Boris Cherny retweeted
We’re adding support for MCP Tasks and Elicitations in Claude.

Tasks let Claude give plugins long-running jobs such as deep research and report back when they’re done.
261
293
5,559
519,958
Agent Skills started as an experiment in Claude Code. Many across the industry have come to adopt it, so we at Anthropic found it more fitting to donate it to the @AgenticAIFdn, next to MCP.
We're donating Agent Skills to the Agentic AI Foundation (@AgenticAIFdn), the same foundation we donated MCP to.

Since December 2025, 70+ agent platforms have integrated the standard, including ChatGPT, Cursor, GitHub Copilot, and VS Code.

Here's what that means for you:
227
99
2,566
255,846
Boris Cherny retweeted
We’re opening a research preview of Claude Duet, a new app where Claude works as a proactive agent.

It comes to you with what needs your attention, completes tasks you ask of it, keeps working when you step away, and checks with you before it acts on your behalf.
2,317
4,190
54,859
10,254,579
Boris Cherny retweeted
We launched OSS Scanner, which gives critical open source projects free, periodic vulnerability scans from our strongest models.

Each finding includes a proof-of-concept, and a patch where possible.

red.anthropic.com/oss-scanner
289
1,338
13,717
1,145,941
Boris Cherny retweeted
In the next version of Bun

bun lint is a 26x faster ESLint-compatible linter with over 1,000 builtin rules - reads eslint & oxlint configs.
55
60
1,151
97,223
Boris Cherny retweeted
We keep improving performance across Claude, and you may have noticed it starts responding sooner!

Claude Code now gzips the conversation it sends on every turn, so it reaches the model faster. Cloud sessions also start up as soon as you start typing.
678
742
17,440
2,901,657
Boris Cherny retweeted
Six projects from the last few weeks that caught our attention:

A wildfire analysis prototype that maps the fire’s spread over time and tracks hot spots, made with Opus 5.5.
663
2,332
34,906
2,226,477
Don't sleep on Claude Slides. This is how I make slide decks now -- no more googling "iphone frame svg" like the old days

Try it: claude.ai/artifacts
200
154
4,674
453,557
I could not imagine being productive without Claude Code Review. It runs on all of my PRs, and catches almost every bug before it goes it. This is a piece of the secret sauce that lets the team and I move so quickly while raising the quality bar
Code Review is now generally available for Claude Team and Enterprise plans.

Reviews are now faster, catch more of the bugs that matter, and admins can pick from Quick, Standard, or Deep review levels for each repo.
354
179
5,022
452,113
Over the last few years, we have made significant progress on prompt injection for Claude models. As agents do more, it is increasingly urgent that we solve it across the industry.

Really excited to partner with Gray Swan to host this competition. Can’t wait to see what you find!
Is prompt injection solved? Here’s $300,000 to find out.

In partnership with @AnthropicAI, @Meta, @GoogleDeepMind, @reflection_ai and our other frontier lab sponsors, @GraySwanAI is excited to announce the largest and most realistic AI red teaming challenge to date.

Indirect ⚫
140
45
777
103,042
Boris Cherny retweeted
Hi, I'm Felix. I'm an eng lead working on Claude. I love watching people take flight and do things they never thought possible.

We often describe that as "being more ambitious" when using AI, which is tricky advice to follow. I wrote a tutorial:

felixrieseberg.com/how-to-be-more…
403
2,517
24,038
5,294,751
Boris Cherny retweeted
What did @AnthropicAI do with his latest Claude Desktop update? I feel like there was a major system prompt/harness upgrade here. Opus 5.5 feels like it's Opus 5.8 now.

cc @trq212 what did y'all do?
61
20
2,242
274,324
Boris Cherny retweeted
We've been working hard on making the Claude Code desktop app great for running lots of sessions side by side.

It's now much quicker to start sessions, easier to split work across a few, and you can always see what each of them is doing. Here’s what's new:
957
912
20,711
2,327,540
Boris Cherny retweeted
New on our Engineering blog: Creating in-house source control.

In May, we merged around 2,500 code changes per day. In September, we merged more than 30,000 per day. As a result, we became bottlenecked by developer infrastructure built for human (rather than agent) scale.

Here, we share how we built a new version control system—and fully migrated our monorepo from git—in five months: anthropic.com/engineering/re…
1,176
2,660
25,980
8,300,377
Boris Cherny retweeted
We just let in every Pro and Max user from the Claude Code Projects waitlist!

If you're new to Claude Code Projects, here's a 4 minute walkthrough to get you started:
553
824
15,837
2,046,214
Boris Cherny retweeted
people really like the versions of Claude Design and Slides built into Claude — usage is much higher.

we're doubling down there and folding standalone Design into Claude on December 14.

before then — PLEASE tell me all the reasons the new one falls short and we'll fix em!
114
23
655
81,987
Boris Cherny retweeted
Claude Dashboards and Claude Motion are in beta today.

Ask Claude to turn your data into live dashboards and your ideas into animated explainers.
1,236
4,600
60,550
11,425,570
Sometimes I read on flights, and sometimes…
170
66
3,125
304,917
Replying to @bcherny
Ok back to reading
15
0
112
24,527
Replying to @bcherny
It was one prompt, claude verified pretty well too! No bugs so far
8
0
54
11,824