[Appreciation] Thank you for this plugin!

[lprior-repo]

I just had to reach out and say thank you. This plugin is absolutely phenomenal and has become an indispensable part of my toolkit.

It might sound strange, but I'm moving significantly faster on both new features and refactoring tasks now. The way it works in tandem with my strict ESLint setup is brilliant!I It iterates through issues and consistently produces clean, working code. It's not an exaggeration to say you've completely changed how I think about TDD and AI in my coding process due to this plugin.

Your ongoing support and development are clearly paying off. I was absolutely thrilled to see you added support for Go, as it's my go-to for backend development!

Please keep up the incredible work. I am so excited to see this project continue to grow and can't wait to see which languages and frameworks you tackle next!

[nizos]

Wow, thank you so much for this incredible feedback! It genuinely made my day!

Go support should hopefully be ready tomorrow after I iron out a few remaining items. Would love your feedback or contributions once it's live, especially since it's your go-to for backend work!

Here's what on the roadmap:

• Faster validation process
• Customizable TDD instructions
• Support for .Net, Ruby, and Rust
• Better utilization of the agent's TODO system

Seriously, thank you again for taking the time to write this. Knowing that it's making a real difference in the way you work is the best motivation to keep pushing this forward!

[mattzollinhofer]

I just stumbled on your project last night and I'm really excited to try it with my team which follows strict TDD. So far agentic dev hasn't felt like a good fit, but I think this is exactly what I'm looking for.

We're a Ruby on Rails project and I'd be happy to be a tester for you!

Thanks for the effort!

[nizos]

Hi @mattzollinhofer,

That's fantastic!

Ruby/Rails support just jumped to the top of my priority list. I'm aiming to have it ready by next weekend. Would love to get your team's feedback once it's live.

Thanks for reaching out and offering your help!

[nizos]

Hi @lprior-repo,

I've just released the initial version of the Go reporter. I haven't had a chance to test it yet in a real project. I will give it a try tomorrow. Feel free to try it out and let me know if you run into any issues or have any suggestions for improvements.

Installation:

go install github.com/nizos/tdd-guard/reporters/go/cmd/tdd-guard-go@latest

Usage:

go test -json ./... | tdd-guard-go -project-root /absolute/path/to/project/root

Using Makefile:

test:
	go test -json ./... | tdd-guard-go -project-root /absolute/path/to/project/root

The project root flag ensures the reporter consistently writes to the correct .claude directory, regardless from which directory the tests are run from.

You can find the full installation and configuration documentation here: TDD Guard Go Reporter

Thank you again for the enthusiasm and support!

[nizos]

Hi @mattzollinhofer,

I'm looking into adding support for Ruby and wanted to get your input! I see that RSpec and Minitest are the most commonly used test frameworks. I'm leaning towards starting with RSpec because it seems to have more flexible reporter extensibility, similar to what we have with Vitest/Jest. That said, Minitest is Ruby's built-in testing framework, so it has that going for it.

Which framework would you find most useful? Or is there another one you would recommend? Would love to hear your thoughts on this :)

[VilemP]

I also wanted to say thank you. I've been fighting with claude code trying to convince it to do proper TDD while "vibe-coding" (almost). I had various successes with prompt design for several months now. But using the hooks was a briliant idea and it definitely works substantially better "out of the box". It took me usually a couple of nudges in each session to get the behavior right, now the nudges come from the hooks. Perfect. THANK YOU.

BTW, do you have any suggested CLAUDE.md that works great for you in combination with hooks? I still feel that CC keeps forgetting about refactoring phase for example and in general, I have to explain constantly the philosophy. A guidance here would help.

[nizos]

@VilemP Thank you for your thoughtful feedback! It's great to hear that TDD with Claude Code is working better for you now!

You might find these two blog posts helpful:

The first covers my general approach and discusses CLAUDE.md. I treat these as flexible guidelines rather than strict rules, sometimes going beyond the mentioned scope when it makes sense.
https://nizar.se/lean-claude-code-for-production/

The second blog post touches on the challenges I've encountered with improving the refactoring phase. Some users have had success using strict lint rules to prompt the agent into refactoring, though I agree this area needs significant improvement.
https://nizar.se/tdd-guard-for-claude-code/

[VilemP]

Thanks. I actually found the TDD Guard thanks to the second blog post. I read the first one now as well. Good stuff, very much overlaps with my experience. I am just trying to see whether I can get to something acceptable - quality wise - with auto accepted edits. :)
And as you rightly mention - without proper adherence to refactoring step (and the principles of refactoring) the bad stuff it produces starts snowballing. I will keep fighting with CLAUDE.md still a bit :) Thanks again for sharing this great project.