ClaudeDevs ✓

@ClaudeDevs You gotta stop trying to trick me to pay API prices okay 13.9K views · 221 likes · 0 reposts · 5 replies Open on X →

Follow the link below to claim the credit or run /claim-credit in the CLI. You’ll need GitHub connected to start a session. Claim by Oct 7. Terms apply. https://t.co/TzoO6fzJHB 4.6M views · 6K likes · 470 reposts · 121 replies Open on X →

The credit is separate from your usage limits, and it applies automatically once you start a cloud session. If you hit a limit locally, keep going in the cloud until your credit runs out. One credit per account, for cloud sessions only. 312.2K views · 443 likes · 7 reposts · 8 replies Open on X →

Cloud sessions run on Anthropic-hosted infrastructure, so the work keeps going even without your computer running. Start one at https://t.co/scIJefCE5h, from the Code tab in the Claude mobile app, from the desktop app, or with claude --cloud in the CLI. 256K views · 527 likes · 11 reposts · 15 replies Open on X →

Cloud sessions are officially available and out of research preview! They let you keep Claude Code working, even when your laptop is closed. Existing subscribers get a one-time credit to try them: $100 on Pro, $250 on Max. https://t.co/SvdB2ATkFw

3.7M views · 11.9K likes · 895 reposts · 410 replies Open on X →

@ClaudeDevs https://t.co/xgUEUyZvyd

6.1K views · 136 likes · 6 reposts · 0 replies Open on X →

Opus 5.5 is available now in Claude Code and the Claude Platform. With its intelligence, lower price, and speed, it's our new daily driver for coding and agentic work. We hope it'll become yours too. 45K views · 321 likes · 5 reposts · 4 replies Open on X →

As our models grow more powerful, safeguards are one way we prevent misuse. Opus 5.5 is the first Opus with Fable 5.1-class safeguards on cyber, bio, and frontier LLM development. Flagged requests fall back to another model, and we're working to reduce incorrect flags. 50.7K views · 282 likes · 6 reposts · 18 replies Open on X →

On the Claude Platform, Opus 5.5 is $4/$20 per million tokens, down from $5/$25. Cache reads drop 60%, from $0.50 to $0.20. Run `/claude-api migrate` in Claude Code to switch to `claude-opus-5-5`. Our guide to lower costs with the Claude Platform: https://t.co/SVkAIm6Oy5. 49.3K views · 321 likes · 5 reposts · 2 replies Open on X →

Thinking is always on for Opus 5.5. Medium is the default, and you can adjust `effort`. For long-running agents, compaction summarizes older turns while keeping recent ones intact: https://t.co/y8E1Z9HdA6. And if you need more speed, fast mode goes up to 2.5x ($8/$40). 74.2K views · 271 likes · 3 reposts · 3 replies Open on X →

If you're on Pro, Max, or Team, your reset is available today in Settings → Usage. Apply it any time until Oct 22. Opus 5.5 is the default for paid plans. It's priced lower than Opus 5, so your 5-hour and weekly limits go 25% further. 341.5K views · 1.8K likes · 113 reposts · 77 replies Open on X →

Opus 5.5 is a lot better at writing too. It’s clearer, uses less jargon, and follows the writing rules you give it. Long Claude Code sessions are much easier to follow! 79.6K views · 953 likes · 16 reposts · 18 replies Open on X →

ClaudeDevs ✓@ClaudeDevs17 Sep

Today we're rolling out Projects in Claude Code on desktop and web. A project is one conversation with Claude. It splits the work into threads itself, runs them as parallel cloud sessions, passes context between them, and keeps going when you leave. In beta for select users. ht

0:25

1.2M views · 8.4K likes · 471 reposts · 356 replies Open on X →

ClaudeDevs ✓@ClaudeDevs16 Sep

Claude Design, Claude Slides and Claude Docs also work inside Claude Code now. Ask for a design review deck or a UI mockup and point it at the actual files and RFCs in the repo. Edit it yourself or keep going in the conversation, and share the link when it's ready. 638.6K views · 5.3K likes · 367 reposts · 158 replies Open on X →

