Anthropic trims action approval loop, lets Claude Code make the call

Sinisa Markovic, Senior Staff Writer, Help Net Security March 25, 2026 Share Anthropic trims action approval loop, lets Claude Code make the call Auto mode is a new permissions feature in the Claude Code system that allows the AI to make approval decisions on a user’s behalf while safeguards review actions before execution. The feature is available on Team plans and requires administrator approval before use, with support for Enterprise and API users expected soon. It runs on newer models such as Claude Sonnet 4.6 and Claude Opus 4.6, and excludes older versions and third party platforms. By default, Claude Code applies strict permission controls, requiring user approval for each file write and shell command, a design that limits unattended work and can interrupt longer tasks. Some developers bypass these checks by disabling permission controls, though this approach can lead to harmful or destructive outcomes and is generally limited to isolated environments. “Auto mode is a middle path that lets you run longer tasks with fewer interruptions while introducing less risk than skipping all permissions,” the company said in a blog post. Actions considered safe proceed without user input, while those flagged as risky are blocked and redirected. If repeated attempts continue to trigger blocks, the system escalates the request and prompts the user for approval. Anthropic notes the classifier trusts the local working directory and configured remotes within a git repository, while treating all other resources, including company source control systems, cloud storage, and internal services, as external until they are explicitly defined as trusted. If auto mode blocks routine actions such as pushing to an organization’s repository or writing to a company storage bucket, it may be because the classifier does not recognize those resources as trusted. Administrators can address this by adding approved infrastructure through configuration settings. The company added that auto mode may have a small impact on token consumption, cost, and latency for tool calls. Over the past few months, Anthropic has released several updates focused on advancing the capabilities of Claude. More about Anthropic Claude Code code analysis Share