claude-flow-novice 2.5.2 → 2.8.1

package/.claude/agents-ignore/cost-savings-coordinator.md

@@ -0,0 +1,173 @@
+---
+name: cost-savings-coordinator
+description: |
+  Cost-optimized coordinator that spawns z.ai workers via CLI (95-98% cost savings).
+  Use when COST_SAVINGS_MODE=yes in root CLAUDE.md.
+  MUST BE USED for multi-agent coordination with budget constraints.
+  Keywords - cost optimization, CLI spawning, budget-aware coordination
+keywords:
+  - cost-reduction
+  - multi-agent
+  - budget-optimization
+  - redis-coordination
+  - cli-spawning
+tools: [TodoWrite, Read, Glob, Grep, SlashCommand, Bash]
+model: sonnet
+color: orange
+type: coordinator
+acl_level: 3
+validation_hooks:
+  - agent-template-validator
+  - cfn-loop-memory-validator
+  - blocking-coordination-validator
+constraints:
+  - "NEVER implement code directly - ALWAYS delegate to specialist agents"
+  - "Your role is PURE ORCHESTRATION: analyze, plan, delegate, monitor, aggregate"
+  - "ALWAYS use CLI spawning: npx cfn-spawn agent <type> --task-id <id>"
+  - "NEVER use Task tool for agent spawning (use CLI only)"
+  - "Only use Read/Grep/Glob for analysis - never Write/Edit for implementation"
+---
+
+# Cost-Savings Coordinator Agent
+
+You are a cost-optimized orchestration expert specializing in budget-aware multi-agent coordination using CLI-based spawning for 95-98% cost savings.
+
+## Core Responsibilities
+
+1. **Analyze** project requirements and context
+2. **Plan** task decomposition and agent assignments
+3. **Delegate** via CLI spawning (z.ai workers)
+4. **Monitor** agent progress via Redis pub/sub
+5. **Aggregate** results and validate completeness
+
+## Redis Coordination
+
+→ See: .claude/templates/redis-coordination.md
+
+**Quick Reference:**
+- Hierarchical: 1:many dependencies
+- Mesh: 2-5 agents, peer-to-peer
+- Sequential: Linear workflows
+
+## Memory Management
+
+→ See: .claude/templates/memory-operations.md
+
+**Quick Reference:**
+- SQLite: `memory.set(key, value, {agentId, aclLevel})`
+- Redis: `redis-cli setex "key" 3600 "value"`
+
+## Post-Edit Validation
+
+→ See: .claude/templates/post-edit-validation.md
+
+**Critical:** Run hook after every Edit/Write operation
+
+## CLI Spawning (REQUIRED)
+
+### Agent Spawning Patterns
+
+```bash
+# ✅ CORRECT: CLI spawning (cost-optimized)
+npx cfn-spawn agent coder --task "Remove forbidden patterns from doc 1" --task-id "cleanup-001"
+npx cfn-spawn agent coder --task "Remove forbidden patterns from doc 2" --task-id "cleanup-002"
+npx cfn-spawn agent coder --task "Remove forbidden patterns from doc 3" --task-id "cleanup-003"
+```
+
+### Coordination Workflow
+
+```typescript
+// 1. Analyze requirements
+const files = await Glob("readme/logs-*.md");
+const violations = await Grep("97%|cost savings|outperforms", { glob: "readme/logs-*.md" });
+
+// 2. Plan specialist assignments
+const taskDescription = `
+Remove forbidden patterns from documentation:
+- coder-1: Clean logs-features.md
+- coder-2: Clean logs-api.md
+- coder-3: Clean logs-mcp.md
+`;
+
+// 3. Delegate via CLI (REQUIRED)
+await Bash(`npx cfn-spawn agent coder --task "Clean logs-features.md" --task-id "cleanup-features"`);
+await Bash(`npx cfn-spawn agent coder --task "Clean logs-api.md" --task-id "cleanup-api"`);
+await Bash(`npx cfn-spawn agent coder --task "Clean logs-mcp.md" --task-id "cleanup-mcp"`);
+
+// 4. Monitor via Redis
+const results = await monitorRedisCompletions("swarm:*:complete", 3);
+
+// 5. Aggregate and report
+const summary = aggregateResults(results);
+console.log(`Cleanup complete: ${summary.filesProcessed} files`);
+```
+
+### Tool Usage Rules
+
+- ✅ Use Bash for CLI commands (npx cfn-spawn, redis-cli, git, npm)
+- ✅ Use SlashCommand for defined hooks and swarm management
+- ❌ NEVER use Task tool for agent spawning (CLI only!)
+- ❌ Never implement code directly
+
+### Cost Metrics
+
+```typescript
+const costProfile = {
+  coordinator: {
+    cost: 0,              // $0 (Claude Max subscription)
+    model: "sonnet-4.5"
+  },
+  workers: {
+    cost_per_1m: 0.50,    // $0.10-2/1M tokens (z.ai)
+    model: "glm-4.6",
+    savings: "95-98%"     // vs Claude Max workers
+  }
+};
+
+// Example: 5 workers × 200K tokens × $0.50/1M = $0.50 total
+// vs 5 Claude Max × 200K tokens × $15/1M = $15 total
+// Savings: $14.50 (97%)
+```
+
+## Decision Heuristics
+
+```typescript
+const delegationPatterns = {
+  simple_tasks: {
+    agents: [2, 3],
+    success_rate: 0.91,
+    avg_duration: 900000,    // 15 minutes
+    typical_roles: ["coder", "reviewer"],
+    est_cost: "$0.20-0.40"
+  },
+  medium_tasks: {
+    agents: [4, 5],
+    success_rate: 0.84,
+    avg_duration: 1800000,   // 30 minutes
+    typical_roles: ["coder", "tester", "reviewer", "security"],
+    est_cost: "$0.40-1.00"
+  },
+  escalation_threshold: 6  // Consider cfn-loop for complex tasks
+};
+```
+
+## Best Practices
+
+1. Keep task assignments simple (2-5 agents)
+2. Default to parallel execution when tasks are independent
+3. Use specific agent roles over generic roles
+4. Always use CLI spawning (never Task tool)
+5. Monitor cost per phase (report savings)
+6. Use Redis for state management
+7. Persist coordination data to SQLite with appropriate ACL
+
+### When NOT to Use
+
+- Task requires >5 agents (use cfn-loop-coordinator)
+- Complex inter-task dependencies (use cfn-loop-coordinator)
+- Enterprise-grade consensus needed (use cost-savings-cfn-loop-coordinator)
+- Immediate Task tool fallback needed (use coordinator)
+
+---
+
+This agent is optimized for cost-effective multi-agent coordination using CLI-based spawning with z.ai workers for maximum budget efficiency.

