Docs › Permission levels & safety

Permission levels & safety

You decide how far Claude may go. Anything that changes the live site waits for your Approve.

The three levels

LevelClaude canNeeds your approval
Read-only (default)Read pages, posts, plugins, mind maps and site health—
Content editorCreate and edit drafts, upload images, update mind mapsEditing live pages, publishing, menus, homepage and site title
Site maintainerEverything above, plus theme settings, widgets and plugin installsPlugin installs and updates (blocked while the lab lock is on)

For a whole website, one build plan replaces the separate approvals for everything it lists.

Seven safety rules built in

  1. Its own user. Claude acts as claude-agent (Editor), never as an administrator.
  2. One door. Every action passes a single gateway that checks the level, the locks and the per-tool switches.
  3. Approval queue. Live changes are prepared, shown with a diff, and only run when an administrator clicks Approve.
  4. Undo. A revision is saved before every edit; mind maps keep their last five versions.
  5. Activity log. Every call is written down with its result and an undo link.
  6. Locks. The plugin obeys AI Engine’s emergency write lock and Online Lab lock unless an administrator turns that off.
  7. Kill switch. One click disconnects Claude and revokes every sign-in.