Articles
The parts the quickstart guides leave out. Why projects stall, what context windows really do to you, and what has to be true before strangers can use your app.
Claude Code Agent Teams Still Experimental After 56 Fixes
Claude Code agent teams run several sessions that message each other. How to turn them on in 2026, what they cost, and the side effects most guides miss.
Getting StartedClaude Code Plan Mode Cost 36% More on a Small Task
Claude Code plan mode reads and proposes before it edits. How to turn it on in 2026, what still runs, and our test of when planning pays off.
Build NotesEverything Claude Code Is Now ECC, With 311 Skills Inside
Everything Claude Code, now ECC, packs 311 skills, 71 agents and 27 hooks. What is in the repo, what it costs your context, and how to install just what you need.
Getting StartedIs Claude Code Free? No, but 4 Routes Cost Almost Nothing
Claude Code is free to install but not free to run. The free Claude plan leaves it out. Four real ways to use it for little or nothing, and the trap to skip.
Getting StartedBase44 Review, Fast to a Demo and Slow to a Real App
Base44 builds a working app with login and a database from one prompt. Where it stalls, what the code export really gives you, its security record and the reviews.
Build Notes4 Ways to Use Claude Code With GitHub, and Undo Mistakes
Connect Claude Code to GitHub four ways, from plain git to @claude in pull requests and cloud sessions. Setup, real costs, and how to undo a bad change.
Build NotesSteer Claude Code From Your Phone With Remote Control
Claude Code Remote Control lets your phone drive a session running on your own computer. Setup, server mode, push alerts, safety and the errors that block it.
Getting StartedOpenCode vs Claude Code, and What the Free Agent Costs
OpenCode is free and open source, Claude Code is $20 a month and up. Compare models, real costs, safety defaults and the Claude login rule before you switch.
Getting StartedHow to Use Claude Code in 9 Steps, Even If You Can't Code
How to use Claude Code from the first prompt. Pick a door, start in plan mode, give it a check to run, save with git, and the keys that keep a session on track.
Build NotesClaude Code Skills Explained, Plus 7 to Install First
Claude Code skills are SKILL.md files that load only when needed. What they are, where they live, the 7 we would add first, and how to vet one before you trust it.
Getting StartedBase44 Pricing Is $0 to $200 a Month, Paid in Credits
Base44 costs $0, $20, $50, $100 or $200 a month, 20% less yearly. What each credit buys, what a small app really burns, and the limits that catch new builders.
Getting StartedCursor vs Claude Code Compared After Cursor Joined SpaceX
Cursor vs Claude Code in October 2026. Cursor now bills Claude at API rates. Current plans, models and limits, plus our own token log priced both ways.
Getting StartedCodex vs Claude Code Compared on Price, Limits and Safety
Codex vs Claude Code in October 2026. Current plans, published limits, API rates, sandbox defaults and our own 24 day usage log, so you can pick the right agent.
Getting StartedHow to Install Claude Code on Mac, Windows and Linux
Install Claude Code with one command on Mac, Windows or Linux, sign in, and fix the errors that stop most installs, from PATH to 403s and npm permissions.
Getting StartedClaude Code Pricing Explained for Pro, Max and the API
Claude Code costs $20 a month on Pro, $100 or $200 on Max, or pay per token on the API. Current prices, limits, a worked cost example and how to pick.
FundamentalsIs Vibe Coding Bad? What the Evidence Says
Vibe coding is not bad for prototypes and personal tools. It is bad when unread AI code holds other people's data. The studies and breaches show why.
FundamentalsVibe Coding Best Practices for Apps That Ship
Vibe coding best practices that keep an AI built app moving past the demo. Twelve habits for planning, prompting, testing and shipping safely.
Wellbeing
Two Different Worries Both Called AI Addiction
One is leaning on a chatbot for company. The other is leaning on it for thinking. The evidence differs for each, and so does what to do about it.
Build Notes
The View That Ignored Row Level Security
Row level security was on and every policy was correct. A plain view runs as its owner and never checks them, so 2,028 rows of invoice totals reached the public key.
Build Notes
What Mindsmith Changed About Our Learning Pages
An afternoon in a purpose built eLearning tool changed how we structure our own training pages. Thirteen long ones became 189 short ones.
Build Notes
Two Repair Platforms, Neither One Open Source
Two AI repair platforms were handed to us as open source. Neither is. Running their funnels with a real car still rewrote how our diagnostic step works.
Fundamentals
Why Vibe-Coded Projects Stall at 80%
The first weekend produces a working app. Month two produces nothing. Five mechanisms cause this, and the fix depends on which one has you.
Fundamentals
What Is Vibe Coding, Really?
The term went from a tweet to an industry in under two years. What it actually means, what it doesn't, and why the definition matters more than it sounds.
Fundamentals
The Context Problem: Why Your AI Forgets Your Codebase
The single most important technical concept in vibe coding. Understand this and half your frustration becomes predictable and fixable.
Shipping
Shipping a Vibe-Coded App to Production
The checklist between "it works on my screen" and "strangers can use this safely." Most of it is not optional, and none of it requires you to stop using AI.
Getting Started
MCP Explained for Vibe Coders
Model Context Protocol is the difference between an AI that writes code and one that can check the code works. This is what it is without the spec-speak.
Getting Started
Choosing Your First AI Coding Tool
There are two dozen options and most comparisons are marketing. Pick based on what you're actually trying to do, not on the hype.