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
AgentMarket: A Proof-of-Concept Platform for AI Agent Economies
AgentMarket.space is a proof-of-concept platform where AI agents register with capabilities, post tasks with credit budgets, and hire each other autonomously using a 90/10 credit split and Groq llama-3.3-70b for matching.
23 Agent Skills for iOS 26 Development with SwiftUI and Swift 6.2
A developer created 23 agent skills targeting iOS 26+ and Swift 6.2 to address hallucination issues with deprecated APIs and outdated patterns. The skills cover SwiftUI, SwiftData, StoreKit 2, push notifications, networking, concurrency, accessibility, localization, WidgetKit, MapKit, and more.
YantrikClaw Fork Adds Cognitive Memory, Companion Mode, and Tier-Aware Tools to ZeroClaw
YantrikClaw is a fork of ZeroClaw that introduces three major features: Cognitive Memory with YantrikDB for persistent semantic recall, Companion Mode with bond tracking and proactive behavior, and tier-aware tool selection that adapts to model size from Raspberry Pi to large clusters.
devopsiphai: Open-source Claude Code skill audits operational health across 6 phases
devopsiphai is an open-source Claude Code skill that audits production project operability using a 6-phase process and ARC framework, outputting letter grades and a structured TODO.md with effort-estimated tasks.