diff --git a/.changeset/update-permission-mode-copy.md b/.changeset/update-permission-mode-copy.md
new file mode 100644
index 000000000..6112978f5
--- /dev/null
+++ b/.changeset/update-permission-mode-copy.md
@@ -0,0 +1,5 @@
+---
+"@moonshot-ai/kimi-code": patch
+---
+
+Clarify the permission mode descriptions shown by `/permission`, `/auto`, and `/yolo`, and reorder `/auto` and `/yolo` in the command list.
diff --git a/apps/kimi-code/src/tui/commands/config.ts b/apps/kimi-code/src/tui/commands/config.ts
index da3fe8c5d..9d9597419 100644
--- a/apps/kimi-code/src/tui/commands/config.ts
+++ b/apps/kimi-code/src/tui/commands/config.ts
@@ -107,7 +107,7 @@ export async function handleYoloCommand(host: SlashCommandHost, args: string): P
     }
     await session.setPermission('yolo');
     host.setAppState({ permissionMode: 'yolo' });
-    host.showNotice('YOLO mode: ON', 'Workspace tools auto-approved.');
+    host.showNotice('YOLO mode: ON', 'AI auto-approves safe actions, asks for approval on risky ones.');
     return;
   }
 
@@ -130,7 +130,7 @@ export async function handleYoloCommand(host: SlashCommandHost, args: string): P
   } else {
     await session.setPermission('yolo');
     host.setAppState({ permissionMode: 'yolo' });
-    host.showNotice('YOLO mode: ON', 'Workspace tools auto-approved.');
+    host.showNotice('YOLO mode: ON', 'AI auto-approves safe actions, asks for approval on risky ones.');
   }
 }
 
@@ -151,7 +151,7 @@ export async function handleAutoCommand(host: SlashCommandHost, args: string): P
     }
     await session.setPermission('auto');
     host.setAppState({ permissionMode: 'auto' });
-    host.showNotice('Auto mode: ON', 'Tools auto-approved. Agent will not ask questions.');
+    host.showNotice('Auto mode: ON', 'Run all actions automatically, including risky ones.');
     return;
   }
 
@@ -174,7 +174,7 @@ export async function handleAutoCommand(host: SlashCommandHost, args: string): P
   } else {
     await session.setPermission('auto');
     host.setAppState({ permissionMode: 'auto' });
-    host.showNotice('Auto mode: ON', 'Tools auto-approved. Agent will not ask questions.');
+    host.showNotice('Auto mode: ON', 'Run all actions automatically, including risky ones.');
   }
 }
 
diff --git a/apps/kimi-code/src/tui/commands/registry.ts b/apps/kimi-code/src/tui/commands/registry.ts
index 7654442b5..8e5a16386 100644
--- a/apps/kimi-code/src/tui/commands/registry.ts
+++ b/apps/kimi-code/src/tui/commands/registry.ts
@@ -136,15 +136,15 @@ export const BUILTIN_SLASH_COMMANDS = [
   {
     name: 'yolo',
     aliases: ['yes'],
-    description: 'Toggle auto-approve mode',
-    priority: 100,
+    description: 'Toggle YOLO mode: AI auto-approves safe actions, asks for approval on risky ones.',
+    priority: 101,
     availability: 'always',
   },
   {
     name: 'auto',
     aliases: [],
-    description: 'Toggle auto permission mode',
-    priority: 100,
+    description: 'Toggle Auto mode: run all actions automatically, including risky ones.',
+    priority: 99,
     availability: 'always',
   },
   {
diff --git a/apps/kimi-code/src/tui/components/dialogs/permission-selector.ts b/apps/kimi-code/src/tui/components/dialogs/permission-selector.ts
index 91668b4f0..4b2db673d 100644
--- a/apps/kimi-code/src/tui/components/dialogs/permission-selector.ts
+++ b/apps/kimi-code/src/tui/components/dialogs/permission-selector.ts
@@ -6,20 +6,17 @@ const PERMISSION_OPTIONS: readonly ChoiceOption[] = [
   {
     value: 'manual',
     label: 'Manual',
-    description:
-      'Ask before commands, edits, and other risky actions. Read/search tools run directly; session approval rules are respected.',
+    description: 'Approve every action yourself.',
   },
   {
     value: 'auto',
     label: 'Auto',
-    description:
-      'Run fully non-interactively. Tool actions are approved automatically, and agent questions are skipped so it can decide on its own.',
+    description: 'Run all actions automatically, including risky ones.',
   },
   {
     value: 'yolo',
     label: 'YOLO',
-    description:
-      'Automatically approve tool actions and plan transitions. The agent can still ask you explicit questions when your input is needed.',
+    description: 'AI decides which actions need your approval.',
   },
 ];