package/.claude/artifacts/ace-reflections/REFLECT-001-summary.json

@@ -0,0 +1,39 @@
+{
+  "reflection_id": "REFLECT-001",
+  "curation_status": "complete",
+  "timestamp": "2025-10-21T12:15:00Z",
+  "curator_agent": "context-curator",
+  "new_bullets_added": [
+    {
+      "id": "PATTERN-009",
+      "category": "pattern",
+      "title": "Multi-Pattern Confidence Parsing",
+      "confidence": 0.95,
+      "priority": 9
+    },
+    {
+      "id": "STRAT-014",
+      "category": "strategy",
+      "title": "Skill Interface Consistency",
+      "confidence": 0.90,
+      "priority": 8
+    },
+    {
+      "id": "EDGE-012",
+      "category": "edge_case",
+      "title": "Output Processing Error Handling",
+      "confidence": 0.88,
+      "priority": 7
+    }
+  ],
+  "recommended_next_steps": [
+    "Update orchestration documentation with new parsing strategies",
+    "Enhance test coverage for output processing skills",
+    "Create comprehensive fallback parsing reference"
+  ],
+  "metrics": {
+    "total_active_bullets": 25,
+    "average_confidence": 0.88,
+    "curation_confidence": 0.95
+  }
+}

package/.claude/artifacts/ace-reflections/sprint-7_$(date -u +/"%Y%m%d_%H%M%S/").json"

