Claude Code Auto Mode: Safer Alternative to Skipping Permissions
What Auto Mode Does
Auto mode provides a middle path between Claude Code's default conservative permissions (which require approval for every file write and bash command) and the risky --dangerously-skip-permissions flag. It lets you run longer tasks with fewer interruptions while introducing less risk than skipping all permissions.
How It Works
Before each tool call runs, a classifier reviews it for potentially destructive actions like mass deleting files, sensitive data exfiltration, or malicious code execution. Actions deemed safe proceed automatically, while risky ones get blocked, redirecting Claude to take a different approach. If Claude insists on taking actions that are continually blocked, it eventually triggers a permission prompt to the user.
Limitations and Considerations
Auto mode reduces risk compared to --dangerously-skip-permissions but doesn't eliminate it entirely. The classifier may still allow some risky actions if user intent is ambiguous or if Claude lacks enough context about your environment. It may also occasionally block benign actions. Auto mode may have a small impact on token consumption, cost, and latency for tool calls.
Getting Started
Auto mode is available in Claude Code as a research preview for Claude Team users today, with rollout to Enterprise and API users coming soon. It works with both Claude Sonnet 4.6 and Opus 4.6.
For developers: Run claude --enable-auto-mode to enable auto mode, then cycle to it with Shift+Tab. On Desktop and in the VS Code extension, first toggle auto mode on in Settings → Claude Code, then select it from the permission mode drop-down in a session.
For admins: Auto mode will soon be available for all Claude Code users on Enterprise, Team, and Claude API plans. To disable it for the CLI and VS Code extension, set "disableAutoMode": "disable" in your managed settings. Auto mode is disabled by default on the Claude desktop app, and can be toggled on using Organization Settings → Claude Code.
📖 Read the full source: HN AI Agents
👀 See Also
Knowledge Raven: A Searchable Knowledge Base Plugin for Claude
Knowledge Raven is a tool that lets Claude search your documents from sources like Confluence, Notion, Google Drive, Dropbox, and GitHub via a Claude Desktop plugin or MCP server, providing semantic search, keyword search, and full document retrieval.
agentcache: Python Library for Multi-Agent LLM Prefix Caching
agentcache is a Python library that enables multi-agent LLM frameworks to share cached prompt prefixes, achieving up to 76% cache hit rates and cutting inference time by more than half in tests with GPT-4o-mini.
JetBrains Introduces Plugin for Modern Go Code with AI Agents Junie and Claude Code
JetBrains has released a plugin for AI agents Junie and Claude Code, enhancing their ability to generate modern Go code by adhering to the latest Go features and best practices.
Scalpel v2.0: Codebase Scanner and AI Agent Orchestrator
Scalpel v2.0 is an open-source tool that scans codebases across 12 dimensions and assembles custom AI agent teams. It includes a pure bash scanner that runs without AI tokens and works with Claude Code, Codex, Gemini, Cursor, Windsurf, Aider, and OpenCode.