I am a happy user of this and have recommended my team also install it. It’s made a sizable reduction in my token use.

Thanks, really appreciate hearing that! Glad it's working well for your team.

HN Mod here. Is the date on the post an error? It says Feb 2025 but the project seems new. I initially went to put a date reference on the HN title but then realised it's more likely a mistake on your post.

His post, code and all the replies here are LLM authored and don't make any sense. He has no idea why his Claude Code instance wrote Feb 2025 instead of Feb 2026. I mean all his results are placebos or nonsense. I can also start new conversations with only 2% of the context in it, or you can call compact, it will all work better. The post has to be flagged.

There was a time when his insight was relevant and spoke to a lot of people. I hope he finds peace in whatever is next.

The tips in the article on enabling vi mode and fzf keybind are worth the read imho

Their multiple rounds of VC funding are predicated on their vision of collaboration so they gotta make a go at it.

Management and product needing vision and foresight is an excellent call out. I can't help but think a lot of these self-proclaimed 9-9-6 startups are in reality 11-3-6 startups with a bunch of wasted time padding to 9-9-6.

Oh I remember a time before CDNs and a big part of your startup fundraise was to build out your own setup inside a data center.

It's not the specialization around hosting that's the problem, but that entities running CDNs realized they're in a privileged position in the network, and decided to capitalize on it.

That's not what CDNs are for. They exist for primarily two purposes: a) speed up video loading for end-users, and b) anonymize IP addresses and routes for businesses.

Cloudflare built a business around b). This doesn't save on hosting costs, only lowers some operational and legal risks.

Their burn agent mode is pretty badass, but is super costly to run.

I'm a big fan of Zed but tbf I'm just using Claude Code + Nvim nowadays. Zed's problem with their Claude integration is that it will never be as good as just using the latest from Claude Code.

Same except with Helix.

The integration in Zed is limited by what the Claude Code SDK exposes. Since about half of the /commands are missing from the SDK, they don’t show up in Zed.

I think ACP was a good strategic move by Zed, but all I personally really need is Claude Code in a terminal pane with diffs of proposed edits in the absolutely wonderful multibuffer view

These extreme rounded corners are super triggering my desktop OCD

Text on frosted glass over other text is really hard to read

We need an option to turn these “improvements” off

FWIW my system does feel more snappy and the improvements to Spotlight are nice

I love Zed but this has all the hallmarks of something being totally rushed out the door.

It works off the Claude Code SDK, which mean it doesn't support many of the built in slash commands - it doesn't support /compact, which is 100% necessary because when you use this implementation enough, you'll eventually get a "Prompt too long" error message with no ability to do anything about it. Since you can't see how far you are in the context window, it's a deal breaker, since you have to start a fresh chat and might run out of room before you can ask it to create a summary prompt for continuing.

There is no way to switch models that I can tell - I think it just picks up on your default model - and there is no way to switch to Plan mode, which has become absolutely crucial to my workflow.

I didn't see Zed picking up on problems reported in the IDE, it was defaulting to running 'tsc -b' in my directories.

At this point it's better to run a terminal inside Zed and work from there. The official response in the Zed Discord has been "talk to your local Anthropic rep" to get them to support Zed's Agent Client Protocol (ACP).

The Agent Model came out very recently, I’ve been following the GitHub issue over the past days and you can see it was rushed out. But I don’t see anything wrong with that, many AI topics are being rushed out and adding slash commands and other small things are very small things to add once the foundation is there.

Tbf I never use /compact but clear instead, and load in the relevant context anew. I just haven’t seen compacted context to be very useful, so far.

The model is usually so confused after a /compact I also prefer a /clear.

I set up my directives to maintain a work log for all work that I do. I instruct Claude Code to maintain a full log of the conversation, all commands executed including results, all failures as well as successes, all learnings and discoveries, as well as a plan/task list including details of what's next. When context is getting full, I do a /clear and start the new session by re-reading the work log and it is able to jump right back into action without confusion.

Work logs are great because the context becomes portable - you can share it between different tools or engineers and can persist the context for reuse later if needed.

The trick is to parametrize the /compact. Something like "/compact focus on the XZY, the next steps will be FOOBAR, and keep a high level summary of BARFOO"

That makes the compaction summary a lot more focused and useful.

edit: But a work log/PRD is essential regardless!

I’ve been using PRD specs at kick things off, but curious about how to a “work log”. Are there examples of how to do this with CC?

"Implement phase 1 of the PRD, when done update the PRD and move on to phase 2."

yep, exactly, using it like this myself

I think both /compact and /clear are valuable / have their own use cases.

my small mental mode: - really quick fix / need to go over board with context -> just /compact + continue pushing - next phase -> ask for handover document or update worklog, and then send fresh one to new phase.

Thank you for this. I didn't know this was an option.

I notice when I'm getting close and I tell it how to document current state into an .md file. Then I hit /clear and @ the new file.

This is probably very similar to /compact except I have a lot of control over the resulting context and can edit it and /clear again and retry if I run into an issue.

Seems like those issues are largely limited by SDK so urging Anthropic to adopt is the only realistic move

Yeah I was initially excited here, but it feels more like a demonstration of what's possible rather than a working tool.

I found the interface very nice but quickly ran up against limitations on prompt length (it wasn't that long) for example. I am used to being able to give detailed instructions, or even paste in errors/tracebacks.

I'll check back in in a few months.

Bun has been awesome for me and my team fwiw