@@ -0,0 +1,47 @@
+{
+    "sprint": 7,
+    "lessons": [
+        {
+            "bullet_id": "STRAT-007",
+            "category": "strategy",
+            "content": "When implementing long-running orchestration workflows (>10 minutes), use background execution with Redis-based status monitoring instead of synchronous Bash calls. Bash tool has hard 10-minute timeout limit that cannot be extended.",
+            "confidence": 0.95,
+            "tags": ["orchestration", "bash-timeout", "redis-monitoring", "background-execution"]
+        },
+        {
+            "bullet_id": "PATTERN-008",
+            "category": "pattern",
+            "content": "Implement a strategic Product Owner decision flow that provides explicit PROCEED/ITERATE/ABORT options after Loop 2 consensus to prevent validator scope creep and maintain clear workflow boundaries.",
+            "confidence": 0.90,
+            "tags": ["workflow-management", "consensus", "product-owner", "decision-flow"]
+        },
+        {
+            "bullet_id": "EDGE-005",
+            "category": "edge_case",
+            "content": "Enforce strict agent ID consistency across orchestrator and CLI spawning by using iteration-suffixed tracking arrays and dynamic agent selection based on task keywords to prevent orchestrator hanging.",
+            "confidence": 0.88,
+            "tags": ["agent-management", "id-tracking", "spawning", "consistency"]
+        },
+        {
+            "bullet_id": "OPT-006",
+            "category": "optimization",
+            "content": "Implement token limit strategies with headroom, targeting 10K tokens with a hard limit of 16K, and use incremental output patterns to handle complex, multi-stage agent workflows.",
+            "confidence": 0.85,
+            "tags": ["token-management", "llm-optimization", "incremental-processing"]
+        },
+        {
+            "bullet_id": "ANTI-004",
+            "category": "anti_pattern",
+            "content": "Avoid using simplistic regex matching for agent validation, such as `[[ \" $AGENTS \" =~ \" $AGENTS \" ]]`, which creates false-positive matches and breaks agent tracking logic.",
+            "confidence": 0.92,
+            "tags": ["regex", "validation", "agent-tracking", "error-prevention"]
+        },
+        {
+            "bullet_id": "DOMAIN-003",
+            "category": "domain_insight",
+            "content": "Design orchestration systems with explicit, unbound state management for tracking agent completion, ensuring that components like LOOP2_COMPLETED_AGENTS can handle dynamic workflow iterations without premature termination.",
+            "confidence": 0.87,
+            "tags": ["orchestration", "state-management", "workflow-design", "agent-coordination"]
+        }
+    ]
+}

package/.claude/artifacts/reflection-merge-logs/cli-agent-spawning-v2.5.2-merge-report.md

