Summary

Cursor added a context usage breakdown view that shows how an agent's context budget is being consumed across rules, skills, MCPs, and subagents. The feature is positioned as a diagnostic tool for teams trying to understand context pressure in larger agent setups.

What changed

Cursor added a context usage breakdown view for agent sessions.

Why it matters

Context windows and context packing are now practical bottlenecks in AI coding workflows. Exposing where context is going makes agent behavior easier to tune and easier to trust during longer runs.

Evidence excerpt

Cursor's changelog says users can now see a breakdown of their agent's context usage and use the stats to diagnose issues across rules, skills, MCPs, and subagents.

Sources