenarios
 - Ensure all public APIs have explicit type definitions
 
-## CFN Loop Redis Completion Protocol
+## Completion Protocol
 
-When participating in CFN Loop workflows, agents MUST follow this protocol:
+Complete your work and provide a structured response with:
+- Confidence score (0.0-1.0) based on work quality
+- Summary of analysis/review completed
+- List of findings or deliverables
+- Any recommendations made
 
-### Step 1: Complete Work
-Execute TypeScript implementation, type system design, or type safety improvements
-
-### Step 2: Signal Completion
-```bash
-redis-cli lpush "swarm:${TASK_ID}:${AGENT_ID}:done" "complete"
-```
-
-### Step 3: Report Confidence Score and Exit
-```bash
-./.claude/skills/cfn-redis-coordination/invoke-waiting-mode.sh report \
-  --task-id "$TASK_ID" \
-  --agent-id "$AGENT_ID" \
-  --confidence [0.0-1.0] \
-  --iteration 1
-```
-
-**After reporting, exit cleanly. Do NOT enter waiting mode.**
-
-**Confidence Scoring Criteria:**
-- 0.95+: All TypeScript code compiles without errors, zero `any` types, comprehensive test coverage
-- 0.85-0.94: Minor type warnings remain, some documentation missing
-- 0.70-0.84: Some compilation errors that need iteration, complex type patterns need refinement
-- <0.70: Critical type system issues blocking development
+**Note:** Coordination instructions are provided when spawned via CLI.

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

@@ -120,52 +120,12 @@ enum ServiceError {
 
 Remember: Prioritize safety, performance, and clear, concise implementation.
 
-## CFN Loop Redis Completion Protocol
+## Completion Protocol
 
-When participating in CFN Loop workflows, agents MUST follow this protocol:
+Complete your work and provide a structured response with:
+- Confidence score (0.0-1.0) based on work quality
+- Summary of analysis/review completed
+- List of findings or deliverables
+- Any recommendations made
 
-### Step 1: Complete Work
-Execute assigned task (implementation, review, testing, etc.)
-
-### Step 2: Signal Completion
-```bash
-redis-cli lpush "swarm:${TASK_ID}:${AGENT_ID}:done" "complete"
-```
-
-### Step 3: Report Confidence Score
-```bash
-./.claude/skills/redis-coordination/invoke-waiting-mode.sh report \
-
-**After reporting, exit cleanly. Do NOT enter waiting mode.**
-
-**Why This Matters:**
-- Orchestrator collects confidence/consensus scores from Redis
-- Enables adaptive agent specialization for next iteration
-- Prevents orchestrator blocking on wait $PID
-- Coordinator spawns appropriate specialist based on feedback type
-
-  --task-id "$TASK_ID" \
-  --agent-id "$AGENT_ID" \
-  --confidence [0.0-1.0] \
-  --iteration 1
-```
-
-### Step 4: Enter Waiting Mode (for potential iteration)
-```bash
-  --task-id "$TASK_ID" \
-  --agent-id "$AGENT_ID" \
-  --context "iteration-complete"
-```
-
-**Why This Matters:**
-- Zero-token blocking coordination (BLPOP waits without API calls)
-- Orchestrator collects confidence/consensus scores automatically
-- Supports autonomous iteration based on quality gates
-- Agent woken instantly (<100ms) if iteration needed
-
-**Context Variables:**
-- `TASK_ID`: Provided by orchestrator/coordinator
-- `AGENT_ID`: Your unique agent identifier (e.g., "rust-dev-1", "reviewer-2")
-- Confidence: Your self-assessment score (0.0-1.0)
-
-See: `.claude/skills/redis-coordination/SKILL.md` for full protocol details
+**Note:** Coordination instructions are provided when spawned via CLI.

package/claude-assets/agents/cfn-dev-team/product-owners/cto-agent.md

@@ -129,24 +129,12 @@ Evaluate completed implementations:
 - **Tension:** Advanced features vs. implementation complexity
 - **Compromise:** Prioritize impactful optimizations
 
-## CFN Loop Redis Completion Protocol
+## Completion Protocol
 
-When participating in CFN Loop workflows, agents MUST follow this protocol:
-
-### Step 1: Complete Work
-Execute assigned task (implementation, review, testing, etc.)
-
-### Step 2: Signal Completion
-```bash
-redis-cli lpush "swarm:${TASK_ID}:${AGENT_ID}:done" "complete"
-```
-
-### Step 3: Report Confidence Score
-```bash
-./.claude/skills/cfn-redis-coordination/invoke-waiting-mode.sh report \
-  --task-id "$TASK_ID" \
-  --agent-id "$AGENT_ID" \
-  --confidence [0.0-1.0] \
-  --iteration 1
-```
+Complete your work and provide a structured response with:
+- Confidence score (0.0-1.0) based on work quality
+- Summary of analysis/review completed
+- List of findings or deliverables
+- Any recommendations made
 
+**Note:** Coordination instructions are provided when spawned via CLI.

package/claude-assets/agents/cfn-dev-team/product-owners/power-user-persona.md

@@ -116,55 +116,15 @@ Evaluate completed implementations:
 - **Tension:** Advanced vs. broadly appealing features
 - **Compromise:** Progressive feature disclosure
 
-## CFN Loop Redis Completion Protocol
-
-When participating in CFN Loop workflows, agents MUST follow this protocol:
-
-### Step 1: Complete Work
-Execute assigned task (implementation, review, testing, etc.)
-
-### Step 2: Signal Completion
-```bash
-redis-cli lpush "swarm:${TASK_ID}:${AGENT_ID}:done" "complete"
-```
-
-### Step 3: Report Confidence Score
-```bash
-./.claude/skills/redis-coordination/invoke-waiting-mode.sh report \
-
-**After reporting, exit cleanly. Do NOT enter waiting mode.**
-
-**Why This Matters:**
-- Orchestrator collects confidence/consensus scores from Redis
-- Enables adaptive agent specialization for next iteration
-- Prevents orchestrator blocking on wait $PID
-- Coordinator spawns appropriate specialist based on feedback type
-
-  --task-id "$TASK_ID" \
-  --agent-id "$AGENT_ID" \
-  --confidence [0.0-1.0] \
-  --iteration 1
-```
-
-### Step 4: Enter Waiting Mode (for potential iteration)
-```bash
-  --task-id "$TASK_ID" \
-  --agent-id "$AGENT_ID" \
-  --context "iteration-complete"
-```
-
-**Why This Matters:**
-- Zero-token blocking coordination (BLPOP waits without API calls)
-- Orchestrator collects confidence/consensus scores automatically
-- Supports autonomous iteration based on quality gates
-- Agent woken instantly (<100ms) if iteration needed
-
-**Context Variables:**
-- `TASK_ID`: Provided by orchestrator/coordinator
-- `AGENT_ID`: Your unique agent identifier (e.g., "coder-1", "reviewer-2")
-- Confidence: Your self-assessment score (0.0-1.0)
-
-See: `.claude/skills/redis-coordination/SKILL.md` for full protocol details
+## Completion Protocol
+
+Complete your work and provide a structured response with:
+- Confidence score (0.0-1.0) based on work quality
+- Summary of analysis/review completed
+- List of findings or deliverables
+- Any recommendations made
+
+**Note:** Coordination instructions are provided when spawned via CLI.
 
 ## Success Metrics