Better access management when agent in different mode

During stress-testing of the latest build, I found that the AI could be “convinced” to perform file writes even while in Plan Mode. To ensure strict adherence to mode boundaries, I propose implementing directory-level read/write permissions tied directly to the active mode:

  • Plan Mode: Write Access: Restricted exclusively to .cursor/*.plan.md.

    • Read Access: Global (or project-wide), but with all other file paths mounted as read-only.
  • Act Mode: Full Read/Write access as currently implemented.

Stripping write permissions at the system/plugin level (rather than relying on model instructions) would prevent accidental or “persuaded” edits during the planning phase.

Hey @Arya_Bhatt

This should be the case now that Plan mode will only edit Markdown files (.md). While not as finely scoped as .plan.md, it’s a good step.

What files got edited when you were using Plan Mode? What version of Cursor are you using?