diff --git a/CLAUDE.md b/CLAUDE.md
index 4cc0797..91fcfc5 100644
--- a/CLAUDE.md
+++ b/CLAUDE.md
@@ -22,7 +22,8 @@ AgentRegistry (agent_registry.py)
   ├── default agent ← AgentConfig (config.py)
   ├── writer agent
   ├── researcher agent
-  └── ops agent
+  ├── ops agent
+  └── linkbuilder agent
     ↓
 Agent (agent.py) ← Memory (memory.py, 4-layer, per-agent scoping)
     ↓                ← Skills (skills.py, markdown skills with frontmatter)
@@ -48,7 +49,7 @@ NotificationBus (notifications.py) → Gradio / future Discord / Slack
 # Run the app
 uv run python -m cheddahbot
 
-# Run tests (124 tests)
+# Run tests (187 tests)
 uv run pytest
 
 # Run tests verbose
@@ -86,6 +87,7 @@ uv add --group test <package>
 | `cheddahbot/memory.py` | 4-layer memory with semantic search + scoping |
 | `cheddahbot/router.py` | System prompt builder |
 | `cheddahbot/skills.py` | Markdown skill registry (discovers skills/*.md) |
+| `cheddahbot/tools/linkbuilding.py` | Link building content pipeline (guest articles, directory listings, social posts) |
 | `cheddahbot/ui.py` | Gradio web interface |
 | `cheddahbot/tools/` | Tool modules (auto-discovered) |
 | `cheddahbot/tools/delegate.py` | delegate_task + delegate_to_agent tools |
@@ -176,6 +178,14 @@ skill_map:
     field_mapping:
       topic: "task_name"        # uses ClickUp task name
       company_name: "Client"    # looks up "Client" custom field
+  "Link Building":
+    tool: "build_links"
+    auto_execute: true
+    field_mapping:
+      keyword: "task_name"      # "LINKS - keyword" → keyword extracted
+      company_name: "Client"
+      target_url: "IMSURL"
+      branded_url: "SocialURL"
 ```
 
 Task lifecycle: `to do` → discovered → approved/awaiting_approval → executing → completed/failed (+ attachments uploaded)
@@ -192,6 +202,7 @@ Tests live in `tests/` and use pytest. All tests run offline with mocked APIs.
 - `test_docx_export.py` — Plain text → .docx formatting and file creation
 - `test_press_advantage.py` — Press Advantage API client, company parsing, link building, submit tool
 - `test_scheduler_helpers.py` — `_extract_docx_paths` regex extraction from tool output
+- `test_linkbuilding.py` — Link building pipeline: keyword extraction, company lookup, content generation, file output, ClickUp sync
 
 Fixtures in `conftest.py`: `tmp_db` (fresh SQLite), `sample_clickup_task_data` (realistic API response).