diff --git a/README.md b/README.md
index 5f624b0a..d3905f59 100644
--- a/README.md
+++ b/README.md
@@ -307,7 +307,8 @@ To maximize economic efficiency, all AI agents follow a **Database-First** appro
 
 ### 6.3. Database Lifecycle and Hygiene
 To maintain a high-performance "Single Source of Truth", Nubenetes implements automated hygiene protocols:
-- **Semantic Drift Detection**: Using **SHA256 Content Fingerprinting**, the system monitors for silent updates in technical resources. If the content of a link changes significantly (e.g., a version update or blog rewrite), it is automatically flagged for AI re-evaluation to refresh its summary and impact score.
+- **Physical File Synchronization**: During the health check cycle, the engine performs **surgical line-by-line updates** on the V1 Markdown files. Dead links are physically removed, and permanent redirections (301/302) are updated to their **Canonical URLs**, ensuring the repository remains clean and low-latency.
+- **Semantic Drift Detection**: Using **SHA256 Content Fingerprinting**, the system monitors for silent updates. If resource content changes significantly, it is automatically flagged for AI re-evaluation to refresh its summary and impact score.
 - **GitHub Branch Auto-Heal**: If a deep link returns a 404, the engine automatically attempts to rescue it by migrating the path from `master` to `main`. Verified revivals are automatically updated in the V1 archive.
 - **Parked Domain Detection**: Using AI-driven content inspection, the engine identifies expired domains displaying "Buy this domain" parking pages, marking them as `DEAD` even if they return an HTTP 200 status.
 - **Auto-Redirect Fix (Canonical Updates)**: During health checks, if a permanent redirection (301/302) is detected, the engine automatically updates the Markdown files with the final **Canonical URL**. This reduces latency and prevents future link rot.
@@ -475,10 +476,9 @@ graph TD
 The heart of the new Nubenetes is a suite of AI Agents that operate on our `develop` branch:
 
 1.  **AgenticCurator (`src/agentic_curator.py`)**:
-    - **Discovery:** Scans multiple high-trust X.com accounts (defined in [`data/curation_sources.yaml`](data/curation_sources.yaml)) and other curation sources.
-    - **Evaluation:** Uses Gemini to score resources based on technical significance, impact, and **publication year**.
-    - **Classification:** Automatically maps new resources to the correct `.md` page using semantic matching and generates professional technical descriptions.
-    - **Primary Curation Sources (X.com):**
+    - **Discovery:** Scans multiple high-trust X.com accounts and RSS feeds.
+    - **Quality Hardening (Mandate 2 & 3):** Systematically filters known blacklisted domains and applies technical impact penalties to stale GitHub repositories (>4 years without activity) to protect V2 Elite standards.
+    - **Classification:** Automatically maps new resources using the **Recursive technical hierarchy** and generates multi-language descriptions (Native for V1, English for V2).
         *   **K8s & Cloud Native:** `@nubenetes`, `@kubernetesio`, `@cncf`, `@kelseyhightower`, `@memenetes`.
         *   **Hyperscalers:** `@awscloud`, `@Azure`, `@GoogleCloud`, `@0GiS0`, `@NTFAQGuy`, `@cantrillio`, `@pvergadia`, `@QuinnyPig`.
         *   **AI & Agents:** `@OpenAI`, `@AnthropicAI`, `@GoogleDeepMind`, `@GoogleAI`, `@LoganK`, `@NotebookLM`, `@LangChainAI`, `@llama_index`.
@@ -564,7 +564,7 @@ graph LR
 ```
 
 ### 9.5. Automated Mandate Auditing
-Every Pull Request generated by the Agentic engine includes a non-blocking **Safety and Mandate Audit** report. This report cross-references the changes against the foundations defined in [`GEMINI.md`](GEMINI.md):
+Every Pull Request generated by the system (covering both **Curation** and **Health Check** cycles) includes a non-blocking **Safety and Mandate Audit** report. This report cross-references the changes against the foundations defined in [`GEMINI.md`](GEMINI.md):
 - **Data Integrity**: Checks for accidental star degradation or V1 description loss.
 - **Architecture Compliance**: Verifies the recursive O'Reilly hierarchy and TOC presence in V2.
 - **MVQ Validation**: Audits the Elite portal for stale or low-impact repositories.