Managing Claude Code, Codex, and Gemini CLI with Homebrew and mise

To simplify setup across multiple Macs, I migrated Codex CLI and Gemini CLI to Homebrew and Claude Code to mise's install script.

A Tour of Anthropic's 17 Official Skills — What the anthropics/skills Repo Can Do

Anthropic's official Agent Skills repository, anthropics/skills, ships 17 skills as of July 2026. From docx, pdf, pptx, and xlsx office-file manipulation to design skills like algorithmic-art and frontend-design, to developer tooling like mcp-builder and skill-creator, this article summarizes each SKILL.md across five categories.

Building a Workflow to Backdate GitHub Releases with Claude Code

Forgetting to create release notes is a common developer struggle. This article introduces a workflow that uses Claude Code to automatically generate GitHub releases from past PR history. We explain the specific steps and know-how that allowed us to organize 7 months of changelog in just a few hours.

How to Switch from Anthropic API Key to Claude Pro/Max/Team Subscription in Claude Code

Learn how to easily switch the authentication method in Claude Code from API key to Claude Pro/Max/Team subscription accounts.

Migrating Claude Code from npm Global Install to Native Install

Claude Code has migrated from npm to native installer. This guide explains how to resolve the shim priority issue for asdf users and properly migrate to the native version.

Cost Estimation for Claude Code on the Team Plan

Claude Code's Team plan has seat types and minimum seat requirements that can make costs hard to predict. Here's a breakdown of monthly costs by team size.

Letting Claude Drive Your Browser with Claude in Chrome — Setup and Caveats After the Paid-Plan Rollout

Claude in Chrome puts Claude in the Chrome side panel, watching the current tab and doing the clicking, typing, form filling, and cross-tab work for you. Announced as a Max-only research preview in August 2025, it is now on every paid plan as of August 2026. This is a hands-on note on getting it running, on the shape of tasks it handles well versus the ones that will bite you, and on how the permission model actually splits between you, Anthropic, and your org admin.

How to Get Audit Logs on Claude Team Plan Without Upgrading to Enterprise

Claude Team plan lacks audit log functionality. Rather than upgrading to Enterprise, you can build equivalent visibility by combining API gateways, browser monitoring, and CASB/DLP controls. This post covers specific tool choices and configuration examples for each layer.

Inviting gmail.com / outlook.com Members to Claude Team Plan — Add Public Email Domains to Allowed Domains

Ever been blocked by Claude Team's domain restriction when trying to invite someone who only has a personal Gmail address? You can simply add gmail.com to the allowed email domains. Contractors and individual partners can then be invited normally. Here's the tip, plus what to watch for when allowing a public email domain.

CLI Agent License Comparison and Commercial Use Guide - Claude Code, Codex, Gemini CLI

License investigation results for embedding CLI Agents into your product. Explains the differences between Claude Code (proprietary) and Codex/Gemini CLI (Apache 2.0), along with commercial use considerations.

Attended Code w/ Claude Extended in Tokyo

Code w/ Claude Extended, a global series of developer events centered on Claude, came to Tokyo. I was able to attend the keynote by Boris Cherny and a tour of Anthropic's office, but had to leave before the afternoon sessions due to hosting another event. Even in that short time, the conversations I had with the team and the questions raised in the keynote shifted how I think about AI-driven development in practice.

HTTP 400 in Hermes Agent After Switching to Claude — Third-Party Apps Now Draw From Extra Usage

Switching Hermes Agent from OpenAI to Claude returned `HTTP 400: Third-party apps now draw from your extra usage, not your plan limits.` The error text says third-party apps consume extra usage credits, while Anthropic's help article says that switch is paused, so the message and the documented state disagree. Here is how I read the error and what I did about it.

How to Invite Team Members with Different Domain Email Addresses in Claude Team Plan

After signing up for Claude's Team plan, are you confused by the message 'Invited members must have the same domain as you'? This article explains the simple steps to add allowed email domains in admin settings and invite members with multiple domains to your team.

Accelerating Java and Spring Boot Web App Development with AI Coding Agents — Repository Practices for the Claude Code and Codex Era

The biggest lever for running AI coding agents fast on Java and Spring Boot is not model selection but shaping the repository so the AI cannot misread it. Pin the boundaries with Spring Modulith and hexagonal architecture, enforce them mechanically with ArchUnit and Modulith verify in CI, reproduce databases locally with Testcontainers @ServiceConnection, and expose your running app to AI through the Spring AI 1.1 MCP Server Boot Starter. This post lays out the full setup for AI-native Java and Spring Boot development.

Comparing Multi-Platform Strategies: Claude Code, Codex, and Gemini

The three major AI coding tool providers, OpenAI Codex, Claude Code, and Google Gemini, have each solved the multi-platform problem differently. Codex uses a bidirectional JSON-RPC protocol (App Server), Claude Code exposes its harness as a library (Agent SDK), and Google fields three separate products along an autonomy spectrum. This post compares their approaches and extracts patterns for designing your own multi-platform product.

Why I Quit Pomodoro in the AI Era - Let AI Run on Autopilot While Humans Rest

25 minutes on, 5 minutes off. I quit Pomodoro after years of faithful practice. When AI agents can work autonomously for hours, a fixed 25-minute timer makes no sense. My new rhythm: let AI work, and let the human rest.