claude-flow-novice 2.14.29 → 2.14.30

package/claude-assets/cfn-agents-ignore/cfn-seo-team/technical-seo-specialist.md.backup

@@ -0,0 +1,208 @@
+---
+name: technical-seo-specialist
+description: SEO-ONLY AGENT - MUST BE USED for technical SEO tasks exclusively. NO general coding or development work. Focuses on search engine optimization: audits, crawl errors, Core Web Vitals, schema markup, sitemaps, robots.txt. Use PROACTIVELY for site performance optimization (SEO-related), structured data validation, crawl budget optimization. Keywords - technical SEO audit, crawl errors, Core Web Vitals, schema markup, XML sitemap, robots.txt, page speed SEO, site architecture SEO
+tools: [Read, Write, Edit, Bash, Grep, Glob, TodoWrite]
+model: haiku
+type: specialist
+acl_level: 1
+capabilities: [technical-seo, performance-optimization, schema-markup, crawl-management, site-architecture]
+---
+
+# Technical SEO Specialist
+
+You are a **technical SEO expert** focused exclusively on search engine optimization. Your role is to improve website visibility and ranking through technical optimization, NOT general web development or coding. You specialize in site infrastructure for SEO, performance optimization for search rankings, and crawlability for search engines.
+
+## Core Responsibilities
+
+1. **Site Audits**
+   - Crawl site using Screaming Frog data
+   - Identify broken links, redirect chains, 404 errors
+   - Analyze page load times and Core Web Vitals
+   - Check mobile usability and responsive design
+
+2. **Performance Optimization**
+   - Optimize images (compression, lazy loading, WebP conversion)
+   - Implement caching strategies
+   - Minimize JavaScript/CSS bloat
+   - Improve Largest Contentful Paint (LCP), First Input Delay (FID), Cumulative Layout Shift (CLS)
+
+3. **Schema Markup Implementation**
+   - Generate JSON-LD structured data
+   - Validate schema using Google Rich Results Test
+   - Implement VideoObject, HowTo, Dataset, FAQ schemas
+   - Ensure schema aligns with Schema.org specifications
+
+4. **Crawl Management**
+   - Configure robots.txt for optimal crawl budget
+   - Generate and validate XML sitemaps
+   - Implement canonical tags to prevent duplicate content
+   - Fix crawl errors reported in Google Search Console
+
+5. **Site Architecture**
+   - Optimize URL structure (clean, descriptive URLs)
+   - Implement breadcrumb navigation
+   - Ensure logical internal linking hierarchy
+   - Validate hreflang tags for international SEO
+
+## Trigger Keywords
+- technical audit
+- crawl errors
+- Core Web Vitals
+- schema markup
+- sitemap generation
+- robots.txt
+- page speed optimization
+- 404 errors
+- redirect chains
+- canonical tags
+- site architecture
+
+## Specialization Areas
+
+### Screaming Frog Analysis
+- Parse Screaming Frog CSV exports
+- Identify critical technical issues (5xx errors, orphaned pages, thin content)
+- Generate prioritized fix lists based on impact
+
+### PageSpeed Insights Integration
+- Query PageSpeed Insights API for performance metrics
+- Analyze field data (CrUX) vs lab data (Lighthouse)
+- Generate actionable recommendations with confidence scores
+
+### Google Search Console Integration
+- Parse GSC API responses for crawl errors
+- Monitor index coverage issues
+- Track Core Web Vitals trends
+
+### n8n Workflow Automation
+- Trigger automated audits via n8n webhooks
+- Schedule weekly performance checks
+- Alert on critical issues (sudden traffic drops, crawl errors)
+
+## Integration Points
+
+**APIs:**
+- PageSpeed Insights API (Core Web Vitals, performance scores)
+- Google Search Console API (crawl errors, index coverage)
+- Schema.org validation API
+
+**Services:**
+- n8n workflows (automated audit triggers)
+- PostgreSQL (store audit history)
+- Performance metrics caching
+
+**External Tools:**
+- Screaming Frog (crawl data exports)
+- Google Rich Results Test (schema validation)
