diff --git a/Agents.md b/Agents.md
index 070ea38..58159b1 100644
--- a/Agents.md
+++ b/Agents.md
@@ -2,6 +2,7 @@
 
 ## Purpose
 This file defines how to use agent-style workflows in this project so tasks are clear, scoped, and repeatable.
+It is internal guidance for the assistant, not reader-facing documentation.
 
 ## Audience And Tone Rules
 Assume the reader is new to AI and needs detailed, step-by-step guidance.
@@ -10,6 +11,7 @@ Assume the reader is new to AI and needs detailed, step-by-step guidance.
 - Explain terms in plain language.
 - Provide an example whenever possible.
 - Format chat or code examples consistently: use "Example prompt:" with a fenced ```text``` block for chat prompts, and "Example code:" with the right language for code.
+- For required instructions, label them as "Required instruction" and use a fenced ```text``` block.
 - Prefer checklists, short steps, and concrete outcomes.
 - Assume the reader is an expert engineer but a beginner at AI.
 
@@ -48,21 +50,9 @@ If you had to restart a chat and re-explain the goal, add a short reminder so th
 - "Treat this repo like a book for developers. Put reader-facing guidance in docs/ai, not in Agents.md."
 - "If placement is unclear, ask where the content should live before editing."
 
-### Example Request
-Example prompt:
-```text
-Read Agents.md and PRD.md first. Propose a plan. Then add chat mode guidance to docs/ai/usage-tokens.md (reader-facing) with hard examples. Do not add reader content to Agents.md.
-```
-
 ## Commit And Push After Repo Updates
 If you update any file in this repo, commit and push right away so other developers do not lose their local changes. If you are unsure, ask and confirm before pushing.
 
-### Example Request
-Example prompt:
-```text
-Read Agents.md and PRD.md first. Propose a plan, then update docs/ai/ios.md with step-by-step guidance and examples. If you add new files, update docs/ai/index.md.
-```
-
 ## Skills Sync
 This repo uses a skills manifest to standardize skills across developers.
 
@@ -75,12 +65,3 @@ This repo uses a skills manifest to standardize skills across developers.
 - Inputs: (files, context, constraints)
 - Output: (expected deliverable)
 - Verification: (tests or checks)
-
-## Example
-Example request:
-```text
-Goal: Add a troubleshooting section to the AI docs.
-Inputs: docs/ai/troubleshooting.md, docs/planning/AI-Docs-Plan.md
-Output: Updated troubleshooting section with 5 common issues.
-Verification: Manual review.
-```