@@ -0,0 +1,61 @@
+# Reflection Curation Report: CLI Agent Spawning v2.5.2
+
+## Merge Actions Performed:
+
+**1. PATTERN-001: Environment Configuration Strategy**
+- Action: ADD_NEW_BULLET
+- Reasoning: Novel insight about CLI environment loading
+- Priority: 9/10 (critical)
+- Confidence: 0.95
+- Tags: environment, configuration, cli, dotenv
+
+**2. PATTERN-002: API Provider Integration**
+- Action: ADD_NEW_BULLET
+- Reasoning: Novel domain insight for multi-provider systems
+- Priority: 8/10 (critical)
+- Confidence: 0.92
+- Tags: api-integration, provider-mapping, resilience, configuration
+
+**3. PATTERN-003: Streaming Compatibility**
+- Action: ADD_NEW_BULLET
+- Reasoning: Novel optimization pattern for API compatibility
+- Priority: 7/10 (important)
+- Confidence: 0.88
+- Tags: streaming, api-compatibility, fallback, optimization
+
+**4. PATTERN-004: Resilient API Calls**
+- Action: ADD_NEW_BULLET
+- Reasoning: Critical edge case handling pattern
+- Priority: 9/10 (critical)
+- Confidence: 0.90
+- Tags: error-handling, timeout, resilience, api-calls
+
+**5. PATTERN-005: Development Testing Anti-Pattern**
+- Action: ADD_NEW_BULLET
+- Reasoning: Helpful anti-pattern to avoid
+- Priority: 6/10 (helpful)
+- Confidence: 0.85
+- Tags: testing, development, package-management, build-verification
+
+## Merge Metadata
+
+- **Reflection ID**: cli-agent-spawning-v2.5.2
+- **Curator Status**: Merged
+- **Merge Timestamp**: 2025-10-20T10:49:00Z
+- **Total Bullets Added**: 5
+- **Average Confidence**: 0.90
+
+## Recommended Next Actions
+
+1. Context Injection:
+```bash
+/context-inject --category=strategy,domain_insight,edge_case
+```
+
+2. Monitor Usage:
+- Track helpful/harmful feedback for these patterns
+- Consider integration into agent-specific prompts for CLI development
+
+3. Follow-up Validation:
+- Run comprehensive tests validating these patterns
+- Collect real-world usage data to confirm effectiveness

package/.claude/commands/CFN_COORDINATOR_PARAMETERS.md

@@ -19,7 +19,7 @@ This document defines the structured parameter specification for CFN Loop coordi
 ```
 /cfn-loop "task"
   ↓
-Main Chat spawns ONE agent: cost-savings-cfn-loop-coordinator
+Main Chat spawns ONE agent: cfn-v3-coordinator
   ↓
 Coordinator runs orchestrate-cfn-loop.sh internally
   ↓
@@ -202,7 +202,7 @@ Product Owner: product-owner
 **Loop 3 (Implementation):**
 - `researcher` - Requirement analysis, research
 - `backend-dev` - Backend implementation
-- `frontend-dev` - Frontend implementation (if needed)
+- `react-frontend-engineer` - Frontend implementation (if needed)
 - `devops` - Infrastructure, deployment
 
 **Loop 2 (Validation):**
@@ -222,7 +222,7 @@ Product Owner: product-owner
 
 ```bash
 1. INVOKE ORCHESTRATOR:
-   ./.claude/skills/redis-coordination/orchestrate-cfn-loop.sh \
+   ./.claude/skills/cfn-loop-orchestration/orchestrate.sh \
      --task-id "${taskId}" \
      --mode ${mode} \
      --loop3-agents "${loop3Agents.join(',')}" \
@@ -435,7 +435,7 @@ Epic-Level Acceptance Criteria:
 ### Example 1: MVP Mode Single Task
 
 ```javascript
-Task("cost-savings-cfn-loop-coordinator", `
+Task("cfn-v3-coordinator", `
   CFN LOOP EXECUTION - STRUCTURED PARAMETERS
 
   ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
@@ -488,7 +488,7 @@ Task("cost-savings-cfn-loop-coordinator", `
   ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
 
   1. INVOKE ORCHESTRATOR:
-     ./.claude/skills/redis-coordination/orchestrate-cfn-loop.sh \\
+     ./.claude/skills/cfn-loop-orchestration/orchestrate.sh \\
        --task-id "cfn-mvp-registration-1729350000" \\
        --mode mvp \\
        --loop3-agents "backend-dev" \\
@@ -517,13 +517,13 @@ Task("cost-savings-cfn-loop-coordinator", `
   - LET orchestrator handle CLI spawning
   - USE Redis BLPOP for dependencies
   - RETURN structured result
-`, "cost-savings-cfn-loop-coordinator")
+`, "cfn-v3-coordinator")
 ```
 
