# Notes on Claude Code, AI agents and the web.

Hands-on posts on Claude Code, MCP, AI agents, Next.js and TypeScript, plus honest tool comparisons from shipping software for clients.

RSS: https://alexcloudstar.com/rss.xml

- [Claude Code GitHub Actions: Setup, @claude Mentions and Automatic PR Review](https://alexcloudstar.com/blog/claude-code-github-actions-2026/): How to connect Claude Code to GitHub: run /install-github-app, mention @claude in issues and pull requests, add an automatic PR review workflow, pick between an API key and a subscription token, cap the cost, and lock down what it can touch. Also where the managed Code Review product fits. Checked against the official docs in October 2026. (Oct 2026)
- [Claude Code Usage Limits: How the Weekly Limit, 5-Hour Window and Reset Times Work](https://alexcloudstar.com/blog/claude-code-usage-limits-2026/): How Claude Code usage limits work on Pro and Max: the weekly limit, the rolling 5-hour session window, when each one resets, the shared pool with claude.ai, what burns through them fastest, how to check usage with /usage, and what to do when you hit the limit. Checked against the official docs in October 2026. (Oct 2026)
- [Claude Code Plan Mode: How It Works, How to Use It, and When to Skip It](https://alexcloudstar.com/blog/claude-code-plan-mode-2026/): How Claude Code plan mode works: the four ways to turn it on, what Claude can and cannot do while planning, the approval menu, editing the plan with Ctrl+G, settings that change its behavior, and the cases where it is not worth the minute. Checked against the official docs in October 2026. (Oct 2026)
- [Claude Code Alternatives in 2026: 8 Tools Worth Switching To, and When Not To](https://alexcloudstar.com/blog/claude-code-alternatives-2026/): Eight real Claude Code alternatives compared on price, models, open source status and who each one fits: OpenCode, Codex, Cursor, GitHub Copilot CLI, Gemini CLI and Antigravity CLI, Aider, Cline and Kilo Code. Checked against official docs and pricing pages in October 2026. (Oct 2026)
- [Claude Code Commands Cheat Sheet: Every Slash Command, Shortcut and CLI Flag](https://alexcloudstar.com/blog/claude-code-commands-cheat-sheet-2026/): Every Claude Code command worth knowing in one place: slash commands grouped by task, keyboard shortcuts for macOS and Windows, CLI commands and flags, custom commands, and which old commands were removed. Checked against the official docs in October 2026. (Oct 2026)
- [I Shipped 32,784 Lines of Code in 2 Days With Claude Code. Here Is What the Number Hides](https://alexcloudstar.com/blog/claude-code-workflow-32784-lines-2-days-2026/): I rebuilt my whole site on Next.js 16 with Claude Code in two days: 228 posts rewritten against keyword data, 543 tests, zero broken URLs. The line count is the least interesting part. This is the Claude Code workflow and best practices behind it, the mistakes the agent made, and why deciding what to build is now the slow step. (Oct 2026)
- [Claude Agent SDK: What It Is and How to Build Your First Agent (2026)](https://alexcloudstar.com/blog/claude-agent-sdk-guide-2026/): The Claude Agent SDK is Claude Code as a library. What it is, how it differs from the Messages API and the claude CLI, how to install it, a minimal working agent in TypeScript and Python, and how tools, permissions, MCP servers, subagents and hooks work. (Oct 2026)
- [Claude Code Hooks: Every Event, the Config Format and Five Working Examples](https://alexcloudstar.com/blog/claude-code-hooks-guide-2026/): What Claude Code hooks are, every hook event and when it fires, where to configure them, how exit codes and JSON output work, and five copy-pasteable examples. Checked against the official docs in October 2026. (Oct 2026)
- [Claude Code Subagents: How They Work and How to Build Your Own (2026)](https://alexcloudstar.com/blog/claude-code-subagents-guide-2026/): What Claude Code subagents are, the built-in ones, how to write a custom subagent file, how Claude delegates and runs them in parallel, and when a skill, hook or MCP server is the better tool. (Oct 2026)
- [Claude Code vs Codex: Which AI Coding Agent to Pick in 2026](https://alexcloudstar.com/blog/claude-code-vs-codex-2026/): Claude Code and OpenAI Codex are both CLI-first coding agents with IDE and cloud modes. Here is how they compare on models, pricing, permissions, MCP and config files, checked against the official docs of both vendors on October 23, 2026. (Oct 2026)
