Here’s what’s new on the Claude Developer Platform (API): - Claude Opus 4.5: The model is a meaningful step forward in what AI systems can do. It’s our most efficient model, and is available at $5 input / $25 output per million tokens—making Opus-level capabilities accessible to even more developers and enterprises. - Advanced tool use (beta): Build agents that can take action with three new capabilities—the tool search tool, programmatic tool calling, and tool use examples. Together, these updates enable Claude to navigate large tool libraries, chain operations efficiently, and accurately execute complex tasks. - Effort parameter (beta): Control how much effort Claude allocates across thinking, tool calls, and responses to balance performance, latency, and cost. - Context management capabilities: Enable agents to handle long-running tasks when using tools with the new compaction control SDK helper and reduce token consumption with thinking block preservation, now enabled by default. 

Wes and team, This link below doesn't work. Does anyone have the txt file they can share? https://github.com/bmadcode/BMAD-METHOD/blob/main/dist/teams/team-fullstack.txt

As Collins’ definition states, “vibe coding” is “the use of artificial intelligence prompted by natural language to assist with the writing of computer code.” Or, as a blog post on the dictionary’s website explains: “Basically, telling a machine what you want rather than painstakingly coding it yourself.”

This solves one of the biggest pain points for MCP tool calls. Context bloated tool calls. https://www.anthropic.com/engineering/code-execution-with-mcp

I made a quick video showing people how to get started vibe coding using a powerful method called "BMAD". This is the first lesson in a new course. More lessons to follow!