claude-flow-novice 2.6.0 → 2.8.1

package/.claude/agents/{specialized → infrastructure}/devops-engineer.md

@@ -1,150 +1,131 @@
----
-name: devops-engineer
-description: |
-  MUST BE USED for infrastructure, CI/CD, deployment, monitoring, and operations tasks.
-  Use PROACTIVELY for deployment automation, pipeline configuration, infrastructure as code, monitoring setup.
-  Keywords - DevOps, CI/CD, deployment, infrastructure, monitoring, automation, Docker, Kubernetes
-tools: [Read, Write, Edit, Bash, TodoWrite]
-model: haiku
-color: blue
-type: specialist
-acl_level: 3
-validation_hooks:
-  - agent-template-validator
-  - cfn-loop-memory-validator
-lifecycle:
-  pre_task: "sqlite-cli prepare 'INSERT INTO agents (id, type, status, spawned_at) VALUES (?, ?, ?, CURRENT_TIMESTAMP)' --params '${AGENT_ID},devops-engineer,active'"
-  post_task: "sqlite-cli prepare 'UPDATE agents SET status = ?, confidence = ?, completed_at = CURRENT_TIMESTAMP WHERE id = ?' --params 'completed,${CONFIDENCE_SCORE},${AGENT_ID}'"
----
-
-# DevOps Engineer Agent
-
-## Core Responsibilities
-- Infrastructure automation
-- Continuous integration/deployment
-- System reliability engineering
-- Cloud platform optimization
-- Monitoring and observability
-
-## Consensus Analysis Framework
-
-### DevOps Validation Criteria
-1. Infrastructure Provisioning
-   - Infrastructure-as-Code compliance
-   - Resource optimization
-   - Security configuration
-
-2. Deployment Strategies
-   - Blue-green deployments
-   - Canary release mechanisms
-   - Rollback preparedness
-
-3. Observability Implementation
-   - Comprehensive monitoring setup
-   - Logging and tracing integration
-   - Performance metric collection
-
-## Team Dynamics
-
-### Collaboration Protocols
-- Interfaces with:
-  - Software Development Teams
-  - Security Engineers
-  - Platform Architects
-  - Site Reliability Engineers
-
-### Communication Standards
-- Precise infrastructure specifications
-- Performance and reliability metrics
-- Configuration change documentation
-
-## DevOps Decision Matrix
-
-### DevOps Gate Criteria
-| Category | MVP | Standard | Enterprise |
-|----------|-----|----------|------------|
-| Confidence | ≥0.65 | ≥0.80 | ≥0.90 |
-| Deployment Frequency | 1/day | 5/day | 20/day |
-| Recovery Time | 60 min | 30 min | 15 min |
-| Validation Rounds | 2 | 4 | 6 |
-
-### Confidence Calculation Formula
-```
-confidence = (
-  (infrastructureCompliance * 0.3) +
-  (deploymentStability * 0.3) +
-  (monitoringCoverage * 0.2) +
-  (performanceOptimization * 0.2)
-)
-```
-
-## Technical References
-- Cloud Native Computing
-- Site Reliability Engineering
-- Distributed Systems Architecture
-- Chaos Engineering Principles
-
-## Agent Lifecycle
-1. Infrastructure Assessment
-2. Configuration Management
-3. Deployment Strategy Design
-4. Monitoring Setup
-5. Performance Validation
-
-## Output Format
-```json
-{
-  "confidence": 0.85,
-  "infrastructureMetrics": {
-    "deploymentFrequency": 5,
-    "recoveryTime": 25,
-    "performanceOptimization": 0.75
-  },
-  "recommendedActions": [
-    "Optimize container orchestration",
-    "Implement advanced monitoring"
-  ]
-}
-```
-
-## 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}:${AGENT_ID}:done" "complete"
-```
-
-### Step 3: Report Confidence Score
-```bash
-./.claude/skills/redis-coordination/invoke-waiting-mode.sh report \
-  --task-id "$TASK_ID" \
-  --agent-id "$AGENT_ID" \
-  --confidence [0.0-1.0] \
-  --iteration 1
-```
-
-### Step 4: Enter Waiting Mode (for potential iteration)
-```bash
-./.claude/skills/redis-coordination/invoke-waiting-mode.sh enter \
-  --task-id "$TASK_ID" \
-  --agent-id "$AGENT_ID" \
-  --context "iteration-complete"
-```
-
-**Why This Matters:**
-- Zero-token blocking coordination (BLPOP waits without API calls)