- [How to Use Claude Code: A Practical Tutorial From Install to Productive](https://alexcloudstar.com/blog/how-to-use-claude-code-2026/): How to use Claude Code from zero: install it on macOS, Windows or Linux, log in, run your first session, write a CLAUDE.md, learn the slash commands that matter, and avoid the mistakes that waste your usage. (Oct 2026)
- [Claude Code Status Line: Setup, a Working Script, and the Best Tools](https://alexcloudstar.com/blog/claude-code-status-line-guide-2026/): The Claude Code status line is a bar under the prompt that runs any script you give it. Here is how the statusLine setting works, the JSON your script receives, a short bash script that shows model, context, cost and git, and how statusline-pro, ccstatusline and statusline.sh compare. (Oct 2026)
- [Git Worktree Guide: Parallel Branches and Claude Code](https://alexcloudstar.com/blog/git-worktree-guide-2026/): A git worktree gives you a second working directory on another branch, sharing one repository. Here are the commands, how a worktree differs from a branch or a stash, the gotchas that trip people up, and how to run parallel Claude Code sessions in separate worktrees. (Oct 2026)
- [How I Keep My Mac Up to Date With Dotfiles and Ansible](https://alexcloudstar.com/blog/ansible-dotfiles-macos-setup-2026/): My dotfiles repo started as a pile of configs and a stow layout. It is now an Ansible playbook that rebuilds my Mac from a bare install, and updates it on demand. Here is how it works, what Stow could not do, and the gotchas that cost me an afternoon each. (Oct 2026)
- [AI Referral Traffic Converts Better. That Does Not Mean You Should Chase It Blindly.](https://alexcloudstar.com/blog/ai-referral-traffic-conversion-saas-2026/): Traffic from ChatGPT and Perplexity often converts better than ordinary organic search because the buyer arrives with a recommendation. The volume is still tiny, the attribution is incomplete, and the wrong response is to rebuild your whole growth plan around a flattering little chart. (Sep 2026)
- [Stop Letting Browser Agents Improvise Every Click. Use AI to Heal Playwright Instead.](https://alexcloudstar.com/blog/self-healing-playwright-ai-browser-automation-2026/): The best browser agent architecture is usually not an agent driving every step. It is a deterministic Playwright workflow that uses AI only when the page changes or the script fails. That keeps normal runs cheap and debuggable while still giving you a way through the web’s inevitable mess. (Sep 2026)
- [The AI Pull Request Manifest: The One Page That Makes Agent Code Reviewable](https://alexcloudstar.com/blog/ai-agent-pull-request-review-policy-2026/): The worst AI pull request is not a bad diff. It is a diff nobody can explain six weeks later. A short manifest, written before the agent starts, turns review from archaeology into a check against a concrete promise. Here is the format and policy I would put in every repository. (Sep 2026)
- [Claude --dangerously-skip-permissions: What It Does and How to Set Up Permissions Safely](https://alexcloudstar.com/blog/coding-agent-permissions-least-privilege-2026/): What claude --dangerously-skip-permissions actually does, when it is safe to use, and the access ladder and settings.json I would use to keep coding agents useful without handing them your whole machine. (Sep 2026)
- [llms.txt Does Not Get You Cited. Here Is What It Is Actually For.](https://alexcloudstar.com/blog/does-llms-txt-work-ai-visibility-2026/): The most honest answer to "does llms.txt work?" is yes for developer documentation, no for AI-search rankings. I read the crawl data, checked what the answer engines support, and made a list of the work that is worth doing before you ship another text file. (Sep 2026)
- [SaaS SEO With No Traffic: The 90-Day Plan I Would Actually Run](https://alexcloudstar.com/blog/saas-seo-zero-traffic-90-day-plan-2026/): A new SaaS with a few impressions and no signups does not need another AI writer or a pile of backlinks. It needs to know whether the problem is indexing, intent, authority, or conversion. This is the 90-day plan I would run before spending a euro on another SEO tool. (Sep 2026)

- [Older posts](https://alexcloudstar.com/blog/2/)