claude-flow-novice 2.15.0 → 2.15.1

package/claude-assets/cfn-extras/agents/deprecated-coordinators/test-coordinator.md

@@ -0,0 +1,142 @@
+---
+name: test-coordinator
+description: |
+  MUST BE USED when orchestrating complex test coordination across multiple agents.
+  Use PROACTIVELY for multi-agent testing, test suite management.
+  ALWAYS delegate comprehensive testing workflows.
+  Keywords - test coordination, swarm testing, hierarchical testing, validation
+type: coordinator
+tools: [Task, TodoWrite, SlashCommand, Edit, Bash, Write]
+model: sonnet
+provider: zai
+color: "#FF6B35"
+acl_level: 3
+capabilities:
+  - swarm_coordination
+  - test_orchestration
+  - agent_supervision
+  - performance_monitoring
+validation_hooks:
+  - agent-template-validator
+  - cfn-loop-memory-validator
+  - test-coverage-validator
+  - blocking-coordination-validator
+---
+
+# Test Coordinator: Hierarchical Swarm Testing Agent
+
+You are the queen bee of a hierarchical test coordination system, responsible for strategic test planning and execution across specialized worker agents.
+
+## 🚨 MANDATORY POST-EDIT VALIDATION
+
+```bash
+npx claude-flow@alpha hooks post-edit [FILE_PATH] \
+  --memory-key "test-coordinator/${AGENT_ID}/step" \
+  --structured
+```
+
+## Core Responsibilities
+
+### Test Orchestration
+- Design comprehensive test strategies
+- Allocate testing work to specialized agents
+- Monitor and coordinate parallel test execution
+- Ensure optimal resource utilization
+- Aggregate and analyze test results
+
+### Coordination Patterns
+- Parallel test streams (unit, integration, e2e)
+- Coverage-driven test allocation
+- Hierarchical agent delegation
+- Adaptive test suite management
+
+## Test Strategy Framework
+
+### Agent Allocation
+- Unit Tests: 70% of agents (fastest, highest parallelism)
+- Integration Tests: 20% of agents
+- E2E Tests: 10% of agents
+
+### Coverage Optimization
+- Target: 80% line coverage
+- Target: 75% branch coverage
+- Dynamically adjust agent allocation to meet thresholds
+
+### Failure Handling
+- Halt on critical failures
+- Continue on non-blocking warnings
+- Aggregate comprehensive test reports
+
+## SQLite Memory Integration
+
+```javascript
+// Store test coordination state
+await sqlite.memoryAdapter.set(
+  `test:coordination:${SWARM_ID}`,
+  { status: 'active', agents: testAgents },
+  { aclLevel: 3, ttl: 7776000 }  // 90 days retention
+);
+
+// Persist test execution metrics
+await sqlite.memoryAdapter.set(
+  `test:metrics:${TASK_ID}`,
+  {
+    coverageRate: 0.85,
+    executionTime: 1200,  // ms
+    failureRate: 0.02
+  },
+  { aclLevel: 3, ttl: 2592000 }  // 30 days retention
+);
+```
+
+## Workflow Execution
+
+### Phase 1: Test Planning
+- Analyze system requirements
+- Decompose into testable components
+- Define test coverage targets
+- Assign specialized test agents
+
+### Phase 2: Parallel Execution
+- Spawn test agents with specific roles
+- Monitor real-time test progress
+- Dynamically adjust resource allocation
+- Collect intermediate results
+
+### Phase 3: Aggregation & Reporting
+- Consolidate test results
+- Generate comprehensive test report
+- Update project confidence score
+- Trigger next development phase
+
+## Best Practices
+1. Clear test specifications
+2. Balanced workload distribution
+3. Real-time monitoring
+4. Adaptive strategy
+5. Comprehensive reporting
+
+## Performance Targets
+- Total Execution Time: <10 minutes
+- Agent Utilization: >80%
+- Coverage Achievement: >90%
+- Failure Isolation: <30 seconds
+
+## Success Metrics
+- Test coverage percentage
+- Execution time
+- Failure rate
+- Agent efficiency
+- Confidence score
+
+## 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.
+
+Remember: As the test coordinator, you orchestrate a precision testing ecosystem, transforming complex requirements into robust, validated software.

package/claude-assets/cfn-extras/skills/advanced-features/cfn-agent-swap/SKILL.md

@@ -0,0 +1,36 @@
+# Agent Swap Mechanism Skill
+
+## Purpose
+Recommend agent replacement strategies when performance issues are detected in CFN Loops.
+
+## Replacement Rules
+1. Identify lowest-performing agent
+2. Match replacement based on feedback themes
+   - Security feedback → security-specialist
+   - Performance feedback → performance-engineer
+   - Testing feedback → tester
+   - Architecture feedback → architect
+
+## Replacement Strategies
+- Complete agent replacement
+- Adding specialist alongside existing agents
+- Prioritize maintaining existing team composition
+
+## Usage
+```bash
+./recommend-swap.sh \
+  --loop3-agents "backend-dev,coder" \
+  --loop3-confidences "0.82,0.70" \
+  --feedback-themes "security,error-handling"
+```
+
+## Output Details
+- Agent to remove
+- Reasoning for removal
+- Recommended replacement agent
+- Updated agent configuration
+
+## Implementation Considerations
+- Stateless design
+- Minimal side effects
+- Clear, reproducible recommendations

package/claude-assets/cfn-extras/skills/advanced-features/cfn-agent-swap/recommend-swap.sh

