Tools.AIBridge 1.0.8

AI Bridge — Usage Guide

A no-agent, no-extension workflow for applying AI-generated code changes to any project directly from your browser using the ai-bridge .NET Global Tool.

Works with any language or technology — .NET, Node.js, Python, React, or any project with a sensible folder structure.

🌟 The Big Picture

AI Bridge is a fast, language-agnostic CLI tool that bridges the gap between your local codebase and web-based LLMs (like Claude, Gemini, Qwen, and ChatGPT).

It offers two modes depending on your project size:

1. Simple Mode (Quick Start): Perfect for small projects. You pack your entire codebase, give it to the AI, and get code back.
2. Advanced Mode (Index Flow): Designed for large codebases. You map your project once, and then only upload the specific files the AI requests, saving millions of tokens and preventing AI confusion.

⚙️ Prerequisites & Installation

• .NET 10 SDK installed on your machine.
• Git installed and on your PATH. AI Bridge uses git ls-files to automatically respect your .gitignore rules.
• A browser AI account (Claude, Gemini, Qwen, or ChatGPT).

💡 Model Recommendation: We highly recommend using thinking or reasoning "High" models (e.g., Claude 4.6 Sonnet, Gemini 3.1 Pro, Qwen 3.7 Max/Plus). Writing high-quality code and safely navigating complex logic requires exceptional reasoning capabilities. Weaker models may struggle to provide bug-free implementations.

Install the tool globally using the .NET CLI:

dotnet tool install --global Tools.AIBridge

(To update later: dotnet tool update --global Tools.AIBridge)

🚀 Getting Started

Open your terminal, navigate to your project directory, and run the init command.

cd /path/to/your-project
ai-bridge init

What it does: It creates a clean, tracked ai-bridge/ folder in your project containing two paths you can take, plus a safe artifacts/ sandbox for the AI's inputs and outputs.

YourProjectRoot/
├── .aiignore                           <-- Custom exclusion rules (Tracked)
└── ai-bridge/                          <-- The AI Bridge workspace
    ├── 1-SimpleMode/                   <-- Templates for quick, small tasks
    ├── 2-AdvancedMode/                 <-- Templates for large project mapping
    └── artifacts/                      <-- Scratchpad for context and AI responses

🟢 Simple Mode (For Small Projects)

Use this mode if your codebase is small enough to fit comfortably inside a single AI prompt window.

1. Pack Your Project

Run the pack command to bundle your codebase into text files.

ai-bridge pack

This generates *-context.txt files inside ai-bridge/artifacts/. (It automatically respects .gitignore, skips binary files, and applies .aiignore).

2. Chat with the AI

1. Open your AI (Claude, Gemini, Qwen, or ChatGPT).
2. Upload the System Prompt: ai-bridge/1-SimpleMode/ai-system-prompt.md
3. Upload the Protocol Skill: ai-bridge/1-SimpleMode/ai-response-skill.md
4. Upload your Context Files: The *-context.txt files from the artifacts/ folder. (Skip this step if starting a brand new project!)
5. Ask the AI to write your feature or fix a bug.

3. Apply the Changes

Copy the XML response generated by the AI to your clipboard and run:

ai-bridge apply --paste

Alternatively: Save the XML to ai-bridge/artifacts/ai-response.xml and run ai-bridge apply.

🔴 Advanced Mode (For Large Projects)

If you have a large codebase, uploading your entire project every time wastes tokens and degrades AI reasoning. Advanced Mode solves this by creating a lightweight index.xml map of your project.

Phase 1: Create the Index (One-Time Setup)

(Skip Phase 1 entirely if you are starting a brand new project from scratch) Before chatting, the AI needs to map out your existing project.

1. Run ai-bridge pack to gather your full context.
2. Start a new AI chat and upload:
   • ai-bridge/2-AdvancedMode/Phase1-CreateIndex/ai-create-index-system-prompt.md
   • All the *-context.txt files from artifacts/.
3. The AI will output an XML map of your project. Save this output exactly as ai-bridge/index.xml.

Phase 2: The Daily Workflow

Now that you have an index, you never need to upload huge context files again!

1. Start a fresh AI Chat.
2. Upload the System Prompt and your Index:
   • ai-bridge/2-AdvancedMode/Phase2-DailyChat/ai-index-system-prompt.md
   • ai-bridge/index.xml (Skip uploading this if starting a brand new project)
3. Upload the 3 Required Skills (so the AI knows how to communicate):
   • ai-bridge/2-AdvancedMode/Phase2-DailyChat/ai-request-skill.md
   • ai-bridge/2-AdvancedMode/Phase2-DailyChat/ai-response-skill.md
   • ai-bridge/2-AdvancedMode/Phase2-DailyChat/ai-update-index-skill.md
4. Ask for a feature.
5. Fulfill the Request:
   • The AI will output an XML request for files (e.g., <ai-request><file>src/app.js</file></ai-request>).
   • Copy the request and run ai-bridge apply --paste.
   • The tool will automatically gather those files and bundle them into ai-bridge/artifacts/ai-requested-context.txt.
   • Upload that text file back to the AI chat.
6. The AI generates the final code changes. Copy them and run ai-bridge apply --paste.

🛠️ Ecosystem Detection

When you run ai-bridge pack, it groups files intelligently based on your ecosystem to keep contexts organized:

📋 Clipboard Support

ai-bridge apply --paste uses native OS commands — no external dependencies required.

🔄 Updating Templates

Because the AI prompts are closely tied to the CLI's parsing engine, you may need to update them when you upgrade the ai-bridge tool. If the tool detects a version mismatch, simply run:

ai-bridge update

This will refresh your 1-SimpleMode and 2-AdvancedMode folders with the latest prompts.