 ### Example 2: Enterprise Mode Multi-Phase Epic
 
 ```javascript
-Task("cost-savings-cfn-loop-coordinator", `
+Task("cfn-v3-coordinator", `
   CFN LOOP EPIC EXECUTION - MULTI-PHASE
 
   ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
@@ -585,10 +585,10 @@ Task("cost-savings-cfn-loop-coordinator", `
   1. CHECK DEPENDENCIES
   2. STORE SCOPE BOUNDARIES (memory)
   3. INVOKE ORCHESTRATOR:
-     ./.claude/skills/redis-coordination/orchestrate-cfn-loop.sh \\
+     ./.claude/skills/cfn-loop-orchestration/orchestrate.sh \\
        --task-id "phase-X-$(date +%s)" \\
        --mode enterprise \\
-       --loop3-agents "backend-dev,frontend-dev,devops,security-specialist,researcher" \\
+       --loop3-agents "backend-dev,react-frontend-engineer,devops,security-specialist,researcher" \\
        --loop2-agents "reviewer,architect,tester,security-specialist,performance-analyst" \\
        --product-owner "product-owner" \\
        --max-iterations 15
@@ -616,7 +616,7 @@ Task("cost-savings-cfn-loop-coordinator", `
   - AUTO-TRANSITION between phases
   - DEFER out-of-scope items
   - RETURN epic summary
-`, "cost-savings-cfn-loop-coordinator")
+`, "cfn-v3-coordinator")
 ```
 
 ---

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

@@ -97,7 +97,7 @@ The coordinator uses CLI spawning per phase and provides full visibility via web
 ### Epic Pattern (SINGLE COORDINATOR FOR ALL PHASES)
 
 ```javascript
-Task("cost-savings-cfn-loop-coordinator", `
+Task("cfn-v3-coordinator", `
   CFN LOOP EPIC EXECUTION - MULTI-PHASE
 
   ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
@@ -141,13 +141,23 @@ Task("cost-savings-cfn-loop-coordinator", `
   Epic ID: epic-$(date +%s)
   Mode: STANDARD (gate: 0.75, consensus: 0.90)
 
-  Phases:
-  ${epicPhases.map((p, i) =>
-    \`  Phase \${i+1}: \${p.name}
-    - Deliverables: \${p.deliverables.join(', ')}
-    - Dependencies: \${p.dependencies.join(', ') || 'None'}
-    - Estimated agents: \${p.estimated_agents}\`
-  ).join('\n')}
+  Phases (ANALYZE EPIC AND DEFINE):
+  # Parse epic description and break into phases
+  # Example structure:
+  Phase 0: Assessment
+    - Deliverables: Requirements analysis, Architecture design
+    - Dependencies: None
+    - Estimated agents: 2 (analyst, architect)
+
+  Phase 1: Core Implementation
+    - Deliverables: Main features, API endpoints
+    - Dependencies: Phase 0
+    - Estimated agents: 3 (backend-dev, researcher, devops)
+
+  Phase 2: Validation
+    - Deliverables: Tests, Security audit, Documentation
+    - Dependencies: Phase 0, Phase 1
+    - Estimated agents: 3 (tester, reviewer, security-specialist)
 
   ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
   EPIC-LEVEL SUCCESS CRITERIA
@@ -155,11 +165,17 @@ Task("cost-savings-cfn-loop-coordinator", `
 
   Scope Boundaries (CRITICAL - ENFORCE STRICTLY):
 
-  In Scope:
-  - ${inScopeItems.join('\n  - ')}
+  In Scope (EXAMPLE - CUSTOMIZE FOR YOUR EPIC):
+  - Feature implementation as described
+  - Basic testing and validation
+  - Essential documentation
+  - Security fundamentals
 
-  Out of Scope (DEFER TO BACKLOG):
-  - ${outOfScopeItems.join('\n  - ')}
+  Out of Scope (DEFER TO BACKLOG - EXAMPLE):
+  - Advanced features not in core spec
+  - Performance optimization beyond basics
+  - Additional integrations
+  - Nice-to-have features
 
   Epic-Level Acceptance Criteria:
   - [ ] All phases complete with consensus ≥0.90
@@ -192,12 +208,20 @@ Task("cost-savings-cfn-loop-coordinator", `
      })
 
   3. INVOKE ORCHESTRATOR FOR PHASE:
-     ./.claude/skills/redis-coordination/orchestrate-cfn-loop.sh \\
-       --task-id "phase-${PHASE_ID}-$(date +%s)" \\
-       --mode standard \\
-       --loop3-agents "backend-dev,frontend-dev,devops" \\
-       --loop2-agents "reviewer,architect,tester,security-specialist" \\
-       --product-owner "product-owner" \\
+     # Generate task ID and construct bash command with actual values
+     # DO NOT use template literals - construct real bash variables
+
+     TASK_ID="phase-0-$(date +%s)"
+     MODE="standard"
+     LOOP3_AGENTS="analyst,architect"
+     LOOP2_AGENTS="reviewer,architect"
+
+     ./.claude/skills/cfn-loop-orchestration/orchestrate.sh \
+       --task-id "$TASK_ID" \
+       --mode "$MODE" \
+       --loop3-agents "$LOOP3_AGENTS" \
+       --loop2-agents "$LOOP2_AGENTS" \
+       --product-owner "product-owner" \
        --max-iterations 10
 
   4. STORE PHASE RESULTS:
@@ -269,7 +293,7 @@ Task("cost-savings-cfn-loop-coordinator", `
   - DEFER out-of-scope items to backlog
   - PUBLISH events per phase
   - RETURN epic summary when complete
-`, "cost-savings-cfn-loop-coordinator")
+`, "cfn-v3-coordinator")
 ```
 
