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
Auto-co: A 50-Line Bash Script That Turns Claude Code Into Autonomous AI Companies
Auto-co is a 50-line bash script that wraps the Claude Code CLI in a loop, allowing it to run autonomously with 14 AI agents playing roles like CEO, engineer, and critic. It has built four products from scratch, including FormReply and Changelog.dev, at a total cost of $268 across 270+ cycles.
Bullshit Benchmark Tests LLM Resistance to Nonsensical Prompts
The Bullshit Benchmark evaluates whether AI models identify and push back on obvious nonsense prompts instead of confidently generating incorrect answers. Results show Claude models perform significantly better than Gemini models at detecting nonsensical questions.
Reverse-Engineered Airtable Internal API Exposed via MCP: 60+ Tools for Claude Code
A developer reverse-engineered Airtable's internal API and built an MCP server with 60+ tools, letting Claude Code and 15+ IDEs control database views, computed fields, and extensions. Already used by 2000+ users, it's free and open source.
Building an Agentic RAG for Obsidian with Claude and an Eval Harness to Detect Hallucinations
A developer built an agentic RAG system over an Obsidian vault to let Claude answer questions from engineering books, then created an eval harness using Claude Sonnet as a judge to detect when the agent was confidently wrong. Rubric iterations improved judge-human agreement from 39% to 94%.