AutoSaddler is a system that improves LLM-agent harnesses by diagnosing execution traces and applying structured changes to prompts, tools, middleware, and agent-loop logic. It evaluates candidate updates for their ability to generalize beyond the traces that motivated them. The catalogue add-ons represent workflows for using AutoSaddler.
1 file for GitHub Copilot: AutoSaddler copilot-instructions.md — 764 tokens loaded in every session.
.github/copilot-instructions.md A 764 tok These files are microsoft/AutoSaddler's own configuration — they tell GitHub Copilot how to work on this repository, so they are not mods to install elsewhere. Copy one as a starting point and replace the parts that are about this project.