+- WebPageTest (advanced performance analysis)
+
+## Workflow
+
+1. **Audit Initiation** (TodoWrite)
+   - Define audit scope (full site vs specific sections)
+   - Identify critical pages (high traffic, conversion paths)
+
+2. **Data Collection** (Bash, Grep)
+   - Parse Screaming Frog exports
+   - Query PageSpeed Insights API
+   - Fetch GSC crawl error reports
+
+3. **Issue Analysis** (Read, Grep, Glob)
+   - Categorize issues by severity (critical, high, medium, low)
+   - Identify patterns (e.g., all blog posts missing schema)
+
+4. **Implementation** (Write, Edit)
+   - Fix robots.txt blocking issues
+   - Generate XML sitemaps
+   - Implement schema markup
+   - Optimize images and scripts
+
+5. **Validation** (Bash)
+   - Re-run PageSpeed Insights
+   - Validate schema using Google Rich Results Test
+   - Verify sitemap accessibility
+
+## Success Criteria
+
+- Core Web Vitals pass thresholds (LCP <2.5s, FID <100ms, CLS <0.1)
+- Zero critical crawl errors (5xx, orphaned pages)
+- All priority pages have valid schema markup
+- Page speed score improvement ≥20 points
+- Sitemap coverage ≥95% of indexable pages
+- Confidence score ≥0.85
+
+## Output Format
+
+**Technical Audit Report:**
+```markdown
+# Technical SEO Audit - [Site/Section Name]
+
+## Executive Summary
+- Overall Health Score: [0-100]
+- Critical Issues: [count]
+- High Priority Issues: [count]
+- Confidence Score: [0.0-1.0]
+
+## Core Web Vitals
+| Metric | Current | Target | Status |
+|--------|---------|--------|--------|
+| LCP    | 2.8s    | <2.5s  | ⚠️ Needs Work |
+| FID    | 45ms    | <100ms | ✅ Pass |
+| CLS    | 0.15    | <0.1   | ⚠️ Needs Work |
+
+## Critical Issues (Fix Immediately)
+1. [Issue description]
+   - Impact: [traffic/rankings/user experience]
+   - Location: [URL or file path]
+   - Fix: [specific action]
+   - Priority: CRITICAL
+
+## High Priority Issues
+1. [Issue description]
+   - Impact: [impact assessment]
+   - Fix: [specific action]
+   - Priority: HIGH
+
+## Schema Markup Status
+- Pages with schema: [count / total]
+- Schema types implemented: [VideoObject, HowTo, etc.]
+- Validation errors: [count]
+
+## Recommendations
+1. [Recommendation with implementation steps]
+2. [Recommendation with implementation steps]
+
+## Next Steps
+- [Action item 1]
+- [Action item 2]
+```
+
+## Example Prompts
+
+1. "Conduct technical SEO audit for OurStories homepage and identify top 5 critical issues"
+2. "Optimize Core Web Vitals for /stories/* pages - target LCP <2.5s"
+3. "Generate XML sitemap for all published stories and memory pages"
+4. "Implement VideoObject schema markup for story video pages"
+5. "Fix robots.txt to allow crawling of /api/stories endpoint"
+6. "Analyze Screaming Frog export and prioritize technical fixes"
+
+## Constraints
+
+- **SEO-ONLY ROLE** - NO general web development, backend coding, or feature implementation
+- Focus ONLY on technical infrastructure for SEO and search engine crawlability
+- Delegate content optimization to content-seo-strategist
+- Delegate programmatic page generation to programmatic-seo-engineer
+- Delegate schema design (complex multi-type) to schema-markup-engineer
+- Delegate general coding tasks to backend-developer or frontend-engineer
+- Maximum audit scope: 10,000 pages per run (use sampling for larger sites)
+- Always provide confidence score with technical SEO recommendations
+
+## CFN Loop Completion Protocol
+
+When participating in CFN Loop workflows, complete your work and report confidence score. Coordination will be handled automatically by the orchestrator.
+
+**Confidence Scoring Criteria:**
+- 0.90+: All Core Web Vitals pass, zero critical errors, schema validated
+- 0.75-0.89: Minor performance issues remain, schema implementation incomplete
+- 0.60-0.74: Significant technical debt identified, complex fixes required
+- <0.60: Critical infrastructure issues blocking indexing or user experience

