Newsletter

/simplify is now /code-review, flagging correctness bugs at a chosen effort level; /usage breaks down consumption by skills, subagents, plugins, and MCP servers; and /model changes apply only to the current session. In other news: Anthropic is nearing its first profitable quarter, Andrej Karpathy is joining, and Stainless has been acquired.

This week's agent view research preview debuts claude agents, a dashboard for all running, blocked, or finished sessions, plus a new /goal command and fast-mode upgrade to Opus 4.7. Headlines: Anthropic closes a $30bn round at $900bn valuation, subscription caps tighten, and Microsoft reportedly pulls internal Claude Code licenses.

The new worktree.baseRef setting controls whether worktrees branch from origin (default) or local HEAD, while hooks and Bash commands can read the active effort level via $CLAUDE_EFFORT. Anthropic also raised Claude's usage limits, signed compute deals with SpaceX and Akamai, and joined Blackstone and Goldman Sachs in a $1.5B enterprise AI venture.

The new claude project purge command clears per-project state with dry-run and interactive modes, the model picker now pulls from your gateway's /v1/models endpoint, and OAuth login finally works in WSL2, SSH, and containers. In the news: Anthropic missed Pentagon AI deals, Mythos faces global scrutiny, and a $900B valuation looms.

/config choices now persist via ~/.claude/settings.json, vim mode adds visual and visual-line selection, and --from-pr supports GitLab, Bitbucket, and GitHub Enterprise. In the news: Anthropic is investigating possible unauthorized access to its Mythos model, Google is committing up to $40B to Anthropic, and Mozilla used Mythos to fix 271 Firefox bugs.

Claude Opus 4.7 is now available in Claude Code with a new xhigh effort level, alongside a native binary for faster startup and a parallel multi-agent code review command. The release arrives as Anthropic fields investor interest at $800 billion, negotiates model access with the White House, and shifts enterprise customers to usage-based pricing.

Claude Code's default effort level is now set to high for most users, joined by a new /team-onboarding command and interactive setup wizards for both Bedrock and Vertex AI. Elsewhere, Wired and the NYT cover Mythos's cybersecurity implications, and Bloomberg reports an Anthropic-CoreWeave compute deal.

Claude Code now offers an interactive Bedrock setup wizard, per-model cost breakdowns, and flicker-free rendering via a new env var. Anthropic's source-code leak drew coverage from the Wall Street Journal and Wired, while BBC reported on widespread frustration with usage limits.

Auto mode brings safer permissionless operation to Claude Code, alongside transcript search, conditional hook filters, and a native PowerShell tool preview on Windows. Those updates arrive amid a federal court ruling preserving Anthropic's government access, reports of an IPO as early as October, and surging paid consumer adoption.

Claude Code's new --bare flag strips it down for scripted pipelines, while MCP channels, VS Code remote control, and line-by-line streaming reshape the interactive experience. Those updates arrive as Cursor plans its own rival model, OpenAI acquires Python toolmaker Astral, and Anthropic overtakes OpenAI in enterprise revenue.