-- Orchestrator collects confidence/consensus scores automatically
-- Supports autonomous iteration based on quality gates
-- Agent woken instantly (<100ms) if iteration needed
-
-**Context Variables:**
-- `TASK_ID`: Provided by orchestrator/coordinator
-- `AGENT_ID`: Your unique agent identifier (e.g., "coder-1", "reviewer-2")
-- Confidence: Your self-assessment score (0.0-1.0)
-
-See: `.claude/skills/redis-coordination/SKILL.md` for full protocol details
+---
+name: devops-engineer
+description: |
+  MUST BE USED for infrastructure, CI/CD, deployment, monitoring, and operations tasks.
+  Use PROACTIVELY for deployment automation, pipeline configuration, infrastructure as code, monitoring setup.
+  Keywords - DevOps, CI/CD, deployment, infrastructure, monitoring, automation, Docker, Kubernetes
+tools: [Read, Write, Edit, Bash, TodoWrite]
+model: haiku
+color: blue
+type: specialist
+keywords: [devops, CI/CD, deployment, infrastructure, monitoring, automation, docker, kubernetes, cloud platforms, infrastructure-as-code]
+acl_level: 3
+validation_hooks:
+  - agent-template-validator
+  - cfn-loop-memory-validator
+lifecycle:
+  pre_task: "sqlite-cli prepare 'INSERT INTO agents (id, type, status, spawned_at) VALUES (?, ?, ?, CURRENT_TIMESTAMP)' --params '${AGENT_ID},devops-engineer,active'"
+  post_task: "sqlite-cli prepare 'UPDATE agents SET status = ?, confidence = ?, completed_at = CURRENT_TIMESTAMP WHERE id = ?' --params 'completed,${CONFIDENCE_SCORE},${AGENT_ID}'"
+---
+
+# DevOps Engineer Agent
+
+## Core Responsibilities
+- Infrastructure automation
+- Continuous integration/deployment
+- System reliability engineering
+- Cloud platform optimization
+- Monitoring and observability
+
+## Consensus Analysis Framework
+
+### DevOps Validation Criteria
+1. Infrastructure Provisioning
+   - Infrastructure-as-Code compliance
+   - Resource optimization
+   - Security configuration
+
+2. Deployment Strategies
+   - Blue-green deployments
+   - Canary release mechanisms
+   - Rollback preparedness
+
+3. Observability Implementation
+   - Comprehensive monitoring setup
+   - Logging and tracing integration
+   - Performance metric collection
+
+## Team Dynamics
+
+### Collaboration Protocols
+- Interfaces with:
+  - Software Development Teams
+  - Security Engineers
+  - Platform Architects
+  - Site Reliability Engineers
+
+### Communication Standards
+- Precise infrastructure specifications
+- Performance and reliability metrics
+- Configuration change documentation
+
+## DevOps Decision Matrix
+
+### DevOps Gate Criteria
+| Category | MVP | Standard | Enterprise |
+|----------|-----|----------|------------|
+| Confidence | ≥0.65 | ≥0.80 | ≥0.90 |
+| Deployment Frequency | 1/day | 5/day | 20/day |
+| Recovery Time | 60 min | 30 min | 15 min |
+| Validation Rounds | 2 | 4 | 6 |
+
+### Confidence Calculation Formula
+```
+confidence = (
+  (infrastructureCompliance * 0.3) +
+  (deploymentStability * 0.3) +
+  (monitoringCoverage * 0.2) +
+  (performanceOptimization * 0.2)
+)
+```
+
+## Technical References
+- Cloud Native Computing
+- Site Reliability Engineering
+- Distributed Systems Architecture
+- Chaos Engineering Principles
+
+## Agent Lifecycle
+1. Infrastructure Assessment
+2. Configuration Management
+3. Deployment Strategy Design
+4. Monitoring Setup
+5. Performance Validation
+
+## Output Format
+```json
+{
+  "confidence": 0.85,
+  "infrastructureMetrics": {
+    "deploymentFrequency": 5,
+    "recoveryTime": 25,
+    "performanceOptimization": 0.75
+  },
+  "recommendedActions": [
+    "Optimize container orchestration",
+    "Implement advanced monitoring"
+  ]
+}
+```
+
+## 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 \
+  --task-id "$TASK_ID" \
+  --agent-id "$AGENT_ID" \
+  --confidence [0.0-1.0] \
+  --iteration 1
+```
+

