Sanjiv
1K posts
agent-browser now supports iframes
→ Snapshots inline iframe content automatically
→ Interact with elements inside iframes using refs directly
→ No frame switching needed
English
Installation of mcp too manual, lack of easy way to enable and disable mcp within a session, ability to export chat conversation to text, / clear reloading mcps ( is this a hot load feature?) . Otherwise really liking the quality of work it produces, it standing its ground even it I try to sway it intentionally.
English
@mattpocockuk Was expecting grill-me to be invoking the Ask Question Answer tool, any reason for its omission?
English
I've been an engineer for nearly a decade. Right now, process has never been more important.
And skills are the best way to bundle up processes for agents.
Here are the 5 I use every day:
/grill-me
/write-a-prd
/prd-to-issues
/tdd
/improve-my-codebase
English
@ryancarson Is this solo work or with a team? Some argue for solo work any sort of tracker is a bit of overkill
English
This works well for me:
1. Plan mode in Codex on xHigh
2. Copy markdown plan
3. Paste md plan into Linear issue and Symphony takes it all the way to human review (or auto merge of low risk)
English
🎁 Happy Friday - Opus 4.6 1M is now the default Opus model for Claude Code users on Max, Team, and Enterprise plans.
Pro and Sonnet users can opt in with /extra-usage.
Claude@claudeai
1 million context window: Now generally available for Claude Opus 4.6 and Claude Sonnet 4.6.
English
@thsottiaux out of the box codex commit messages are very minimal on details compared to claude. Would be great to see some improvements in this area.
English
Conversational analytics. It's working! 🎉
@aisdk 🤝 json-render 🤝 @tinybird
Forrest can answer business questions, with built-in domain knowledge, by scanning millions of rows and hundreds of columns and responding like a super-analyst in a matter of seconds.
Full chat persistence with every message stored securely in the database.
English
New in Claude Code: Code Review. A team of agents runs a deep review on every PR.
We built it for ourselves first. Code output per Anthropic engineer is up 200% this year and reviews were the bottleneck
Personally, I’ve been using it for a few weeks and have found it catches many real bugs that I would not have noticed otherwise
Claude@claudeai
Introducing Code Review, a new feature for Claude Code. When a PR opens, Claude dispatches a team of agents to hunt for bugs.
English
GPT 5.4 xhigh is ridiculously good. Been using Opus 4.6 as my daily driver but threw a hard problem that required wide changes across my codebase at GPT-5.4 xhigh and it solved it very robustly. There’s something different about the way if reasons and shares reasoning along the way as feedback for long or complex tasks. Super impressive!
Tibo@thsottiaux
With GPT-5.4 out. What should Codex ship or improve next?
English
@bcherny @iamjstevenson I would be nice to have the pasted image placeholder appear at the point in the message that the user pasted it. Right now the message looks like “compare this image with the other one from prod” image1 image2
English
@iamjstevenson We buffer the bytes to verify they’re really images. I bet we can improve this, looking
English
@stephenhaney The video is cool but I’d like to see a tutorial video covering various features
English
Hello!
Today we're releasing Paper Desktop
Paper is now a canvas for Cursor, Claude Code, Codex. Any agent can read and write html to Paper.
• push or pull from your codebase
• pull real data from anywhere
• less work, more design
What will you ship? Sound on 🎶
English
@trq212 @DeanLearner This happened to me as well a few weeks ago. Glad to see the team on top of this now.
English
oh wow! just got my Claude Max account suspended because of "an internal investigation of suspicious signals associated with your account indicates a violation of our Usage Policy"
I wasn't using it with OpenClaw or doing anything crazy with it; I wonder what triggered it
English
@AnthropicAI with the latest Claude build on OSX, when I go to the Organization settings I get the message below. I'm on a Team plan. The message doesn't seem to affect the prior functionality but still a little surprising to see such a message.
English
@HamelHusain Seen this too but if often just says “This is good feedback”
English
I'm very amused by how much claude pushes back against codex
- "this is over engineering"
- "looks like they don't understand the big picture"
etc.
I'm also amused by codex's passive aggressive blunt commentary
It really is the perfect pairing 🤣🤣🤣
English
I've been having codex review claude so much that I made a thing to automate the ping-pong
github.com/hamelsmu/claud…
English
@HamelHusain This has been my manual workflow. Looking forward to taking it for a spin
English
@robzolkos It’s like walking on eggshells. Your account could be banned any time arbitrarily without explanation.
English
The best thing the public faces of Claude Code could do right now as this blows up - is come out with a simple - developer and human friendly - explainer on what is and is not allowed. No legal mumbo jumbo - just be up front and clear with your customers. List the 20 common scenarios you see in the wild and just yay or nay them.
Rob Zolkos@robzolkos
Major Claude Code policy clear up from Anthropic: "Using OAuth tokens obtained through Claude Free, Pro, or Max accounts in any other product, tool, or service — including the Agent SDK — is not permitted"
English