Show HN: Stage CLI – an easier way of reading your AI generated changes locally

ccpan22 about 4 hours ago 13 commentsRead Article on github.com

ZH version is available. Content is displayed in original English for accuracy.

Hey HN! We're Charles and Dean. A few weeks ago we posted about Stage, a code review tool that guides you through reading a PR step by step - https://news.ycombinator.com/item?id=47796818.

We got a lot of great feedback but also heard from many people that they wanted to have the chapters experience even before opening a PR… so we built the Stage CLI as the local, open-source version that anyone can try.

Here’s a quick demo video: https://www.tella.tv/video/stage-cli-demo-f55q

It works with any coding agent of your choice. The skill instructs the agent to read your current branch’s changes, break them down into separate logical chapters, and open them in a local browser.

We’ve found that reading changes this way is a lot easier for us than reading them in an IDE or other similar CLI tools, which present diffs to you in repository tree order. You can see a few examples of what it feels like here: https://stagereview.app/explore.

Try it out and let us know what you think! Would love to hear any feedback :)

⚡ Community Insights

Discussion Sentiment

83% Positive

Analyzed from 415 words in the discussion.

Discussion (13 Comments)Read Original on HackerNews

adamtaylor_13•16 minutes ago

Minor nitpick: This isn't what I expected when I read "CLI". I envisioned a terminal-native experience. Unless I skimmed over this way too fast, this is a browser experience that you trigger from the terminal.

EDIT: I should mention that I think the idea is cool. We're in a new age where reviewing large amounts of unfamiliar code has become a larger problem than it was previously.

cpan22•8 minutes ago

yep sorry about that, we weren't exactly sure what the best framing was

glad you like the idea though! let us know what you think

sanufar•about 1 hour ago

Looks cool! Chapters is definitely something I've been angling towards as well. Any plans on going in the other direction (directly incorporating rich feedback/review into the agent loop through Stage)?

dean_stratakos•38 minutes ago

appreciate it! and yep, we've got lots of ideas on the roadmap to bring a more complete iteration experience closer to the coding agent.

we've found it pretty silly that we have to push to GitHub in order to get comments from a review bot, pull them down locally, then rinse and repeat. the whole agentic coding landscape could benefit from some centralization

sanufar•8 minutes ago

yeah, i definitely feel like we're currently in a very time-sparse model for review, when a lot of changes can be condensed locally. it'd reduce a lot of friction and also save a lot of compute costs if we were able to left-shift a lot of our current review work

mkw5053•about 2 hours ago

Looks cool and will give it a try.

I've been spending a lot of my energy lately on how to run eng teams where we:

1. Maximize long-term shipping velocity

2. Maximize quality (whatever that means)

3. Maintain minimal complexity

4. Are intentional about which skills we let atrophy, which we keep sharp, and which new ones we have to build

5. Make juniors more capable, not just more productive

These are always in tension.

I've been thinking about instituting some sort of socratic method during planning and review plus spaced interval testing to ensure both the humans and AI coding agents understand and find some max of the factors above.

cpan22•about 2 hours ago

Great let us know what you think!

And yeah, I think number 5 on your list is particularly interesting - juniors will develop much slower if they don't go through the struggle of understanding implementation

We're hoping that our tool can help make that easier

Meliwat93•36 minutes ago

Love the idea. This would have been a game-changer in previous projects I've worked on.

burnJS•27 minutes ago

This feature exists already. It's called git.

pi-victor•about 1 hour ago

love this. i had the same issue with ai generated code and wrote parley. https://parley.cloudflavor.io it's a TUI that can help you review code by enabling you to comment on the diff itself. but i like this approach of organizing code into chapters. i think what my tool is missing this exact thing.

dean_stratakos•41 minutes ago

parley looks awesome! we're planning to add support for comments soon, which is definitely a key feature to being able to iterate back and forth with a coding agent

tim-projects•about 1 hour ago

> We’ve found that reading changes this way is a lot easier for us than reading them in an IDE or other similar CLI tools

If this tool was in the terminal I'd use it.

cpan22•about 1 hour ago

we're planning on adding it!