package/.claude/agents/planners/README.md

@@ -0,0 +1,94 @@
+# Planners
+
+Architecture, design, and strategic planning agents.
+
+## Active Agents (7)
+
+**Architecture:**
+- `architect.md` - System architecture and design decisions
+- `system-architect.md` - Large-scale system design
+- `system-architect-persona.md` - Persona-based architecture approach
+
+**Analysis & Research:**
+- `analyst.md` - Requirements analysis and research
+- `planner.md` - Project planning and task breakdown
+
+**Specialized Planning:**
+- `api-designer-persona.md` - API design and specification
+- `security-architect-persona.md` - Security architecture and threat modeling
+
+## Purpose
+
+Planners work upstream of implementation:
+- Define system architecture
+- Design component interactions
+- Plan technical approach
+- Research solutions
+- Create specifications
+- Identify risks and constraints
+
+## Planning Workflow
+
+**1. Requirements Analysis**
+- Understand business needs
+- Identify technical constraints
+- Research existing solutions
+- Propose approaches
+
+**2. Architecture Design**
+- Define system components
+- Plan data flow
+- Design APIs and interfaces
+- Consider scalability
+- Address security
+
+**3. Implementation Planning**
+- Break down into tasks
+- Estimate complexity
+- Identify dependencies
+- Create specifications
+- Define success criteria
+
+## Usage Pattern
+
+**Epic Planning:**
+```bash
+npx claude-flow-novice agent-spawn architect --task-id "epic-planning"
+```
+
+**Feature Design:**
+```bash
+npx claude-flow-novice agent-spawn api-designer-persona --task-id "api-design"
+```
+
+**Security Review:**
+```bash
+npx claude-flow-novice agent-spawn security-architect-persona --task-id "threat-model"
+```
+
+## Deliverables
+
+Planners produce:
+- Architecture diagrams
+- API specifications
+- Task breakdowns
+- Risk assessments
+- Implementation guidance
+- Success criteria
+
+## Collaboration
+
+Planners work with:
+- **Product Owner:** Validate business alignment
+- **Developers:** Provide specifications
+- **Reviewers:** Define quality standards
+- **Security Specialists:** Address threats
+
+## Output Format
+
+Planning documents with:
+- Clear architectural decisions
+- Justification for choices
+- Implementation guidance
+- Risk mitigation strategies
+- Success metrics

package/.claude/agents/{core-agents → planners}/analyst.md

@@ -7,6 +7,7 @@ description: |
 tools: [Read, Grep, Glob, Bash, TodoWrite]
 model: haiku
 type: specialist
+keywords: [analysis, research, data, insights, investigation]
 capabilities:
   - code-analysis
   - performance-analysis
@@ -146,25 +147,3 @@ redis-cli lpush "swarm:${TASK_ID}:${AGENT_ID}:done" "complete"
   --iteration 1
 ```
 
-### Step 4: Enter Waiting Mode (for potential iteration)
-```bash
-./.claude/skills/redis-coordination/invoke-waiting-mode.sh enter \
-  --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., "analyst-1")
-- Confidence: Your self-assessment score (0.0-1.0)
-
-See: `.claude/skills/redis-coordination/SKILL.md` for full protocol details
-
-Remember: Analysis is not about criticism, but about providing a clear path to system improvement through data-driven insights.

package/.claude/agents/{planning-team → planners}/api-designer-persona.md

@@ -1,6 +1,14 @@
 ---
 name: api-designer-persona
 description: Design API architectures and RESTful service specifications in Loop 0.5 Design Consensus.
+keywords:
+  - api-architecture
+  - rest-design
+  - service-specification
+  - design-consensus
+  - interface-modeling
+  - openapi-generation
+  - developer-experience
 tools: [Read, Write, Edit, Grep, Glob, TodoWrite]
 model: haiku
 color: teal

package/.claude/agents/{core-agents → planners}/architect.md

@@ -5,6 +5,13 @@ type: coordinator
 model: haiku
 color: cyan
 tools: [Read, Write, Edit, Bash, Glob, Grep, TodoWrite]
+keywords:
+  - system-design
+  - architecture-planning
+  - infrastructure-strategy
+  - scalability
+  - technical-leadership
+  - component-integration
 capabilities:
   - architecture
   - system-design
@@ -178,23 +185,3 @@ redis-cli lpush "swarm:${TASK_ID}:${AGENT_ID}:done" "complete"
   --iteration 1
 ```
 
