claude-flow-novice 2.14.28 → 2.14.30

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

@@ -34,7 +34,7 @@ lifecycle:
 
 ### NoSQL Databases
 - **MongoDB**: Document modeling, aggregation pipelines, sharding
-- **Redis**: Data structures, caching strategies, pub/sub
+- **Memcached**: Simple key-value caching strategies for application use
 - **Cassandra**: Wide-column modeling, partition keys
 - **DynamoDB**: Single-table design, GSI/LSI strategies
 
@@ -195,7 +195,7 @@ WHERE id = 123 AND version = 5;
 
 ### Caching Strategy
 ```
-Application → Redis Cache → Database
+Application → Cache Layer → Database
               ↓ (cache miss)
               Database → Populate Cache
 ```

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

@@ -13,7 +13,7 @@ capabilities:
   - android-development
   - cross-platform
   - native-modules
-coordination_role: implementer
+role: implementer
 mode_support: [mvp, standard, enterprise]
 validation_hooks:
   - agent-template-validator
@@ -22,7 +22,7 @@ validation_hooks:
 acl_level: 1  # Private - implementer level
 lifecycle:
   pre_task: |
-    sqlite-cli exec "INSERT INTO agents (id, type, status, spawned_at, coordination_role, mode, platform_focus)
+    sqlite-cli exec "INSERT INTO agents (id, type, status, spawned_at, role, mode, platform_focus)
                      VALUES ('${AGENT_ID}', 'mobile-dev', 'active', CURRENT_TIMESTAMP, 'implementer', '${MODE:-standard}', '${PLATFORM:-cross_platform}')"
 
     # Initialize mobile development context
@@ -40,12 +40,6 @@ lifecycle:
     sqlite-cli exec "INSERT INTO mobile_development_results (agent_id, task_id, mode, platform, confidence, screens_implemented, components_created, native_modules_integrated, performance_score, accessibility_score, timestamp)
                      VALUES ('${AGENT_ID}', '${TASK_ID}', '${MODE:-standard}', '${PLATFORM:-cross_platform}', ${CONFIDENCE_SCORE}, ${SCREENS_COUNT}, ${COMPONENTS_COUNT}, ${NATIVE_MODULES_COUNT}, ${PERFORMANCE_SCORE}, ${ACCESSIBILITY_SCORE}, CURRENT_TIMESTAMP)"
 
-# Templates referenced from global Claude Flow repository
-templates:
-  - redis-coordination: .claude/templates/redis-coordination.md
-  - memory-operations: .claude/templates/memory-operations.md
-  - post-edit-validation: .claude/templates/post-edit-validation.md
-  - test-coverage: .claude/templates/test-coverage.md
 ---
 
 # React Native Mobile Development Specialist
@@ -165,54 +159,14 @@ Key performance indicators:
 - Native module integration success
 - Cross-platform consistency
 
-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.
+Remember: Mobile development requires constant testing on actual devices and consideration of platform-specific patterns. Deliver high-quality, performant mobile applications.
 
-## 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:** Complete your work and provide a structured response with your confidence score and deliverables.

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:** Complete your work and provide a structured response with your confidence score and deliverables.

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

@@ -23,7 +23,7 @@ lifecycle:
                          completed_at = CURRENT_TIMESTAMP
                      WHERE id = '${AGENT_ID}'"
 acl_level: 1
-coordination_role: implementer
+role: implementer
 mode_support: [mvp, standard, enterprise]
 ---
 # Rust Developer Agent
@@ -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:** Complete your work and provide a structured response with your confidence score and deliverables.

package/claude-assets/agents/cfn-dev-team/documentation/api-documentation.md

@@ -72,7 +72,7 @@ You are a technical documentation expert focused on creating comprehensive, user
 ## Coordination Patterns
 
 ### Documentation Updates
-- Real-time Redis coordination
+- Automated documentation synchronization
 - Semantic versioning tracking
 - Automated changelog generation
 - Review and approval workflows

package/claude-assets/agents/cfn-dev-team/documentation/pseudocode.md

@@ -42,19 +42,11 @@ acl_level: 1
 - Formatting Validation
 - Test Coverage Verification
 - Quality Recommendations
-- Cross-Agent Memory Coordination
+- Algorithm Documentation
 
-## SQLite & Redis Integration
+## Documentation Approach
 
-→ See: `.claude/templates/sqlite-integration.md`
-
-### Memory Persistence Example
-```typescript
-await sqlite.memoryAdapter.set(
-  `agent/${agentId}/pseudocode/${taskId}`,
-  {
-    confidence: 0.85,
-    algorithms: ['auth-algorithm.txt', 'rate-limit-algorithm.txt'],
+Focus on clear, executable algorithm documentation that can be implemented across different programming languages.
     reasoning: "Algorithms designed, complexity analyzed"
   },
   { agentId, aclLevel: 1 }

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

@@ -24,11 +24,7 @@ threshold_targets:
 
 # SPARC Specification Agent
 
-→ Common templates:
-- `.claude/templates/redis-coordination.md`
-- `.claude/templates/memory-operations.md`
-- `.claude/templates/post-edit-validation.md`
-- `.claude/templates/cfn-loop-mechanics.md`
+**This agent focuses on requirements specification and analysis without coordination dependencies.**
 
 ## Team Role Awareness
 
@@ -112,8 +108,7 @@ threshold_targets:
 ## Collaboration and Coordination
 
 ### Cross-Agent Communication
-- Share requirements via SQLite (ACL Level 3)
-- Publish specification events via Redis
+- Share requirements through structured documentation
 - Coordinate with:
   - Analyst agents (requirements refinement)
   - Technical architect (feasibility validation)
@@ -140,15 +135,10 @@ threshold_targets:
 - Confidence score tracking
 - Fallback mechanisms for requirement validation
 
-## Template Inheritance and Extensibility
+## Unique Capabilities
 
-This specification agent inherits from:
-- Redis coordination template
-- SQLite memory operations
-- Post-edit validation hooks
-- CFN Loop mechanics
-
-**Unique Extensions:**
+**Specialized Features:**
 - SPARC-specific requirement gathering techniques
 - Stakeholder analysis methodology
-- Mode-adaptive specification development
+- Structured specification development
+- Evidence-based requirement validation

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