10 articles · Updated daily
Claude Code news for developers following Anthropic's coding agent, desktop workflows, agentic programming features, pricing changes, and real-world engineering use cases.
Anthropic appears to have removed Claude Code access from its $20 Pro tier, pushing users toward Max plans starting at $100 a month. The change surfaced via an updated pricing page, with no public announcement attached.
Anthropic has rolled out a redesigned Claude Code desktop app focused on managing multiple agent sessions at once, with a new sidebar, in-app tools, and a workspace built for parallel coding work.
Anthropic has introduced Routines for Claude Code in research preview, letting teams configure repeatable automations that run on schedules, API calls, and GitHub events without depending on a local machine.
Frustration with Claude Code's slowdowns, permission friction, and uneven performance is pushing more developers on X to talk openly about switching to OpenAI Codex and GPT-5.4 for day-to-day coding work.
Shopify has launched an AI Toolkit that lets agents such as Claude Code, Cursor, and VS Code connect directly to store operations, pushing agentic commerce closer to real merchant workflows.
A builder has open-sourced Career-Ops, a Claude Code-powered job search system that evaluated 700-plus roles, generated tailored resumes, and reportedly helped land a Head of Applied AI job.
Anthropic is separating OpenClaw and other third-party harness usage from Claude Code subscriptions, forcing affected developers onto pay-as-you-go billing and adding fresh tension to the fast-growing AI coding tools market.
A 60MB source-map file included in Claude Code v2.1.88 exposed 1,906 proprietary TypeScript source files on the public npm registry — the same packaging oversight that struck Anthropic in February 2025.
JustPaid's CTO replaced most of his dev workflow with seven AI agents running on OpenClaw and Anthropic's Claude Code — delivering 10 major features in a month and training a new human hire almost entirely through AI.
Anthropic's new 'auto mode' for Claude Code lets the AI decide which actions to take without waiting for human approval, using an AI safety layer to filter risky behavior in real time.