ClaudeDevs

Claude Code sessions can now message each other: instead of re-explaining context in a second session, one session sends a summary, not history or files, and the other picks it up mid-task.

An article by ClaudeDevs explaining the concept of 'designing loops' for coding agents, a emerging paradigm shift from traditional prompting. It helps developers building with Claude AI understand how to structure agent workflows for more reliable and effective code generation.

Anthropic extends the 50 percent increase to weekly Claude Code limits through August 31, with a warning that model demand may make capacity tight and no commitment yet on making the change permanent.

Claude Code desktop adds an auto-continue option: hit your usage limit and it resumes where you left off once the limit resets.

Claude Code ships a /design skill in research preview that generates editable artboards in the CLI and Desktop and hands the chosen one back to the agent to implement.

Anthropic sets Claude Code's weekly limits: a permanent 25% raise for Pro, Max, Team and seat-based Enterprise from September 14, replacing the temporary 50% increase — a net 17% reduction from current headroom, with usage visibility controls promised next.

Auto mode becomes Claude Code's default permission mode for Pro, Max and Team on August 14. Its separate classifier caught 89% of dangerous commands in testing, against 14% for manual approval.

Claude Code adds a Concise output style that leads with the result and keeps responses short, with full detail still available on request. It is switched on from the config menu or by setting the output style key in the settings file.

Claude Code adds a built-in 'You should know' plugin, implemented as a mod that spins off a side agent to watch Claude's output and surface easily missed information. Enable it with the plugin command; Anthropic also published a getting-started post on mods.

Anthropic's new developer blog collects engineering deep dives, Claude Code and API playbooks, skills guidance, and videos from the teams building Claude, including posts on eval automation, Opus 5.5 task costs and context engineering for Claude 5 models.

Anthropic ships Fable 5.1 to Claude Code and the Claude Platform at Fable 5 pricing, with cache reads cut to $0.25/MTok and 55.8% on Terminal-Bench 4.0. New accounts also lose the ability to edit context before thinking blocks, an anti-distillation measure.

Remote Control adds phone started sessions and recovers dropped connections on its own.

Claude Code adds a screen reader mode: a flag swaps the visual terminal UI for plain linear text that VoiceOver and NVDA can follow.

Anthropic reports Claude Code CLI now uses half the CPU at p99 after moving Bun's garbage collection off a fixed timer to run only when the process is idle.

The Claude Code desktop app now supports /resume, which lists any session started from the CLI and picks it up in the app with the full conversation and context carried over. Terminal and desktop share one session history.

Claude Managed Agents gains session budgets: set a spend limit and a session that reaches it pauses with a budget_reached event until the budget is raised.

Anthropic developers migrated ten code packages, tens to hundreds of thousands of lines each, in a month using Claude Code, turning what were multi-year porting projects into individual work.

This week's Claude Code shipping list: the CLI stops blocking on sandbox and MCP startup, the Linux x64 download drops ~4.5x to roughly 75 MB, /cost gains a prompt-cache line, /usage attributes tokens per /loop run, /permissions gets an editable Auto mode tab, and dropped remote sessions reconnect.

Auto mode rolls out as Claude Code's default for Pro, Max and Team. Existing default-mode settings are respected, and modes still switch via Shift+Tab or a settings pin.

Anthropic explains the safety classifier behind Claude Code's auto mode, which decides what is safe to run now that actions no longer need individual approval.

Anthropic's Claude Desktop now boots roughly twice as fast, after the team found background windows were throttling timers and dropping the JS engine into power-saving mode.

A cookbook wiring Claude Managed Agents to Vercel's Chat SDK: one typed direct-message handler fans out across 15+ chat surfaces while the agent runtime, session state and memory stay server-side, with a sandbox option for tool execution.

Anthropic ships enterprise-managed auth for MCP connectors: Team and Enterprise admins centralize authorization through their identity provider, so tools connect without per-user OAuth. Launch partners include Linear, Notion, Slack, Figma and Supabase; third-party connectors can opt in.

Claude Code will now write its own feedback reports — triggered when a command fails, when Claude catches its own mistake, or when you say something went wrong — leaving you to edit and approve before anything is sent. Configurable or disableable in /config.