ClaudeDevs ✓@ClaudeDevs15 Sep

We work with a lot of early-stage teams through Claude for Startups. At Frontier Day we asked a few of the founders what building a company on Claude looks like right now: https://t.co/Pb36MRla8V

2:07

150.1K views · 1.2K likes · 45 reposts · 73 replies Open on X →

Join a Fable 5.1 Build Day near you! We'd love to see what you're building. 295.3K views · 1.1K likes · 50 reposts · 172 replies Open on X →

Here's how our team uses Claude Tag for on-call: When an alert fires in Slack, Claude pulls metrics, diffs deploys, and checks flags. It finds a likely cause and proposes a fix, which we can approve and merge. Every minute counts, so we love that it starts right away! https://t.

2:10

286.3K views · 2K likes · 118 reposts · 116 replies Open on X →

@ClaudeDevs I sense a reset https://t.co/27H7o5eJOk

4.5K views · 52 likes · 0 reposts · 3 replies Open on X →

Evals call the model, so they use tokens and results vary. Pilot with `--runs 1` before a full run. Your plugin's hooks and MCP servers run as you, so only evaluate plugins you trust. Run claude update to try it. Docs: https://t.co/K3fKEzO7bI 34.7K views · 98 likes · 5 reposts · 2 replies Open on X →

New in Claude Code: claude plugin eval See what value your plugin is adding, or if it needs more work. You can create test cases, run your plugin or skill against those test cases, score those runs, then run each case again without the plugin to see the differences. https://t.c

913.2K views · 6.1K likes · 419 reposts · 197 replies Open on X →

Start in your plugin's folder and run `claude plugin eval init` You tell Claude what good and bad output looks like and bring a few real prompts. Claude drafts the test cases and checks, pilots the suite, and tells you what a full run will cost. 35.8K views · 146 likes · 5 reposts · 3 replies Open on X →

Then run `claude plugin eval` You'll see each case's score with and without your plugin in your terminal, plus an HTML report with the full detail. If your account supports it, the report is also published as a private artifact. 39.6K views · 88 likes · 1 reposts · 3 replies Open on X →

ClaudeDevs ✓@ClaudeDevs10 Sep

Two fresh updates to Claude Managed Agents: First, we've added a session viewer to the ant CLI. `ant beta:sessions connect` attaches your terminal to a running session, and `--web` opens a web UI served from localhost. https://t.co/1UgRRLyxUA

0:56

194.2K views · 1.4K likes · 83 reposts · 86 replies Open on X →

ClaudeDevs ✓@ClaudeDevs10 Sep

You can pop out any pane in the Claude Code desktop app into its own window. Drag the diff or terminal to a second screen while Claude keeps working in the main window, then dock it back whenever you want. You can also run sessions side-by-side or stacked. https://t.co/5BF38zm4k

0:22

351.8K views · 4.1K likes · 203 reposts · 225 replies Open on X →

ClaudeDevs ✓@ClaudeDevs3 Sep

We've added `ant apply` to the ant CLI. Now you can declare Claude Managed Agent environments, agents, skills, memory stores, and deployments as files in your repository and keep the API's resources in sync with them using `ant apply`. Docs: https://t.co/qQchmDjTmm https://t.c 321.6K views · 2.5K likes · 159 reposts · 133 replies Open on X →

ClaudeDevs ✓@ClaudeDevs3 Sep

We're exploring a new way to let you extend and customize Claude Code: Function Hooks. Here's a couple videos showing what you'd be able to do. It hasn't shipped yet, we'd love feedback on this on our GitHub issue. https://t.co/0F3kBO3kjl 879.4K views · 3.2K likes · 168 reposts · 201 replies Open on X →

@ClaudeDevs Can someone add a community note? 🤣 https://t.co/smeB7I7V1e 13.4K views · 353 likes · 10 reposts · 6 replies Open on X →

Read the full announcement: https://t.co/CDUDN3GvhD 56.4K views · 136 likes · 10 reposts · 1 replies Open on X →

Also, see our open-source reference implementation. This includes shopping & merchant agents, four vertical demos, and a Claude Code plugin that builds an agent against your backend. See here: https://t.co/rSLAFE1NUH 88.7K views · 442 likes · 49 reposts · 6 replies Open on X →