Agent context
Linear models
4 SQL models that turn the raw Linear 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
- 1Raw tables
- 1Staging
- 4Core
- 4Analytics
Staging cleans each raw table once, core holds the logic, and analytics is the table dashboards and agents read.
- Cycle progressScope and completion per cycle: the numbers behind Linear's cycle graph.grain: team x cycle · 1 raw table
- Issue cycle timeLead time, cycle time and triage time for every completed issue. Recreates the cycle time and lead time charts in Linear Insights.grain: completed issue · 1 raw table
- Issue flowIssues created, started, completed and canceled per day, team and assignee. The created-vs-completed chart from Linear Insights, as a table.grain: day (UTC) x team x assignee · 1 raw table
- Open backlogEverything still open, by team, workflow state, priority and assignee, with age and overdue counts. A snapshot as of the last sync.grain: team x state x priority x assignee · 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 Linear's own reports first. Each model's notes say what the synced data can and can't support.
Connect Linear.
Your agents start with context.
Sync Linear to your warehouse, deploy these models, and query them from Claude, Cursor or ChatGPT over MCP. Free for 14 days, no credit card.