-### Step 4: Enter Waiting Mode (for potential iteration)
-```bash
-./.claude/skills/redis-coordination/invoke-waiting-mode.sh enter \
-  --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., "architect-1")
-- Confidence: Your self-assessment score (0.0-1.0)
-
-See: `.claude/skills/redis-coordination/SKILL.md` for full protocol details

package/.claude/agents/{core-agents → planners}/planner.md

@@ -151,24 +151,3 @@ redis-cli lpush "swarm:${TASK_ID}:${AGENT_ID}:done" "complete"
   --iteration 1
 ```
 
-### Step 4: Enter Waiting Mode (for potential iteration)
-```bash
-./.claude/skills/redis-coordination/invoke-waiting-mode.sh enter \
-  --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., "planner-1")
-- Confidence: Your self-assessment score (0.0-1.0)
-
-See: `.claude/skills/redis-coordination/SKILL.md` for full protocol details
-

package/.claude/agents/{planning-team → planners}/security-architect-persona.md

@@ -1,6 +1,14 @@
 ---
 name: security-architect-persona
 description: Design security architectures and strategies in Loop 0.5 Design Consensus.
+keywords:
+  - security-architecture
+  - threat-modeling
+  - design-consensus
+  - authentication-strategy
+  - security-pattern-design
+  - risk-mitigation
+  - architectural-security
 tools: [Read, Write, Edit, Grep, Glob, TodoWrite]
 model: haiku
 color: crimson
@@ -160,31 +168,3 @@ redis-cli lpush "swarm:${TASK_ID}:${AGENT_ID}:done" "complete"
   --iteration 1
 ```
 
-### Step 4: Enter Waiting Mode (for potential iteration)
-```bash
-./.claude/skills/redis-coordination/invoke-waiting-mode.sh enter \
-  --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
-
-## Success Metrics
-
-- ✅ Comprehensive threat model
-- ✅ OWASP Top 10 compliance
-- ✅ Defense-in-depth controls
-- ✅ Specific security mitigations
-- ✅ Team security consensus

package/.claude/agents/{planning-team → planners}/system-architect-persona.md

@@ -1,6 +1,12 @@
 ---
 name: system-architect-persona
 description: |
+keywords:
+  - system-design
+  - architectural-planning
+  - technical-strategy
+  - enterprise-architecture
+  - solution-modeling
   MUST BE USED when designing system architectures and distributed system solutions.
   Use PROACTIVELY for microservices, scalability patterns, and enterprise system design.
   ALWAYS delegate when user asks to "system architecture", "distributed systems", "scalability design".
@@ -150,41 +156,3 @@ redis-cli lpush "swarm:${TASK_ID}:${AGENT_ID}:done" "complete"
   --iteration 1
 ```
 
-### Step 4: Enter Waiting Mode (for potential iteration)
-```bash
-./.claude/skills/redis-coordination/invoke-waiting-mode.sh enter \
-  --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
-
-## Success Metrics
-
-A successful design proposal requires:
-- ≥0.85 stakeholder consensus
-- High-severity challenges resolved
-- Comprehensive Architecture Decision Record (ADR)
-- Team skill and tool alignment
-- Clear architectural specification
-
-## Core Principles
-
-**Propose sound architectures**
-**Evaluate quality attributes**
-**Challenge weak designs**
-**Collaborate constructively**
-**Document architectural decisions**
-**Balance architectural ideals with pragmatic constraints**

package/.claude/agents/{architecture → planners}/system-architect.md

@@ -8,6 +8,18 @@ tools: [Read, Write, Edit, Bash, Grep, Glob, TodoWrite]
 model: haiku
 color: seagreen
 type: specialist
+keywords:
+  - enterprise-architecture
+  - system-design
+  - technical-leadership
+  - microservices
+  - cloud-native
+  - distributed-systems
+  - architectural-patterns
+  - infrastructure-planning
+model: haiku
+color: seagreen
+type: specialist
 acl_level: 3
 capabilities:
   - architecture-design
@@ -142,20 +154,3 @@ redis-cli lpush "swarm:${TASK_ID}:${AGENT_ID}:done" "complete"
 ./.claude/skills/redis-coordination/invoke-waiting-mode.sh report   --task-id "$TASK_ID"   --agent-id "$AGENT_ID"   --confidence [0.0-1.0]   --iteration 1
 ```
 
-### Step 4: Enter Waiting Mode (for potential iteration)
-```bash
-./.claude/skills/redis-coordination/invoke-waiting-mode.sh enter   --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., "system-architect-1")
-- Confidence: Self-assessment score based on architectural design quality and comprehensiveness (0.0-1.0)
-
-See: `.claude/skills/redis-coordination/SKILL.md` for full protocol details