Welcome to HowToShipIt — practical how-to guides for developers: code, AI tools, and servers, explained step by step.

Best AI Coding Model in 2026: What the Benchmarks Actually Say

best AI coding model 2026 benchmark leaderboard illustration

Last verified: October 8, 2026. Benchmark scores change fast in this space — this post is date-stamped so you know exactly what it reflects. Ask ten developers which is the best AI coding model in 2026 and you will get eleven answers, most of them based on vibes. Ask the leaderboards instead and you get … Read more

How to Use Together Link: Run Open Models in Claude Code Without Changing Your Workflow (2026)

Together Link: run open models like Kimi K3 and GLM 5.3 inside Claude Code

If your Claude Code usage has started to feel like a second AWS bill, you’re not alone. Most developers route every single prompt — the one-line typo fix and the full module rewrite — through the same expensive frontier model, because changing that routing meant changing your tools. Together Link is Together AI’s answer to … Read more

How to Use AGENTS.md in Any Repo: A Practical Guide for 2026

How to use AGENTS.md files in any repo - practical guide for AI coding agents

A year ago, every AI coding tool wanted its own instruction file. Cursor had .cursorrules, Claude Code had CLAUDE.md, Copilot had its own thing. If you worked with more than one agent, you maintained the same instructions twice and watched them drift out of sync. That mess has a fix now. AGENTS.md is a single … Read more

Claude Code Hooks Explained: 7 Practical Examples You Can Copy (2026)

Claude Code hooks workflow illustration: gears, plug and circuit lines showing how PreToolUse, PostToolUse and Stop hooks automate coding sessions

Claude Code hooks are one of the most powerful features in the AI coding assistant — and one of the least used. A hook is a shell command (or an LLM prompt, a subagent, or an HTTP endpoint) that runs automatically at a specific point in Claude Code’s lifecycle: before a tool executes, after a … Read more

Cursor Rules: How to Write and Share Configs That Actually Work

Cursor rules: shareable .mdc configs that actually work

You have probably had this moment: you spend twenty minutes explaining your stack, your conventions, and your non-negotiables to Cursor’s Agent, it generates something great, and then the next day — or the next tab — you start all over again. Cursor rules are how you stop repeating yourself. They are persistent, project-level instructions that … Read more

How to Run Ollama: Install, Models, and API in 30 Minutes

How to run Ollama locally: install Ollama and run LLMs on your machine

If you want to know how to run Ollama on your own machine, this guide gets you there in about 30 minutes: install, your first model, chat in the terminal, custom models with Modelfiles, and calling the API from Python. No API keys, no usage bills, no sending your code to someone else’s servers. Ollama … Read more

How to Write a CLAUDE.md File That Makes Claude Code 10x Better

How to write claude.md

Why a Good CLAUDE.md Changes Everything If you have ever retyped the same instructions into every Claude Code session — “this is a Laravel app, run php artisan test before committing, never touch deployed migrations” — you already understand the problem this file solves. Learning how to write claude.md properly is the highest-leverage thing you … Read more

10 Genuinely Free AI Tools That Are Actually Worth Your Time

Free AI tools for developers

Last verified: October 2026. Free tiers change — sometimes without notice — so treat every limit below as “as of today” and check the linked pricing page before you plan around it. Most “free AI tools for developers” lists are recycled affiliate bait. They promise “100% free,” then every link leads to a 7-day trial … Read more

Claude Code vs Cursor: Which AI Coding Assistant Should You Actually Pay For?

Claude Code vs Cursor comparison

You have $20 a month to spend on an AI coding assistant, and everyone keeps shouting that Claude Code vs Cursor is the fight that matters. Here’s the uncomfortable truth most comparison posts skip: these two tools aren’t really competing. They solve different problems, they bill you differently, and the “right” choice depends on how … Read more