trigger-tree is a powerful tool designed to enhance the documentation discovery process for AI coding assistants like Claude and OpenAI Codex by providing insights into which documentation files are being accessed. With an emphasis on keeping operations local and token-free, trigger-tree eliminates cloud dependencies and analytics vendors, ensuring user privacy and data control.

Project Overview

The tool visualizes documentation usage through features such as:

• Heat and Cold Maps: Gain insights into which documents are frequently accessed (heat) versus those that are ignored (cold).
• Live Pulse Dashboard: Monitor real-time documentation interactions to evaluate how AI assistants are engaging with project files.
• Evidence-Backed Router Fixes: Receive suggestions for enhancing documentation visibility and accessibility based on concrete usage data.

Why Measure Documentation?

In the realm of AI-assisted software development, documentation serves as a crucial guiding resource. By understanding which documents the AI interacts with, development teams can ensure their guidance is effective and recognized. trigger-tree addresses the quiet failure that occurs when important documentation goes unread, transforming documentation from a static collection into dynamic, monitored infrastructure with measurable health grades.

Core Features

• Discovery Reporting: Analyze which documents are utilized and identify those that remain untouched, along with the reasons for their inactivity.
• User-Friendly Commands: Highly intuitive commands enable users to quickly assess documentation status and gather insights without hassle:

  /tt status         # View current documentation access status
  /tt insights       # Generate a comprehensive report of documentation usage
  

• Robust Configuration: Tailor the tool's configuration to optimize documentation interaction based on unique project needs.

How It Works

trigger-tree operates by installing lightweight logging hooks into the coding environment, silently tracking interactions and recording which documentation files are read. This data is stored locally, ensuring privacy while allowing users to:

• Identify gaps in documentation accessibility.
• Review how modifications to routers affect AI document access.

Platform Support

Compatible with macOS, Linux, and Windows, trigger-tree provides extensive coverage for diverse development environments, emphasizing seamless integration without compromising functionality.

Conclusion

By leveraging the unique insights provided by trigger-tree, teams can fine-tune their documentation, ensuring that their AI coding assistants have access to the right information at the right time, ultimately improving efficiency and collaboration in software development.

For more information, please visit the official website. Privacy and security measures are thorough, as outlined in the project's privacy policy.

Note: This project is continuously evolving, and feedback is encouraged to enhance its capabilities. Engage with the community or contribute directly on the GitHub repository.