HN user
I'm building https://github.com/tomasz-tomczyk/crit - GitHub PR-style review tool for all of your LLM agent's output
I like the look of it - my main problem with remote control feature in CC is the inability to start a new terminal session on my computer - can I do that from Pulse?
Yeah I have a soft spot for Cursor because it was my first tool that unlocked huge productivity with AI, but I avoid doing anything there now.
Should try their CLI!
Same experience here - I built a similar tool, for reviewing both plans and code - https://crit.md (shameless plug), browser based as opposed to TUI.
Having said that, I don't review the code until going through a few iterations of reviews from Claude. Each round it does find some "obvious" issue, so as long as I'm not close to maxing my subscription for the week I let it run an audit -> validator checks the claims -> fix issues before I get to it.
It's been three months now of building Crit - https://crit.md - local first, open source tool for reviewing markdown and code output from your favourite AI agent.
It's inspired by GitHub PR review workflow, only with quick iterations and local.
It's been great! I found some dedicated users, dogfooding it every day with Claude and starting to get more contributions from the little community. We just got accepted into Homebrew core which was my target.
I'm expanding the team features now as I've got a few users keen to get the sharing service deployed in their private networks!
That is very close to what I was looking to whip up with CC myself, so thanks!
What is your read on the ToS? From what I understood, Anthropic want anything automation-wise be on their cloud so they can charge you extra...
I was hoping to have some sort of schedule to check specific things and only alert me if there is something I care about - I was looking at desktop notifications but have you found a workflow you like? I don't see myself looking at results of reminders... I guess my prompt could invoke whatever skill (e.g. emailing)
Does it work well with recurring reminders?
Any way to make it work with CLI tools?
When building new features, I use a skill that generates 5+ variants based on various companies' design language and patterns, in plain html/css/js - quick throwaway prototypes, gives me an idea of different ways the thing could look or behave. It's very very useful and I usually end up combining a couple of the best aspects. For side projects with no designer, it's been great.
I don't have any issue with markdown though - but terminal isn't a place to review it and leave useful feedback. Use one of the many tools that are popping up or build your own (like I did) to leave comments and iterate.
On a personal note, as this is my first proper OSS project, I'm very humbled by the response and the feedback from the users! And it made me realise I need to be reaching out to maintainers of OSS work I rely on more and thank them!
Thanks! What extension were you using?
https://crit.md - a CLI tool for reviewing AI coding agent output like a GitHub PR.
I got frustrated with Claude Code and Cursor producing plausible-but-wrong changes with no easy way to annotate and push back, without making a full PR. crit makes the review stage fun again!
Works on both plans as well as code itself. It’s been very rewarding hearing from folks who use it, everyone has been very kind! My most successful side project already :)
https://crit.md - a CLI tool for reviewing AI coding agent output like a GitHub PR.
I got frustrated with Claude Code and Cursor producing plausible-but-wrong changes with no easy way to annotate and push back, without making a full PR. crit makes the review stage fun again!
Works on both plans as well as code itself. It’s been very rewarding hearing from folks who use it, everyone has been very kind! My most successful side project already :)
https://crit.md - a CLI tool for reviewing AI coding agent output like a GitHub PR.
I got frustrated with Claude Code and Cursor producing plausible-but-wrong changes with no easy way to annotate and push back, without making a full PR. crit makes the review stage fun again!
Works on both plans as well as code itself. It’s been very rewarding hearing from folks who use it, everyone has been very kind! My most successful side project already :)
I've been doing a lot of parallel work and it can be draining. It feels exciting to have 6 agents spinning on things, but unless you have very well scoped plans, you need to still check in frequently.
If you have the tokens for it, having a team of agents checking and improving on the work does help a lot and reduces the slop.
I'd love for all these tools to standardise on the structure of plugins / skills / commands / hooks etc., so I can swap between them to compare without feeling handicapped!
Well, it's one conversation per bot. I set it up, connected the channel. DM'd it (only way to converse with it - wish I could have a Discord channel per project, different CWDs etc...) and asked what happens when I start 2 claude sessions connected to the channel and it said it'll just work with one.
Suppose you could have multiple bots, but it looks like it only supports one bot token anyway.
I like it but it's one conversation at a time, no ability to manually compact the chat... I guess it's an early version still.
Just when I increased my subscription with CC for more Opus 4.6 usage :)
I'm using obra superpowers plugin in CC and the plans it produces are very code-heavy, which is great for reviewing - I catch issues early. It's quite verbose however and if your codebase moves quickly, the code might have bad/stale examples.
Those very detailed specs then let agents run for a long time without supervision so nice for multi tasking :)
Yes, reviewing things make things slower. Not reviewing them produces horrible results. There's a balance to be found and it depends on the team/org.
I hope we shift engineers closer to users than ever before. Get them to understand user's needs and the actual product more - they'll write better plans and prompts. Review the plans.
Code review becomes less of a thing when the team's on the same page, so regularly align on what the goals are.
Accept post-merge code reviews. Things slip, normalise coming back and saying "actually, we should have done this differently". It's not a bad thing, you're learning!
Not sure this works very well. I got 10/21 with 3 quick wins:
- Start recording major architecture and workflow decisions in ADRs.