package/claude-assets/commands/CFN_LOOP_TASK_MODE.md

@@ -6,17 +6,6 @@
 
 ## Overview
 
-Task Mode: Main Chat coordinates directly and spawns agents via Task() tool with full context injection and visibility. NO coordinator agent is used.
-
-| Aspect | Task Mode | CLI Mode |
-|--------|-----------|----------|
-| **Spawning** | Main Chat directly via Task() | Coordinator via npx CLI |
-| **Visibility** | Full transparency in Main Chat | Background, Redis logs |
-| **Provider** | All Anthropic | CLI uses Z.ai routing |
-| **Cost** | ~$0.150/iteration | ~$0.054/iteration (64% savings) |
-| **Use Case** | Debugging, prototyping, learning | Production, cost optimization |
-| **ACE Reflection** | Optional via `--ace-reflect` flag | Always enabled |
-
 ### ACE Reflection Flag
 
 ```bash
@@ -39,7 +28,7 @@ Task Mode: Main Chat coordinates directly and spawns agents via Task() tool with
 
 **Critical Fix**: Prevents Task Mode agents from executing CLI coordination scripts that cause memory leaks.
 
-### Three-Layer Defense System
+### Defense System
 
 #### Layer 1: Agent Documentation
 **Task Mode agents use mode-specific completion protocols:**
@@ -56,26 +45,7 @@ Task Mode: Main Chat coordinates directly and spawns agents via Task() tool with
 - ✅ CLI coordination allowed
 ```
 
-#### Layer 2: Agent-Level Detection
-**Automatic detection functions prevent CLI usage:**
-```bash
-detect_task_mode_and_exit() {
-  if [[ -z "${TASK_ID:-}" || -z "${AGENT_ID:-}" ]]; then
-    echo "❌ TASK MODE DETECTED - CLI commands forbidden"
-    exit 1
-  fi
-}
-```
-
-#### Layer 3: Code-Level Runtime Blocking
-**Coordination scripts include early exit checks:**
-```bash
-# ⚠️ ANTI-023 MEMORY LEAK PROTECTION
-if [[ -z "${TASK_ID:-}" || -z "${AGENT_ID:-}" ]]; then
-    echo "❌ TASK MODE DETECTED - Redis coordination forbidden"
-    exit 1
-fi
-```
+`
 
 ### Memory Impact Resolution
 - **Before Fix**: Up to 23GB memory consumption per hanging agent

package/claude-assets/commands/cfn-mode.md

@@ -15,6 +15,6 @@ Check `.cfn-mode.json` or run `/cfn-mode status`
 
 **Mode Details:**
 - **CLI Mode**: Coordinator → orchestrator → CLI agents (Z.ai routing)
-- **Task Mode**: Coordinator → JSON → Main Chat spawns Task() agents (Anthropic)
+- **Task Mode**: main chat is Coordinator → JSON → Main Chat spawns Task() agents (Anthropic)
 
-Both modes use Redis context storage for swarm recovery.
+Only CLI mode use Redis context storage for swarm recovery.

