#developer tools

A practical guide to writing CLAUDE.md as a permission contract for AI coding agents, covering tool tiers, hard stops, failure behavior, and MCP server security.

AI is generating more pull requests than humans can review. The fix isn't picking the best AI code review tool — it's combining the right ones.

Gemini CLI shipped subagents in April 2026. Here is an architectural comparison with Claude Code covering orchestration, context capacity, and permission controls.

Claude Code's Monitor tool streams background process output directly into the agent session, replacing polling loops with event-driven reactions that cost nothing during idle periods.

GitHub's new gh skill command brings npm-style package management to AI agent skills for Copilot, Claude Code, Cursor, and Codex — but 36.82% of public skills carry security issues. Here's how to use it safely.

Anthropic has released Claude Opus 4.6 with a 1 million token context window, Agent Teams for parallel coding agents, and the discovery of 500+ zero-day vulnerabilities during testing. Here's a deep dive into what makes this release fundamentally different.

OpenAI has officially launched Codex, a native macOS application that serves as a command center for managing multiple AI coding agents. Here's everything developers need to know about Skills, Automations, pricing, and how it compares to Cursor, Copilot, and Replit.