The skill ships in the ASSERT repo with seven worked domains and 14 risk suites: github.com/responsibleai/ASS…

Introducing run-assert-eval. With a single prompt in @code, the skill identifies risks specific to your agent, measures how often they occur, generates runtime policy based on those findings, and reruns the same eval to see whether the policy worked. commandline.microsoft.com/ru…

Claude Opus 5.5, Anthropic’s newest Opus model, is now available in GitHub Copilot and Microsoft Foundry. In early testing, Opus 5.5 resolved tasks comparably to Claude Opus 5 while using significantly fewer steps and tokens.

Build agentic apps with the GitHub Copilot SDK, without implementing the agent loop yourself. Join this beginner-friendly livestream to learn how to use sessions, tools, MCP servers, streaming events, and more to embed Copilot’s agent runtime in your apps. Plus, check out specific sessions for .NET and Java development. No prior SDK experience required. Register for English, Chinese, Portuguese, Spanish, Japanese, or Korean 👇 gh.io/letslearn

Yes or YES? Get your #GitHubUniverse pass 👇 githubuniverse.com/?utm_sour…

Small feature, massive workflow win.

never starred two repos so fast

GitHub CLI now lets you attach local images and videos with --attach, so you can add media directly to issues, pull requests, and comments without leaving the command line. See it in action from @madebygps

Clear your calendars tomorrow for four hours of GitHub Copilot. We’ll get into agents, models, the CLI, VS Code, live demos, new stuff, and plenty of code along the way. Tune in and hang out with us. nitter.net/i/broadcasts/1vJpPNqoV…

Try ThinkingBox 👇   github.com/microsoft/thinkin… contains the runtime.  github.com/microsoft/thinkin… contains the benchmark tasks, synthetic records, and MCP servers.

We built ThinkingBox to measure whether agents actually finish the job. ThinkingBox runs agents in isolated, stateful tool environments, lets simulated users answer follow-up questions, and inspects the side effects left behind. commandline.microsoft.com/th…

Welcome to MCP Live! Join us for a half-day of MCP, from how it’s being adopted across the developer ecosystem to hands-on sessions on MCP at @github, building MCP servers with @code, and more. piped.video/watch?v=uydwDk91…

Starting soon 👇

Friday, September 4 8:00 AM - 10:00 AM PDT aka.ms/the-story-of-vs-code

This is the story of how @code got here, told by the people who built it and the developers who helped shape it.

Explore the repo: github.com/theagentplane/tok… Then get under the hood on TokenOps’ architecture and run-scoped governance 👇 commandline.microsoft.com/to…

Who spent all the tokens? 👀 TokenOps gives multi-agent workflows one shared, run-scoped budget, with policies that can step in before the next model or tool call executes. The result is real-time control over spend and agent behavior while the run is still happening.

Happy building! 🥳

What are you liking most about it?