Have you seen Claude Code’s Sub-Agent feature and immediately wanted to design a bunch of them? Backend Agent, Frontend Agent, and so on—it feels like getting more powerful tools. But do you really need them?

During WebConf 2025, chatting with friends about this topic revealed that many people are still unfamiliar with when to use Sub-Agents. Two talks at the conference provided good entry points: ihower’s AI Agents Development and 91APP’s Chief Architect Andrew’s From Service to Agent.

Recently, the Hono framework launched the Hono CLI tool, and I quickly created a Hono Plugin for Claude Code, adding Agent Skill support for querying documentation using Hono CLI.

At the same time, I realized that the ri (Ruby Information) command, which I rarely use, provides similar capabilities to the Hono CLI. Therefore, I created the Ruby Plugin ahead of schedule to provide the ri skill.

I was originally planning to release a tool that applied techniques from my COSCUP talk in August. However, I discovered that there are many considerations in development, and practical usage has its barriers.

I decided to start from a simpler, more immediately accessible angle. Recently, I finally completed the basic functionality of ccharness, which can improve Claude Code’s output quality from a different perspective.

Recently, due to work-related reasons, I took a moment to revisit Open Policy Agent and discovered that the Cedar Language introduced by AWS is more suitable for implementing a policy mechanism similar to AWS IAM in software applications. Since it is built on Rust, I decided to try writing an extension in Rust so that it can be utilized in Ruby.

mruby compiles source code using a compiler (usually mrbc), resulting in a binary file in the mrb format. This file format is called RITE, and in order to execute compiled mruby code, it needs to be parsed and read.

Even Ruby on Rails is one of the fastest frameworks of web development, and you can use it to build a web rapidly. You still need the DevOps to deploy or update it manually that you can test or release it.

Can you have a better way to resolve it?

We have 4 ~ 5 times meetup in TGONext, and this time is the last meetup in the schedule. In the possible last meetup, we discuss some topic which we are not planning to discuss at first.

This time we are talking about log tracing and how to deal with technical debt.

The Form Object is a common pattern in Rails when our form becomes complex. But the tutorial in network’s example usually incapable of Rails’ form helper.

And I start thinking about is it possible to support form helpers without too many changes?

A few years ago, I have a post talking about Autoloading. In recent days, my colleague has some problems with Autoloading and Reloading.

Therefore I decided to review the Autoloading mechanism in Rails 5 and 6.

Before we starting to discuss architecture, our mentor let us ask some questions.

Between this meetup and previous meetup, my customer breaks their migration due to some incorrect plan. So I raise a migration question to discuss the zero-downtime migration plan.