Saad | building CoralSwarm & CrossTask

Starting June 15, paid Claude plans can claim a dedicated monthly credit for programmatic usage. The credit covers usage of: - Claude Agent SDK - claude -p - Claude Code GitHub Actions - Third-party apps built on the Agent SDK

2 days into the work week and my weekly limit is already maxed out. #Claude @trq212

Now that OpenAI announced Daybreak I bet Anthropic will drop Mythos within the Week

I wish my skills synced from one machine to another. It’s so annoying when I switch machines and the skills I had are all gone.

I’ve seen this happen a lot when making html plans compared to markdown @trq212

@icanvardar I don’t put random line breaks in my paragraphs

tell me you’re not an ai without telling me you’re not an ai

Single-agent AI code reviews have a trust problem. Too many false positives, not enough signal. So I built a Code Review Panel skill that runs 10 agents in parallel — paired for consensus. Five categories: Security, Performance, Correctness, Maintainability, Style. Two agents per category, reviewing independently. An issue only makes the final report when both agents in a domain flag it. Disagreements get filtered out as likely noise. Anyone else experimenting with multi-agent consensus patterns? #AI #AgenticCoding

Me when I hit my weekly Claude Limit

@CPME_USA @AnthropicAI @claudeai @trq212 I was able to get past it by logging out and logging back in a few times.

@verdaxxed @AnthropicAI @claudeai @trq212 same here....extra usage enabled, nothing used in the budget and locked out waiting on timed reset @AnthropicAI happened on both personal and team plans today

@AnthropicAI @claudeai @trq212 Says I am out of Extra Usage even when i have Usage available?

Being in San Francisco this week was so inspiring and motivating. If you’re in the DFW Area and you’re a founder or building something cool let’s connect! #AI #DFW

@james406 Imagine seeing someone copy from vs code and pasting it into ChatGpt

saw someone vibe coding at a cafe no voice mode no multi-agent setup no 3-hour extended thinking loops no switching between Codex and Claude Code just typing a prompt, and staring at the screen, waiting for the response like a psychopath

Has Anyone else not been able to access their Projects in Claude Design? @trq212 @claudeai

One thing I’ve realized is I’ve been building in private for too long, my goal for this year is to build in public more!

That's a wrap on Code with Claude San Francisco! Clawd had an amazing time, and we hope you did too. Thanks to everyone who came out and everyone who tuned in 🧡

I had the opportunity to have a conversation with a member of Anthropic's Staff today. I asked him: "how crazy is Mythos Really??" His response: "Crazier then you can imagine." We're in for a fun ride #AI #Anthropic #StartUp

Code w/ Claude was an amazing experience shoutout to the anthropic team for hosting! #CodeWithClaude #Anthropic

Live from Code with Claude: we're launching dreaming in Claude Managed Agents as a research preview. Outcomes, multiagent orchestration, and webhooks are now in public beta.

New for financial services: ready-to-run Claude agent templates for building pitches, conducting valuation reviews, closing the books at month-end, and more. Install them as plugins in Cowork and Claude Code, or use our cookbooks to run them in production as Managed Agents.

Managing API keys is one of the top security concerns we hear from customers. Today we’re introducing keyless auth for Claude Platform: authenticate via browser with the CLI, or let workloads use their existing cloud identity (AWS, GCP, Azure, or any OIDC token provider).