package/dist/agents/agent-loader.js

@@ -1,145 +1,12 @@
-"use strict";
 /**
  * Dynamic Agent Loader - Reads agent definitions from .claude/agents/ directory
  * Single source of truth for agent types in the system
- */ var __awaiter = this && this.__awaiter || function(thisArg, _arguments, P, generator) {
-    function adopt(value) {
-        return value instanceof P ? value : new P(function(resolve) {
-            resolve(value);
-        });
-    }
-    return new (P || (P = Promise))(function(resolve, reject) {
-        function fulfilled(value) {
-            try {
-                step(generator.next(value));
-            } catch (e) {
-                reject(e);
-            }
-        }
-        function rejected(value) {
-            try {
-                step(generator["throw"](value));
-            } catch (e) {
-                reject(e);
-            }
-        }
-        function step(result) {
-            result.done ? resolve(result.value) : adopt(result.value).then(fulfilled, rejected);
-        }
-        step((generator = generator.apply(thisArg, _arguments || [])).next());
-    });
-};
-var __generator = this && this.__generator || function(thisArg, body) {
-    var _ = {
-        label: 0,
-        sent: function() {
-            if (t[0] & 1) throw t[1];
-            return t[1];
-        },
-        trys: [],
-        ops: []
-    }, f, y, t, g = Object.create((typeof Iterator === "function" ? Iterator : Object).prototype);
-    return g.next = verb(0), g["throw"] = verb(1), g["return"] = verb(2), typeof Symbol === "function" && (g[Symbol.iterator] = function() {
-        return this;
-    }), g;
-    function verb(n) {
-        return function(v) {
-            return step([
-                n,
-                v
-            ]);
-        };
-    }
-    function step(op) {
-        if (f) throw new TypeError("Generator is already executing.");
-        while(g && (g = 0, op[0] && (_ = 0)), _)try {
-            if (f = 1, y && (t = op[0] & 2 ? y["return"] : op[0] ? y["throw"] || ((t = y["return"]) && t.call(y), 0) : y.next) && !(t = t.call(y, op[1])).done) return t;
-            if (y = 0, t) op = [
-                op[0] & 2,
-                t.value
-            ];
-            switch(op[0]){
-                case 0:
-                case 1:
-                    t = op;
-                    break;
-                case 4:
-                    _.label++;
-                    return {
-                        value: op[1],
-                        done: false
-                    };
-                case 5:
-                    _.label++;
-                    y = op[1];
-                    op = [
-                        0
-                    ];
-                    continue;
-                case 7:
-                    op = _.ops.pop();
-                    _.trys.pop();
-                    continue;
-                default:
-                    if (!(t = _.trys, t = t.length > 0 && t[t.length - 1]) && (op[0] === 6 || op[0] === 2)) {
-                        _ = 0;
-                        continue;
-                    }
-                    if (op[0] === 3 && (!t || op[1] > t[0] && op[1] < t[3])) {
-                        _.label = op[1];
-                        break;
-                    }
-                    if (op[0] === 6 && _.label < t[1]) {
-                        _.label = t[1];
-                        t = op;
-                        break;
-                    }
-                    if (t && _.label < t[2]) {
-                        _.label = t[2];
-                        _.ops.push(op);
-                        break;
-                    }
-                    if (t[2]) _.ops.pop();
-                    _.trys.pop();
-                    continue;
-            }
-            op = body.call(thisArg, _);
-        } catch (e) {
-            op = [
-                6,
-                e
-            ];
-            y = 0;
-        } finally{
-            f = t = 0;
-        }
-        if (op[0] & 5) throw op[1];
-        return {
-            value: op[0] ? op[1] : void 0,
-            done: true
-        };
-    }
-};
-var __spreadArray = this && this.__spreadArray || function(to, from, pack) {
-    if (pack || arguments.length === 2) for(var i = 0, l = from.length, ar; i < l; i++){
-        if (ar || !(i in from)) {
-            if (!ar) ar = Array.prototype.slice.call(from, 0, i);
-            ar[i] = from[i];
-        }
-    }
-    return to.concat(ar || Array.prototype.slice.call(from));
-};
-Object.defineProperty(exports, "__esModule", {
-    value: true
-});
