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?
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)
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!
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'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.
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.