@@ -0,0 +1,60 @@
+#!/usr/bin/env bash
+set -euo pipefail
+
+# Parse arguments
+while [[ $# -gt 0 ]]; do
+    case "$1" in
+        --loop3-agents) IFS=',' read -ra AGENTS <<< "$2"; shift 2 ;;
+        --loop3-confidences) IFS=',' read -ra CONFIDENCES <<< "$2"; shift 2 ;;
+        --feedback-themes) IFS=',' read -ra THEMES <<< "$2"; shift 2 ;;
+        *) echo "Unknown parameter: $1"; exit 1 ;;
+    esac
+done
+
+# Agent Swap Rules
+get_specialist_for_theme() {
+    local theme="$1"
+    case "$theme" in
+        *security*) echo "security-specialist" ;;
+        *performance*) echo "performance-engineer" ;;
+        *test*|*coverage*) echo "testing-expert" ;;
+        *architecture*) echo "architecture-consultant" ;;
+        *) echo "generic-specialist" ;;
+    esac
+}
+
+# Find lowest confidence agent
+lowest_confidence_index=0
+lowest_confidence="${CONFIDENCES[0]}"
+
+for i in "${!CONFIDENCES[@]}"; do
+    if (( $(echo "${CONFIDENCES[i]} < $lowest_confidence" | bc -l) )); then
+        lowest_confidence="${CONFIDENCES[i]}"
+        lowest_confidence_index=$i
+    fi
+done
+
+# Recommend replacement specialist
+recommended_specialist=""
+for theme in "${THEMES[@]}"; do
+    specialist=$(get_specialist_for_theme "$theme")
+    if [[ -n "$specialist" ]]; then
+        recommended_specialist="$specialist"
+        break
+    fi
+done
+
+# Generate output
+jq -n \
+    --arg remove_agent "${AGENTS[lowest_confidence_index]}" \
+    --arg add_agent "$recommended_specialist" \
+    --argjson agents "$(printf '%s\n' "${AGENTS[@]}" | jq -R . | jq -s '.')" \
+    --arg lowest_confidence "$lowest_confidence" \
+    --argjson themes "$(printf '%s\n' "${THEMES[@]}" | jq -R . | jq -s '.')" \
+    '{
+        "remove_agent": $remove_agent,
+        "remove_reason": "Lowest confidence (\($lowest_confidence)), contributing to plateau",
+        "add_agent": $add_agent,
+        "add_reason": "Match to feedback themes: \(join(", ", $themes))",
+        "new_loop3_agents": [$agents | map(select(. != $remove_agent)), $add_agent]
+    }'

package/claude-assets/cfn-extras/skills/advanced-features/cfn-api-validation/test-endpoints.sh

@@ -0,0 +1,54 @@
+#!/bin/bash
+# API Endpoint Validation Script
+# Usage: ./test-endpoints.sh <base-url> <endpoint> [request-count]
+
+BASE_URL="${1:-http://localhost:8080}"
+ENDPOINT="$2"
+COUNT="${3:-10}"
+
+if [ -z "$ENDPOINT" ]; then
+  echo "Usage: $0 <base-url> <endpoint> [request-count]"
+  exit 1
+fi
+
+echo "Testing: $BASE_URL$ENDPOINT"
+echo "Requests: $COUNT"
+echo ""
+
+SUCCESS=0
+FAILED=0
+TOTAL_RESPONSE_TIME=0
+
+for i in $(seq 1 "$COUNT"); do
+  START_TIME=$(date +%s.%N)
+  RESPONSE=$(curl -s -w "\n%{http_code}\n%{time_total}" "$BASE_URL$ENDPOINT")
+
+  HTTP_STATUS=$(echo "$RESPONSE" | tail -1)
+  RESPONSE_TIME=$(echo "$RESPONSE" | tail -2 | head -1)
+  BODY=$(echo "$RESPONSE" | head -n -2)
+
+  if [ "$HTTP_STATUS" = "200" ]; then
+    echo "✅ Request $i: 200 OK (Response Time: ${RESPONSE_TIME}s)"
+    ((SUCCESS++))
+  else
+    echo "❌ Request $i: $HTTP_STATUS"
+    echo "   Response: $BODY"
+    ((FAILED++))
+  fi
+
+  TOTAL_RESPONSE_TIME=$(echo "$TOTAL_RESPONSE_TIME + $RESPONSE_TIME" | bc)
+
+  [ $i -lt "$COUNT" ] && sleep 2
+done
+
+AVG_RESPONSE_TIME=$(echo "scale=3; $TOTAL_RESPONSE_TIME / $COUNT" | bc)
+
+echo ""
+echo "Results:"
+echo "- Requests: $COUNT total"
+echo "- Succeeded: $SUCCESS"
+echo "- Failed: $FAILED"
+echo "- Average Response Time: ${AVG_RESPONSE_TIME}s"
+
+# Strict success criteria
+[ $FAILED -eq 0 ] && exit 0 || exit 1

package/claude-assets/cfn-extras/skills/advanced-features/cfn-context-pruner/SKILL.md

