Agent context
Wordpress models
2 SQL models that turn the raw Wordpress tables into the reports people ask about. Deploy them in Weld and your agent queries the definitions behind every number.
How the set is built
- 2Raw tables
- 2Staging
- 2Core
- 2Analytics
Staging cleans each raw table once, core holds the logic, and analytics is the table dashboards and agents read.
- Content inventoryEvery published post and page with its length, age, last update, comments and featured image: the Posts and Pages lists in wp-admin, as a content audit.grain: one row per published post or page (current state as of the last sync) · 2 raw tables
- Publishing cadenceHow much is published and edited each month, per author and content type: the editorial output report WordPress itself does not have.grain: one row per month (site time zone) x post type x author · 1 raw table
- Weld or dbt
- The same SQL in both dialects. Sync the folder with GitHub Sync, or copy the dbt models into your project.
- Check before you rely on it
- Reconcile a month against Wordpress's own reports first. Each model's notes say what the synced data can and can't support.
Connect Wordpress.
Your agents start with context.
Sync Wordpress to your warehouse, deploy these models, and query them from Claude, Cursor or ChatGPT over MCP. Free for 14 days, no credit card.