Claude Code 2.1.330: scheduled tasks run for 30 days, risky rm commands ask first, and enterprise sign-in arrives

Claude Code 2.1.330 extends scheduled tasks and /loop from 7 to 30 days, makes more destructive rm commands ask for approval, and adds sign-in for organisations managed in Anthropic's Enterprise Admin Console.

On 20 November 2026 Anthropic released Claude Code 2.1.330. Per the Claude Code changelog, three changes stand out for anyone commissioning software built with AI coding tools.

Longer-running automation. Scheduled tasks and /loop now run for up to 30 days instead of 7, for as long as their session keeps running. Recurring jobs such as daily checks or reports no longer need restarting each week.

More guardrails on deletion. More rm (file deletion) commands aimed at the root, the home folder, a top-level folder or the working folder now ask for approval, or are refused where nobody can answer. That matters most for unattended sessions.

Enterprise sign-in. After claude auth login, Claude Code can sign in to organisations managed in Anthropic’s Enterprise Admin Console. It then applies the organisation’s settings and uses its cloud provider or gateway.

Also in the release

Why it matters

Two themes repeat across recent releases: AI tools are being left to run longer on their own, and vendors are adding safeguards for that. A tool that works unattended for a month needs clear limits on what it can delete or change, and organisation-level control over who signs in and where the work runs.

So what

If a supplier uses AI coding tools on your product, ask what runs unattended, what it is allowed to change, and who approves destructive actions. Our AI-assisted development approach keeps a named engineer accountable for every change. For a product built to your needs, see custom software development, or start a project.

← All research

More research.

MAI Code 2 and MAI Code 2 Flash arrive in GitHub Copilot, including a model for free-plan users

GitHub has added Microsoft's MAI Code 2 and MAI Code 2 Flash to Copilot across editors, the CLI, the cloud agent and mobile, with administrators able to control access through model policy.

Read ›

GitHub Copilot team customizations are generally available: set default agent plugins for a whole team

GitHub has made team customizations generally available, so team maintainers and organisation owners can set approved Copilot agent plugins as defaults for every member of a team.

Read ›

OpenAI's GPT-6.2 Astra and Sol are generally available in GitHub Copilot, with a code review focus

GitHub made OpenAI's GPT-6.2 Astra and GPT-6.2 Sol generally available in Copilot for agentic coding and code review. GitHub reports early tests catching more real issues.

Read ›

Copilot code review adds adaptive effort and secret detection in public preview

GitHub's Copilot code review can now choose Lite, Balanced or Max effort per pull request and flag exposed secrets, both in public preview. Azure DevOps support is generally available.

Read ›

Claude Code 2.1.329: /code-review now covers the whole branch, and saved scheduled tasks need rescheduling

Claude Code 2.1.329 makes /code-review review the whole branch against the default branch and adds fixes for Code Mode and sign-in. Saved scheduled tasks mostly need setting up again.

Read ›

GitHub Copilot adds Supabase, Webflow, Wix and five more connectors in public preview

GitHub Copilot now connects to eight more services, including Supabase, Webflow, Wix and Mixpanel, through verified MCP connectors in public preview. They join more than 25 existing ones.

Read ›

Start a project

Building with AI? Let's talk.

Tell us what you are building. We'll give you an honest view of the right approach.

Start a projectSee our work