diff --git a/docs/ai/usage-tokens.md b/docs/ai/usage-tokens.md
index eb5c1da..152efad 100644
--- a/docs/ai/usage-tokens.md
+++ b/docs/ai/usage-tokens.md
@@ -62,6 +62,17 @@ Think of each model as a different "speed and cost" setting. Some models are che
 - Use expensive models only when the task is truly complex or high-stakes.
 - If you are unsure, start with Auto or a 0.33x or 1x option, then move up only if needed.
 
+## Chat Modes And Cost (Plain Language)
+Copilot chat has four modes. The lighter the mode, the less work you ask it to do.
+
+Ask: Questions, summaries, or explanations. Example: "Summarize this file in 5 bullets and list 2 risks."
+
+Edit: Small, targeted changes with clear constraints. Example: "Update this function to return nil on empty input. Keep behavior the same otherwise."
+
+Plan: Get steps before edits. Example: "Give me a 5-step plan to refactor this module. Wait for approval before edits."
+
+Agent: Multi-step work across files or tools. Example: "Refactor these two files, update tests, run the test task, and summarize results."
+
 #### Example: Choosing A Model
 - Task: "Summarize this file in 5 bullets." Use a 0.33x or 1x model.
 - Task: "Refactor three files and update tests." Start with a 1x model. Move to 3x only if the 1x model fails.