-exports.refreshAgents = exports.getAgentsByCategory = exports.isValidAgentType = exports.searchAgents = exports.getAgentCategories = exports.getAllAgents = exports.getAgent = exports.getAvailableAgentTypes = exports.agentLoader = exports.AgentLoader = void 0;
-exports.resolveLegacyAgentType = resolveLegacyAgentType;
-var node_fs_1 = require("node:fs");
-var glob_1 = require("glob");
-var node_path_1 = require("node:path");
-var yaml_1 = require("yaml");
+ */ import { readFileSync, existsSync } from 'node:fs';
+import { glob } from 'glob';
+import { resolve, dirname } from 'node:path';
+import { parse as parseYaml } from 'yaml';
 // Legacy agent type mapping for backward compatibility
-var LEGACY_AGENT_MAPPING = {
+const LEGACY_AGENT_MAPPING = {
     analyst: 'code-analyzer',
     coordinator: 'hierarchical-coordinator',
     optimizer: 'perf-analyzer',
@@ -150,40 +17,38 @@ var LEGACY_AGENT_MAPPING = {
 };
 /**
  * Resolve legacy agent types to current equivalents
- */ function resolveLegacyAgentType(legacyType) {
+ */ export function resolveLegacyAgentType(legacyType) {
     return LEGACY_AGENT_MAPPING[legacyType] || legacyType;
 }
-var AgentLoader = /** @class */ function() {
-    function AgentLoader() {
-        this.agentCache = new Map();
-        this.categoriesCache = [];
-        this.lastLoadTime = 0;
-        this.CACHE_EXPIRY = 60000; // 1 minute cache
-    }
-    AgentLoader.prototype.getAgentsDirectory = function() {
-        var currentDir = process.cwd();
+export class AgentLoader {
+    agentCache = new Map();
+    categoriesCache = [];
+    lastLoadTime = 0;
+    CACHE_EXPIRY = 60_000;
+    getAgentsDirectory() {
+        let currentDir = process.cwd();
         while(currentDir !== '/'){
-            var claudeAgentsPath = (0, node_path_1.resolve)(currentDir, '.claude', 'agents');
-            if ((0, node_fs_1.existsSync)(claudeAgentsPath)) {
+            const claudeAgentsPath = resolve(currentDir, '.claude', 'agents');
+            if (existsSync(claudeAgentsPath)) {
                 return claudeAgentsPath;
             }
-            currentDir = (0, node_path_1.dirname)(currentDir);
+            currentDir = dirname(currentDir);
         }
-        return (0, node_path_1.resolve)(process.cwd(), '.claude', 'agents');
-    };
-    AgentLoader.prototype.parseAgentFile = function(filePath) {
+        return resolve(process.cwd(), '.claude', 'agents');
+    }
+    parseAgentFile(filePath) {
         try {
-            var content = (0, node_fs_1.readFileSync)(filePath, 'utf-8');
-            var frontmatterMatch = content.match(/^---\r?\n([\s\S]*?)\r?\n---\r?\n([\s\S]*)$/);
+            const content = readFileSync(filePath, 'utf-8');
+            const frontmatterMatch = content.match(/^---\r?\n([\s\S]*?)\r?\n---\r?\n([\s\S]*)$/);
             if (!frontmatterMatch) {
-                console.warn("No frontmatter found in ".concat(filePath));
+                console.warn(`No frontmatter found in ${filePath}`);
                 return null;
             }
-            var yamlContent = frontmatterMatch[1], markdownContent = frontmatterMatch[2];
-            var frontmatter = (0, yaml_1.parse)(yamlContent);
-            var description = frontmatter.description;
+            const [, yamlContent, markdownContent] = frontmatterMatch;
+            const frontmatter = parseYaml(yamlContent);
+            const description = frontmatter.description;
             if (!frontmatter.name || !description) {
-                console.warn("Missing required fields (name, description) in ".concat(filePath));
+                console.warn(`Missing required fields (name, description) in ${filePath}`);
                 return null;
             }
             return {
@@ -204,13 +69,129 @@ var AgentLoader = /** @class */ function() {
                 content: markdownContent.trim()
             };
         } catch (error) {
-            console.error("Error parsing agent file ".concat(filePath, ":"), error);
+            console.error(`Error parsing agent file ${filePath}:`, error);
             return null;
         }
-    };
-    AgentLoader.prototype.parseTools = function(frontmatter) {
-        var extractTools = function(input) {
+    }
+    parseTools(frontmatter) {
+        const extractTools = (input)=>{
             if (Array.isArray(input)) return input.map(String);
+            if (typeof input === 'string') {
+                return input.split(/[,\s]+/).map((t)=>t.trim()).filter((t)=>t.length > 0);
+            }
+            return [];
+        };
+        // Safely handle tools and capabilities.tools
+        const toolsFromFrontmatter = frontmatter.tools ? extractTools(frontmatter.tools) : [];
+        const toolsFromCapabilities = frontmatter.capabilities && typeof frontmatter.capabilities === 'object' ? extractTools(Object(frontmatter.capabilities).tools) : [];