 ### Coordinator Autonomous Multi-Phase Execution

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

@@ -33,7 +33,7 @@ The coordinator uses CLI spawning (95-98% cost savings) and provides full visibi
 ### Step 1: Spawn Coordinator Agent (SINGLE AGENT PATTERN)
 
 ```javascript
-Task("cost-savings-cfn-loop-coordinator", `
+Task("cfn-v3-coordinator", `
   CFN LOOP SINGLE TASK EXECUTION
 
   ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
@@ -120,7 +120,7 @@ Task("cost-savings-cfn-loop-coordinator", `
   ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
 
   1. INVOKE ORCHESTRATOR:
-     ./.claude/skills/redis-coordination/orchestrate-cfn-loop.sh \\
+     ./.claude/skills/cfn-loop-orchestration/orchestrate.sh \\
        --task-id "cfn-single-$(date +%s)" \\
        --mode standard \\
        --loop3-agents "researcher,backend-dev,devops" \\
@@ -155,7 +155,7 @@ Task("cost-savings-cfn-loop-coordinator", `
   - USE Redis BLPOP for dependencies
   - PUBLISH events to web-portal channel
   - RETURN structured result to Main Chat
-`, "cost-savings-cfn-loop-coordinator")
+`, "cfn-v3-coordinator")
 ```
 
 ### Step 2: Coordinator Autonomous Execution

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

@@ -111,7 +111,7 @@ Task("CFN Loop Coordinator", `
 
   MANDATORY: Use orchestrator script for dependency enforcement.
 
-  ./.claude/skills/redis-coordination/orchestrate-cfn-loop.sh \
+  ./.claude/skills/cfn-loop-orchestration/orchestrate.sh \
     --task-id "sprint-${sprintId}-$(date +%s)" \
     --mode standard \
     --loop3-agents "backend-dev,tester,security-specialist" \