ci: add GitHub Pages workflow and update README project details

- Introduce .github/workflows/pages.yml to automate static site deployment to GitHub Pages on master branch pushes.
- Revamp README.md with centered header, status badges, and expanded tech stack details including ROCm GPU setup, LACT tuning, and Debian environment.
- Clarify the AI-driven development workflow, emphasizing manual code review and open-source tooling focus.
- Fix missing trailing newline in AGENTS.md and add commit formatting instructions.

Author: tsb99x

.github/workflows/pages.yml

@@ -0,0 +1,37 @@
+name: Deploy to GitHub Pages
+
+on:
+  push:
+    branches: ["master"]
+  workflow_dispatch:
+
+permissions:
+  contents: read
+  pages: write
+  id-token: write
+
+concurrency:
+  group: "pages"
+  cancel-in-progress: false
+
+jobs:
+  deploy:
+    environment:
+      name: github-pages
+      url: ${{ steps.deployment.outputs.page_url }}
+    runs-on: ubuntu-latest
+    steps:
+      - name: Checkout
+        uses: actions/checkout@v4
+
+      - name: Setup Pages
+        uses: actions/configure-pages@v4
+
+      - name: Upload artifact
+        uses: actions/upload-pages-artifact@v3
+        with:
+          path: "."
+
+      - name: Deploy to GitHub Pages
+        id: deployment
+        uses: actions/deploy-pages@v4

AGENTS.md

@@ -12,4 +12,8 @@ Each subfolder is an independent project with its own `AGENTS.md` that describes
 
 ## Agent Instructions
 
-Before making any changes, **always look into the relevant subproject's `AGENTS.md`** for detailed context, file structure, coding conventions, and constraints. The root `AGENTS.md` only serves as a navigation guide.
+Before making any changes, **always look into the relevant subproject's `AGENTS.md`** for detailed context, file structure, coding conventions, and constraints. The root `AGENTS.md` only serves as a navigation guide.
+
+## Commit Details
+
+- Commit details should be a list denoted with `-`.

README.md

@@ -1,11 +1,21 @@
-# Vibecoding
+<div align="center">
+
+# 🤖 Vibecoding
+
+![Vibecoding](https://img.shields.io/badge/✨_Vibecoding-AI_Powered-blue?style=for-the-badge&logo=ai)
+![Model](https://img.shields.io/badge/🧠_Model-Qwen3.6--27b-orange?style=for-the-badge)
+![GPU](https://img.shields.io/badge/🎮_GPU-RX_7900_XTX-red?style=for-the-badge&logo=amd)
+![License](https://img.shields.io/badge/📄_License-Unlicense-green?style=for-the-badge)
+
+</div>
 
 This is a repository for my vibecoding experiments. This project explores the actual capabilities of vibecoding, pushes the boundaries of this approach, and investigates how AI technology can be integrated into my development workflow.
 
 ## Tech Stack
 
-- **Backend**: [Ollama](https://ollama.ai/) running in [Podman](https://podman.io/)
-- **Model**: [Qwen3.6-27b](https://ollama.com/library/qwen3.6:27b)
+- **Backend**: [Ollama](https://ollama.ai/) with ROCm on Sapphire Pulse RX 7900 XTX (24G VRAM), running in [Podman](https://podman.io/) on Debian Trixie
+- **GPU Tuning**: [LACT](https://github.com/UbuntuForSA/LACT) is used to limit GPU clocks to 1929 MHz and fan speed to 40% for reduced noise
+- **Model**: [Qwen3.6-27b](https://ollama.com/library/qwen3.6:27b) running with 64k context window
 - **Plugin**: [Cline](https://github.com/cline/cline) for [VSCodium](https://github.com/VSCodium/vscodium)
 
 ## Web Page
@@ -30,11 +40,14 @@ This is a repository for my vibecoding experiments. This project explores the ac
 
 This repository follows a hands-off file editing approach:
 
+- **Ideas & Prompts**: All project ideas and prompts are my own, originating from old unfinished or dropped projects, or even projects I deemed not viable to research into at all.
 - **File Editing**: All files are edited exclusively by the AI model via the Cline plugin. This includes this README.md. I do not manually edit any files.
+- **Review**: I perform a thorough review of everything that is generated before it is committed.
 - **Git Management**: I manually manage the Git repository (pushes, branches, signing, etc.), but commit messages are generated by the AI model.
+- **Deployment**: Automated via [GitHub Actions](.github/workflows/pages.yml) on every push to `master` (deployment configuration also created by AI).
 - **Local Environment**: Everything runs locally and self-hosted. No cloud services or external APIs are used.
 - **Open-Source Focus**: This project exclusively uses open-source solutions for both models and tooling.
 
 ## License
 
-This project is released under the [Unlicense](UNLICENSE).
+This project is released under the [Unlicense](UNLICENSE).