permission modes
18 articles about permission modes in AI news
Claude Code's New Auto Mode: Run Commands Without Constant Permission Prompts
Claude Code's new Auto Mode uses a safety classifier to autonomously execute safe actions while blocking risky ones, eliminating constant permission prompts for routine tasks.
Claude Code's Architecture Revealed
An analysis of Claude Code's source code shows its core is a simple loop, but its power comes from systems like a 5-layer compaction pipeline and a 7-mode permission system, which developers can leverage for better performance.
Claude Code v2.1.101: /team-onboarding
Claude Code v2.1.101 introduces practical features like team onboarding generation and fixes long-standing issues with session resumption and tool permissions.
Stop Wasting Your CLAUDE.md Instruction Budget — Here's What Actually Works
Your CLAUDE.md has a limited instruction budget. Stop filling it with platitudes and obvious stack info. Focus on project-specific failure modes and safety guards.
Claude Code Plan Mode: How to Catch Wrong Assumptions Before They Become
Claude Code plan mode uses Shift+Tab or /plan to enforce read-only exploration before edits. It catches wrong approaches on 71% of cross-file refactors, saving hours of diff archaeology.
JetBrains IDE Now Supports Codex Agent and MCP Server Management — Here's
JetBrains adds Codex agent, MCP server management, and approval controls. Claude Code users should compare MCP management UX and consider hooks for CLI workflows.
Never Let the LLM Write the Joins
This article details a two-phase text-to-SQL pipeline: Phase A deterministically plans (intent, entity resolution, joins, RBAC) and Phase B executes with bounded LLM calls. The subject graph caches entity mappings lazily, and security is enforced before the model sees any schema.
Dual-Track Development: How Claude Code Teams Ship 3x Faster with
Adopt a dual-track operating model: use Claude Code for fast exploration (2-hour limit) and production exploitation with CLAUDE.md guardrails to ship 3x faster.
Claude Code Reverse-Engineered: 98.4% of Codebase is Operational Harness
A reverse-engineering analysis of Claude Code reveals only 1.6% of its codebase is AI decision logic, with the rest being operational infrastructure. This challenges current agent design paradigms by prioritizing a robust deterministic harness over complex model routing.
Multi-User LLM Agents Struggle: Gemini 3 Pro Scores 85.6% on Muses-Bench
A new benchmark reveals LLMs struggle with multi-user scenarios where agents face conflicting instructions. Gemini 3 Pro leads but only achieves 85.6% average, with privacy-utility tradeoffs proving particularly difficult.
Claude Code's OAuth API Key Issue: What Happened and How to Prepare for Next Time
Claude Code's recent OAuth API key expiration incident highlights the importance of monitoring service status and having fallback workflows.
How a 12-Hour Autonomous Claude Code Loop Built a Full-Stack Dog Tracker
A developer's autonomous Claude Code system built a sophisticated dog tracking application with 67K lines of code across 133 sessions, showcasing the potential of fully automated build pipelines.
Genspark Raises $385M at $1.6B Valuation, Scales AI Agent Platform After Strong Japan Traction
Genspark has raised $385 million at a $1.6 billion valuation to scale its AI Agent platform. The funding follows strong user engagement in Japan and will accelerate the commercialization of its 'AI Workspace' for enterprises.
Overnight CLI: Train Claude Code on Your Own Chat History to Work While You Sleep
Overnight is a new open-source CLI that analyzes your Claude Code conversations to build a personal coding profile, then predicts and executes your next steps autonomously.
The Claude Code Cheat Sheet: Master the 10 Commands That Matter
Stop memorizing 50+ commands. This cheat sheet prioritizes the 10 slash commands and shortcuts you'll use daily to work faster and smarter.
How to Audit Your CLAUDE.md to Prevent 'Ghost File' Security Risks
A security researcher demonstrated how vague CLAUDE.md instructions can create hidden 'ghost files'—here's how to audit your prompts to prevent this.
OpenDev Paper Formalizes the Architecture for Next-Generation Terminal AI Coding Agents
A comprehensive 81-page research paper introduces OpenDev, a systematic framework for building terminal-based AI coding agents. The work details specialized model routing, dual-agent architectures, and safety controls that address reliability challenges in autonomous coding systems.
Anthropic's Accidental Code Release: Inside the Claude Code CLI That Wasn't Meant to Be Seen
Anthropic's Claude Agent SDK inadvertently includes the entire minified Claude Code CLI executable, revealing the inner workings of their AI coding assistant. The 13,800-line bundled JavaScript file contains everything from agent orchestration to UI rendering, raising questions about security and transparency in AI tooling.