Vigil-CMCC — Content Moderation Command Center

Description

Vigil-CMCC (Content Moderation Command Center) provides a unified, powerful moderation system for WordPress that goes far beyond built-in comment moderation. Built for site administrators, editorial teams, and community managers, Vigil-CMCC centralizes every aspect of content review into a single, intuitive interface.

Key Features

• Unified Moderation Queue – Review, approve, reject, or mark items as spam from a single interface. No more jumping between screens.
• Spam Firewall – Configurable rules including link limits, keyword blacklists, duplicate detection, and more to automatically block unwanted content.
• AI-Powered Moderation – Integrated with OpenRouter API for automated content classification, spam detection, sentiment analysis, and language detection.
• Real-time Analytics – Queue statistics, spam ratios, content type breakdowns, and activity heatmaps to understand moderation patterns at a glance.
• Activity Log – Full audit trail of all moderation actions for accountability and compliance.
• Bulk Actions – Approve, reject, or export multiple items at once to accelerate your workflow.
• 10 Settings Tabs – General, Spam Firewall, Notifications, Appearance & Display, Integrations, Advanced Auto Moderation, Moderator Management, Data Retention, API & Webhooks, and Backup & Restore.
• Multi-Platform Support – Extensible architecture supporting WordPress, Shopify, Storyblok, Strapi, and Wix.
• Webhooks – Real-time notifications for new items, approvals, and spam detection to integrate with your existing tools.
• Collaboration – Internal notes, item assignment, activity feed, and history timeline for team-based moderation workflows.

AI Moderation

Leverage the OpenRouter API to automatically classify content, detect spam with high accuracy, analyze sentiment, and detect languages. AI rules work alongside your existing spam firewall to reduce manual review workload.

Multi-Platform Ready

While built for WordPress, Vigil-CMCC’s architecture is extensible across multiple platforms including Shopify, Storyblok, Strapi, and Wix — making it an ideal choice for organizations managing content across a diverse tech stack.

Webhook Integrations

Send real-time notifications to Slack, Discord, or any custom endpoint when new items arrive in the queue, when content is approved or rejected, and when spam is detected.

External Services

This plugin connects to third-party AI services to provide automated content moderation and spam detection. The following external services are used:

OpenRouter AI

• Service: OpenRouter provides access to various AI models for content classification.
• Data sent: Content text, system prompt, and model parameters are sent to OpenRouter’s API endpoint (https://openrouter.ai/api/v1/chat/completions) when AI moderation is triggered (e.g., when new content enters the moderation queue and AI rules are enabled).
• Purpose: To classify content as spam, toxic, phishing, hate speech, or safe; to detect language; and to analyze sentiment.
• Terms of Service: https://openrouter.ai/terms
• Privacy Policy: https://openrouter.ai/privacy

OpenAI

• Service: OpenAI provides GPT-based AI models for content classification.
• Data sent: Content text, system prompt, and model parameters are sent to OpenAI’s API (https://api.openai.com/v1) when the user configures an OpenAI API key directly via the plugin’s integration settings.
• Purpose: To classify content for spam detection when OpenAI is selected as the AI provider.
• Terms of Service: https://openai.com/policies/terms-of-use/
• Privacy Policy: https://openai.com/policies/privacy-policy/

Anthropic (Claude)

• Service: Anthropic provides Claude AI models for content classification.
• Data sent: Content text, system prompt, and model parameters are sent to Anthropic’s API (https://api.anthropic.com/v1) when the user configures an Anthropic API key directly via the plugin’s integration settings.
• Purpose: To classify content for spam detection when Anthropic is selected as the AI provider.
• Terms of Service: https://www.anthropic.com/legal/terms
• Privacy Policy: https://www.anthropic.com/legal/privacy

Google Gemini

• Service: Google Gemini provides AI models for content classification.
• Data sent: Content text and model parameters are sent to Google’s API (https://generativelanguage.googleapis.com/v1beta) when the user configures a Google API key directly via the plugin’s integration settings.
• Purpose: To classify content for spam detection when Google Gemini is selected as the AI provider.
• Terms of Service: https://ai.google.dev/terms
• Privacy Policy: https://policies.google.com/privacy

Important: AI moderation is optional. All core features — spam firewall, queue management, analytics, activity log, and collaboration — work without any external service. Users must explicitly configure an API key in the plugin’s Integrations settings to enable AI-powered features. Content is only sent to external services when AI moderation rules are active and new content is being processed.