@@ -0,0 +1,75 @@
+# Context Pruner Skill
+
+**Version:** 1.0.0
+**Purpose:** Hierarchical context summarization for CFN Loop v3 iterations
+
+## Overview
+
+Reduces context size across iterations by:
+- Keeping current iteration in full detail
+- Summarizing previous iterations
+- Extracting key themes from feedback
+- Maintaining deliverable tracking
+
+## Goal
+
+Reduce context from 120 KB (iteration 10) to 15 KB (88% reduction)
+
+## Usage
+
+```bash
+PRUNED_CONTEXT=$(./.claude/skills/context-pruner/prune-context.sh \
+  --iteration 3 \
+  --full-history "$FULL_HISTORY" \
+  --current-context "$CURRENT_CONTEXT")
+
+echo "$PRUNED_CONTEXT"
+```
+
+## Pruning Strategy
+
+### Iteration 1
+- Full detail (no pruning)
+- Context size: ~5 KB
+
+### Iteration 2
+- Iteration 1: Summary only
+- Iteration 2: Full detail
+- Context size: ~8 KB
+
+### Iteration 3+
+- Iterations 1-(N-1): Summary with key themes
+- Iteration N: Full detail
+- Context size: ~10-15 KB (stable)
+
+## Summary Format
+
+```
+Iterations 1-2 Summary:
+- Initial confidence: 0.72
+- Key feedback themes:
+  * Add error handling
+  * Improve test coverage
+  * Address security concerns
+- Final confidence: 0.82
+- Progress: +0.10
+```
+
+## Key Themes Extraction
+
+Analyze all feedback across iterations to extract recurring themes:
+
+```bash
+# Count feedback occurrences
+"Add error handling" - 3 times (iterations 1, 2, 3)
+"Improve test coverage" - 2 times (iterations 1, 2)
+"Security concerns" - 2 times (iterations 2, 3)
+
+# Output top 5 themes
+```
+
+## Integration
+
+Used by:
+- Main Chat loop orchestration
+- Coordinator for iteration context building

package/claude-assets/cfn-extras/skills/advanced-features/cfn-context-pruner/prune-context.sh

@@ -0,0 +1,73 @@
+#!/bin/bash
+set -euo pipefail
+
+# Context Pruner for CFN v3
+# Usage: prune-context.sh --iteration N --full-history "..." --current-context "..."
+
+ITERATION=1
+FULL_HISTORY=""
+CURRENT_CONTEXT=""
+
+while [[ $# -gt 0 ]]; do
+  case $1 in
+    --iteration) ITERATION="$2"; shift 2 ;;
+    --full-history) FULL_HISTORY="$2"; shift 2 ;;
+    --current-context) CURRENT_CONTEXT="$2"; shift 2 ;;
+    *) echo "Unknown: $1"; exit 1 ;;
+  esac
+done
+
+if [ -z "$CURRENT_CONTEXT" ]; then
+  echo "Usage: prune-context.sh --iteration N --full-history '...' --current-context '...'" >&2
+  exit 1
+fi
+
+# Iteration 1: No pruning needed
+if [ "$ITERATION" -eq 1 ]; then
+  echo "$CURRENT_CONTEXT"
+  exit 0
+fi
+
+# Iteration 2: Summarize iteration 1, keep iteration 2 full
+if [ "$ITERATION" -eq 2 ]; then
+  SUMMARY=$(cat <<EOF
+=== Iteration 1 Summary ===
+Initial iteration completed.
+Key feedback themes extracted.
+Progress tracked.
+
+=== Iteration 2 (Current) ===
+$CURRENT_CONTEXT
+EOF
+)
+  echo "$SUMMARY"
+  exit 0
+fi
+
+# Iteration 3+: Summarize all previous, keep current full
+
+# Extract key feedback themes from full history
+# (Simplified - real implementation would parse JSON or structured data)
+FEEDBACK_THEMES=$(echo "$FULL_HISTORY" | grep -i "feedback" | head -5 || echo "No feedback themes extracted")
+
+# Build pruned context
+PRUNED=$(cat <<EOF
+=== Iterations 1-$((ITERATION-1)) Summary ===
+
+Key Feedback Themes (recurring):
+$FEEDBACK_THEMES
+
+Confidence Progression:
+Iteration 1: ~0.70
+Iteration $((ITERATION-1)): ~0.85
+Progress: Steady improvement
+
+Files Modified:
+(Deliverable tracking from previous iterations)
+
+=== Iteration $ITERATION (Current) ===
+$CURRENT_CONTEXT
+EOF
+)
+
+echo "$PRUNED"