rickye26

I really like how it leverages the existing session persistence feature in each harness. I write my own session manager https://github.com/hyperlogue/captain-miao and it uses its own launcher with hook to monitor session status. Not as elegant as faplex but can support more harnesses.

To ensure max utilization of my attention, I do the following steps when working on new features:

  - Straight brain dump for ideas. I don't spend time organizing thoughts. Sometimes I don't even write prompts with right English syntax. But AI will understand most of them.
  - Ask AI to grill me on the missing details in the design. Usually it's the most painful step.
  - AI writes design doc. I skim through it. Give some feedback.
  - Let AI implement the feature. Recent AI models can usually complete the full feature without my intervention, as long as the design doc is solid.
  - If I feel there are unclear part in the implementation, I ask AI to write explainer doc.

The things many people probably don't do is:

  - The reverse grilling. Our description on the thing we want is often incomplete. If we don't make AI to ask enough clarification questions, there will be misalignment.
  - Now I ask AI to write all docs in html. It takes more tokens and time to finish, but much easier to read and understand, because of the richer layout and sometimes the interactivity of html/js. 

I used claude artifacts to give feedback about the html design doc directly to the agent, and later on, developed my own tool (https://github.com/hyperlogue/r3) to do the same thing but for all kinds of agents.

My workflow is very similar. But I just ask agents to write design in html instead of markdown, due to its richer layout and better interactivity. When the design is about UI or anything related to graphics, this approach is extremely efficient.

I also found that having the design reviewed by multiple agents has very little marginal value. The review agent will always find something to improve, but mostly it’s just nit and not anything super important.

I used to let Claude just upload the html design doc to Claude artifacts for me to review. Recently I switched to codex and started to use my own tool https://github.com/hyperlogue/r3 to complete this workflow.

Hi HN, author here. r3 is a tool originally built for reviewing code changes and design doc. I recently revamped it to better support html artifacts, similar to claude artifacts, but running locally and for all agents. This reflects a shift in my daily workflow: I now prefer html design doc over markdown for its richer layout and interactivity. I'd love to hear your thoughts on it!

This looks really cool, especially on the remote control part. I've experienced exactly the same problem, but ended up building my own tool through an opposite architectural approach than Saggar.

The main difference is that I want to keep my existing workflow in Kitty and tmux/zellij. Since all of them provide solid remote control protocol, I wrote captain-miao (https://github.com/hyperlogue/captain-miao) which is a standalone TUI app that runs inside these terminals, observing the agent sessions, managing tabs and windows, and allow me to quickly jump to the exact window/tab that needs my attention. The sessions are still native windows/panes inside the terminal/multiplexer that I configured and polished for years.

One difficulty I found when trying to expanding the agent support beyond claude code and codex, many agents don't provide a good way to inject hooks to listen to the session status change. wondering how Saggar solves this problem. do it infer state from the screen buffer?

I built r3 to scratch my own itch when reviewing long design doc and planning doc from AI. The chat interface is inherently bad at tracking multiple pieces of feedback across different parts of a document, so I created a lightweight local web UI to streamline the review process.

I have been using it on my own projects for two weeks, and it has made design review much easier. I thought others working with AI coding agents might find it useful too.

Previously https://news.ycombinator.com/item?id=48855670. Resubmit as lots of significant improvements have been made and I consider it's near the stable state.

I'd love to hear what you think and any feedback you have!

Your product looks great! Having AI to highlight important part of a code review is a great feature. I will add it to r3 too