Claude Code Launches /goals Command to Separate Execution From Evaluation

Anthropic developed Claude Code as an agentic tool that can inspect repositories, edit software and run tests from a terminal. Connecting it with Claude Design narrows a longstanding gap between interface mockups and production code: developers can explore visual directions using an existing project’s components and brand rules, then continue implementation without exporting static files or rebuilding the design by hand. The integration puts design iteration and software development in a shared workflow.

Anthropic released the update on June 17, 2026, adding the /design command for creating, editing and synchronizing design projects without leaving Claude Code. Users can generate and refine multiple editable canvases, turn existing code into a live prototype and hand a selected direction back to Claude Code for implementation. Anthropic said more than 1 million people used Claude Design in its first week. The beta is included with Pro, Max, Team and Enterprise subscriptions, although Enterprise administrators must enable it.

Claude Code is Anthropic’s agentic software-development tool, and its system prompt supplies persistent instructions governing tool use, coding style and behavior. Such prompts have traditionally accumulated rules and examples meant to prevent failures in weaker models. Anthropic’s latest change matters because it suggests more capable Claude 5 models can infer intent and local conventions with less prescriptive guidance, shifting context engineering toward model judgment, better-designed interfaces and information loaded only when a task requires it.

Anthropic technical staff member Thariq Shihipar said in a July 24, 2026 blog post that the company removed more than 80% of Claude Code’s system prompt for Claude Opus 5 and Claude Fable 5, with no measurable decline in its coding evaluations. Verification and code-review guidance was moved into selectively loaded Skills, while tool instructions were consolidated. Anthropic did not disclose the evaluation set, before-and-after scores or any associated cost figures, and older models continue to use fuller prompts.

Artificial intelligence company Anthropic is working to make generative AI more practical. Its autonomous agent service can carry out multistep tasks across files and applications, marking a milestone in improving business productivity. The service turns AI from a one-way conversational tool into a virtual assistant that can operate in the background and handle complex workflows, opening new possibilities for business automation.

Anthropic announced web and mobile app versions of Claude Cowork on July 16, 2026. The service is initially rolling out to users of its top-tier Max plans, priced at $100 and $200 a month. It supports multistep business tasks across platforms, allowing users to submit work to the cloud and then go offline while the workflow runs entirely in the background.

The open-source claude-peers-mcp project enables multiple Claude Code sessions on the same computer to exchange messages directly and synchronize task status without relying on cloud services or intermediary APIs. The project extends a single AI assistant into a local team capable of dividing work across parallel development, software debugging and research tasks.

claude-peers-mcp has recently drawn attention for demonstrating a decentralized model of AI collaboration, with individual sessions sharing progress and coordinating tasks locally. Reports did not disclose a release date, developer or funding amount. Practical use remains constrained by hardware demands, conflicts when multiple agents edit content simultaneously, and the stability of state synchronization during long-running operations.

Anthropic’s Claude Code uses the `.claude/` folder to manage project rules, tool permissions and collaboration workflows. This enables the AI coding agent not only to generate code but also to perform tasks according to team conventions. The control architecture helps reduce uncertainty in agent behavior while making development work more reproducible and governable.

According to information compiled as of July 20, 2026, AI engineer Akshay has published a comprehensive guide covering project-level and global configurations. It also explains six core components: `CLAUDE.md`, `rules/`, `commands/`, `skills/`, `agents/` and `settings.json`. The guide focuses on modular instructions, custom commands and permission management. It is not associated with any funding, transaction or financial figures.

Claude Code is Anthropic’s agentic coding tool, capable of reading and writing files, running Bash commands and executing tests. Its default permission system requires human approval before writing files or running commands. Auto Mode instead uses a separate classifier to review each tool call, aiming to keep long-running tasks moving while preventing file deletion, data exfiltration and malware execution.

Anthropic launched Auto Mode as a research preview for Team plans on March 24, 2026, expanding it to Enterprise plans and the API within days. On July 10, it announced that the feature was formally available to all eligible users. Auto Mode requires Claude Code version 2.1.83 or later. It blocks high-risk operations and pauses after three consecutive blocks or 20 blocks in total. Anthropic did not announce separate pricing.

Anthropic is expanding Claude from a chatbot into infrastructure for knowledge work and software development. Cowork supports desktop collaboration, while Claude Code, Skills, Agents and MCP connect software development, tools and multi-step tasks. The integration allows AI agents to work continuously across documents, spreadsheets and large codebases, extending their role beyond one-off questions and answers.

Anthropic launched Opus 4.6 on February 5, 2026, and Sonnet 4.6 on February 17, with both offering a 1 million-token context window in beta. Sonnet 4.6 is available in Cowork, Claude Code and the API, with pricing unchanged at $3 per million input tokens and $15 per million output tokens. A March 25 report brought the complete workflow together.

Anthropic engineer Thariq explained the core role of Skills in Claude Code: they are not merely static prompts, but tools that can load instructions on demand, run dynamic scripts and preserve work context. The design allows an AI coding assistant to accumulate team knowledge while reducing repetitive prompting and workflow inconsistencies. No financial amounts were involved.

A 2026 guide outlines nine use cases drawn from Anthropic's internal practices, including workflow automation, product validation, operations and maintenance, and taking notes while coding. Thariq also shared advanced prompt-engineering techniques, arguing that Skills should explicitly define task steps, tools and memory rules to make Claude Code more reliable when handling complex work.