+        return [
+            ...toolsFromFrontmatter,
+            ...toolsFromCapabilities
+        ];
+    }
+    async loadAgents() {
+        const agentsDir = this.getAgentsDirectory();
+        if (!existsSync(agentsDir)) {
+            console.warn(`Agents directory not found: ${agentsDir}`);
+            return;
+        }
+        const agentFiles = await new Promise((resolve, reject)=>{
+            glob('**/*.md', {
+                cwd: agentsDir,
+                ignore: [
+                    '**/README.md',
+                    '**/MIGRATION_SUMMARY.md'
+                ],
+                absolute: true
+            }, (err, matches)=>{
+                if (err) reject(err);
+                else resolve(matches);
+            });
+        });
+        this.agentCache.clear();
+        this.categoriesCache = [];
+        const categoryMap = new Map();
+        for (const filePath of agentFiles){
+            const agent = this.parseAgentFile(filePath);
+            if (agent) {
+                this.agentCache.set(agent.name, agent);
+                const relativePath = filePath.replace(agentsDir, '');
+                const pathParts = relativePath.split('/');
+                const category = pathParts[1] || 'uncategorized';
+                if (!categoryMap.has(category)) {
+                    categoryMap.set(category, []);
+                }
+                categoryMap.get(category).push(agent);
+            }
+        }
+        this.categoriesCache = Array.from(categoryMap.entries()).map(([name, agents])=>({
+                name,
+                agents: agents.sort((a, b)=>a.name.localeCompare(b.name))
+            }));
+        this.lastLoadTime = Date.now();
+    }
+    // Rest of the methods remain similar to the original implementation
+    needsRefresh() {
+        return Date.now() - this.lastLoadTime > this.CACHE_EXPIRY;
+    }
+    async ensureLoaded() {
+        if (this.agentCache.size === 0 || this.needsRefresh()) {
+            await this.loadAgents();
+        }
+    }
+    async getAvailableAgentTypes() {
+        await this.ensureLoaded();
+        const currentTypes = Array.from(this.agentCache.keys());
+        const legacyTypes = Object.keys(LEGACY_AGENT_MAPPING);
+        return Array.from(new Set([
+            ...currentTypes,
+            ...legacyTypes
+        ])).sort();
+    }
+    async getAgent(name) {
+        await this.ensureLoaded();
+        return this.agentCache.get(name) || this.agentCache.get(resolveLegacyAgentType(name)) || null;
+    }
+    async getAllAgents() {
+        await this.ensureLoaded();
+        return Array.from(this.agentCache.values()).sort((a, b)=>a.name.localeCompare(b.name));
+    }
+    async getAgentCategories() {
+        await this.ensureLoaded();
+        return this.categoriesCache;
+    }
+    async searchAgents(query) {
+        await this.ensureLoaded();
+        const lowerQuery = query.toLowerCase();
+        return Array.from(this.agentCache.values()).filter((agent)=>agent.name.toLowerCase().includes(lowerQuery) || agent.description.toLowerCase().includes(lowerQuery) || agent.capabilities?.some((cap)=>cap.toLowerCase().includes(lowerQuery)));
+    }
+    async isValidAgentType(name) {
+        await this.ensureLoaded();
+        return this.agentCache.has(name) || this.agentCache.has(resolveLegacyAgentType(name));
+    }
+    async getAgentsByCategory(category) {
+        const categories = await this.getAgentCategories();
+        const found = categories.find((cat)=>cat.name === category);
+        return found?.agents || [];
+    }
+    async refresh() {
+        this.lastLoadTime = 0;
+        await this.loadAgents();
+    }
+}
+// Singleton instance
+export const agentLoader = new AgentLoader();
+// Convenience exports for use in other modules
+export const getAvailableAgentTypes = ()=>agentLoader.getAvailableAgentTypes();
+export const getAgent = (name)=>agentLoader.getAgent(name);
+export const getAllAgents = ()=>agentLoader.getAllAgents();
+export const getAgentCategories = ()=>agentLoader.getAgentCategories();
+export const searchAgents = (query)=>agentLoader.searchAgents(query);
+export const isValidAgentType = (name)=>agentLoader.isValidAgentType(name);
+export const getAgentsByCategory = (category)=>agentLoader.getAgentsByCategory(category);
+export const refreshAgents = ()=>agentLoader.refresh();
+
+//# sourceMappingURL=agent-loader.js.map.isArray(input)) return input.map(String);
             if (typeof input === 'string') {
                 return input.split(/[,\s]+/).map(function(t) {
                     return t.trim();