How to achieve greater code refactoring automation?
Great thread here.
Personally for refactoring I heavily rely on IDE (PHP storm) calling agents from the console inside the IDE
Also I have released this PHP storm skill which might help your agent to work with IDE:
github.com
GitHub - TechSpokes/skill-ide-phpstorm-mcp: IDE PHPStorm MCP server best practices. Helps AI...
IDE PHPStorm MCP server best practices. Helps AI agents to leverage your IDE tools for better efficiency.
Also what helps a lot is having the architecture overview document created by the agent after the analysis of your code base with weak spots flagged during the analysis.
And some alignment on the documentation is also good to help agent produce better code.
Here are some examples I put in the repository as adopted conventions:
github.com
GitHub - TechSpokes/agency-specifications-files-agents-md: AGENTS.md file guidelines
AGENTS.md file guidelines
github.com
GitHub - TechSpokes/agency-specifications-files-readme-md: Readme.md Specification
Readme.md Specification
gist.github.com
https://gist.github.com/sergeliatko/2e3f2a165797db81337c598e9f5f2c53
code-commenting-specification-v2.md
# Code Commenting Specification
Version 2.0.0
A specification for code commenting in multi-entity codebases where humans, AI agents, and automated tools collaborate.
## 1. Abstract
This specification defines principles, a tag vocabulary, requirement levels, and guidelines for code comments in software projects. It treats code comments as a form of cross-intelligence context transfer: persistent, asynchronous messages embedded in source code that carry information not available from the code itself.
This file has been truncated. show original
Hope that helps.
Discussion in the ATmosphere