I'm not sure all decisions need to be in ADRs. I think AGENTS.md can summarise a lot of this and as long as you keep it up to date, it sounds more efficient than keeping every record? Some is fair though to show how you make decisions
- Add at least one linter and formatter with explicit repo-level commands.
I have it with go, not detected
- Group repo docs under `docs/` or add an index that links the important pages.
What happened to comments in code? :)
It's likely going to be a game of whack-a-mole, especially with AI as opposed to simple bots/scripts. Not that they shouldn't try to prevent it, but not entirely sure what the solution is.
Late to the thread but I've been excited to be building crit to help reviewing plans & output from LLM agents - it has boosted my productivity a lot personally and I had a lot of nice feedback from other experienced engineers finding value in it - turns out while terminal is a nice way to chat with agents, GitHub-esque PR review wins for long markdown and diff view :)
It's MIT open source, offline first, single binary
Beautiful apps! Well done
I like the idea of Kvile, I hate Postman with passion -- but I'm having difficulty getting started - I expected a screen to start creating a network request; it asked me to add a folder so I did it and now the Collections is spinning (it's an empty folder, so not sure what's it doing?) and I still don't have a screen to create the HTTP request itself. Do I need the .http files, i.e. Kvile doesn't give you the editor?
Beautiful landing page!
I'm juggling two projects:
Offline first, no tracking PWA for intermittent fasting and mindful eating. It helped me lose another 3 kg in January. Spiked a native iOS version, but I really like the simplicity of just the PWA. Not sure what's next!
--
Having done a lot of back and forth with LLMs and at the end throwing away learnings from a conversation felt so wasteful - reposit allows you to /share a summary of the valuable learning from your LLM chat for others to discover.
At the beginning of researching a problem, your agent can search reposit just like Context7 for docs. This way, even if you opt out of sharing your data with your LLM provider (as it's all or nothing), you can choose to publicise a solution to your problem with very little effort.
I'm working on extracting valuable learnings from open-source community projects as a starting point now (with attribution), as it probably needs a larger database to be valuable for users to install and use.
You can also self-host it and share privately within the company.
I've been consistently pushing updates to my intermittent fasting & mindful eating companion app - https://www.fastpause.app/ - offline first PWA with no tracking.
It helped me stay more consistent with IF - added visual indicator of previous fasts in a little calendar widget on the dashboard so every time I open it, I see my streak visually, which has been a great motivator to continue.
I also added a BMI calculator, as the NHS one I had to enter all my values from scratch each time I went, so got a bit annoyed :)
I think I'm still the only user, but it's given me a lot of value as I beat my plateau!
Offline first PWA for intermittent fasting tracking and mindful eating. No account needed, no ads, no tracking, no cookies, no AI integrations. Built it for myself out of annoyance with the bloated apps (admittedly it's still bigger bundle than ideal, since I'm using React, but I think it's something like 2mb compared to 200mb similar apps on app store).
IF and mindful eating have been massive in terms of my weight loss, but it's still very much a conscious effort, and this tool has been helpful in improving my habits.
Vetspire | Full Stack Software Engineer | REMOTE US / Canada (HQ in Austin, TX) | Full-Time | $120k - $150k | https://vetspire.com
Vetspire is a veterinary medical records and practice management platform. We’re a startup reimagining the way that veterinarians use technology, impacting every aspect of patient care from the exam room to managing client communications and clinical analytics. As part of our team, you’ll be designing the future of what veterinary technology should and can be, and you’ll be joining a founding team out of the Stanford Artificial Intelligence Laboratory building a research platform for evidence-based veterinary medicine.
We’re growing quickly and looking for a full stack engineer to join the team to help bring veterinarians’ dreams into fruition. Your day to day work will consist of learning and understanding veterinarians' and veterinary staff needs and bringing them into reality from the front-end to the backend. To do this, you’ll be working at every stage of patient care from the exam room to back-end analytics.
Some examples of what your weeks may look like: creating an emergency room clinical census to monitor patients and alert staff in real-time, designing the interface and algorithms for intelligent immunization reminders, and building a secure messaging platform for client and doctor communications.
We're looking for someone who will take ownership over the full pipeline of their work in a team-centered atmosphere that will work and talk directly with the users every day. You'll want to take pride in talking with clients to understand their needs, brainstorm with the clients to find the ideal solution, implement the back-end architecture at scale, design beautiful and intuitive interfaces on the front-end, and continually iterate based on client feedback.
This specific role will be very hands-on: you'll work closely with our users to understand their unique needs and build solutions for them to solve real problems in the field. It's half-part engineering, half-part problem solving.
Our backend is a GraphQL Phoenix/Absinthe application written in Elixir, our front end is a React SPA using the Apollo GraphQL framework, our primary database is PostgreSQL, and it all runs on Google Cloud via Kubernetes.
Experience with these technologies will be a great bonus (especially Elixir, React, and GraphQL), but the most important experience is in understanding users’ problems and putting together end-to-end solutions. Experience in healthcare technology is also a boon, but not at all required. Keen attention to detail and design is a must.
Email me: tomasz@vetspire.com (include "HN" in the subject) or apply at https://angel.co/l/2vmjQK