# Return the Custom Modes features **URL:** \ **Category:** Feature Requests\ **Created:** [November 25, 2025, 7:03pm UTC](https://forum.cursor.com/t/return-the-custom-modes-features/144170 "2025-11-25T19:03:10Z")\ **Posts on this page:** 1\ **Showing post:** 5
**Author:** ![Texarkanine](https://sea3.discourse-cdn.com/cursor1/user_avatar/forum.cursor.com/texarkanine/32/115280_2.png) [@Texarkanine](https://forum.cursor.com/u/Texarkanine)\ **Post date:** [November 26, 2025, 8:45pm UTC](https://forum.cursor.com/t/return-the-custom-modes-features/144170/5 "2025-11-26T20:45:54Z")
The core value of Custom Modes was controlling the LLM experience without relying on the LLM. For one example, manually disabling an MCP is **not** the same as telling an LLM to “please not use it” in a Command’s Markdown file. Additionally, a mode and all its customizations could be set _once_ and persist across repeated prompts and Agent conversations. A Command must be manually typed again every single time. This makes it much more likely for the human to forget to type it and waste time (and tokens) on an incorrect prompt. A key differentiator of Cursor versus other AI-assisted coding tools has long been the rich deterministic tuning available that takes place _before_ LLMs start processing tokens. Examples that come to mind include Rule activation criteria, the context pills… and Custom Modes. Please bring them back; I _cannot_ achieve with Commands what I was doing with Custom Modes. --- _[View the full topic](https://forum.cursor.com/t/return-the-custom-modes-features/144170)._