Claude-Code

Google says its new Android CLI cuts LLM token use by more than 70%. Google also says tasks finish 3x faster. Both numbers come from Google’s own internal tests. Nobody outside Google has published a measurement. So I made one. I installed Android CLI 1.0. I built a real project. I counted every character an AI agent must read. Here is the short answer. The token claim is true. I measured 87%. But the tool only helps with some tasks, not all of them. I also found a bug that matters more than the token number. ...

If you write Kotlin and you pick an AI coding agent based on a benchmark score, you have a problem. Almost every popular benchmark is Python. Your agent might be great at Python and mediocre at Kotlin, and the score would never tell you. JetBrains just shipped a fix: the Kotlin Benchmark, a public leaderboard that scores AI coding agents on real Kotlin work. Here is what it measures, what it does not measure, and what the current results actually say. ...

On August 5, 2026, Meta released a new AI coding agent called Muse Code. It went straight into public beta, aimed at the same developers who use Claude Code and Cursor. (Meta AI Research) I looked at three things: what Muse Code actually does, how it performs against Claude Code, and what its cheapest pricing tier really costs you. Short answer: the low price is real, but it is not free money. Read on for the details. ...

On July 8, 2026, the security firm Wiz published research on a flaw they named GhostApproval. It is not one bug in one tool. It is the same design mistake, made independently, in six different AI coding agents: Amazon Q Developer, Claude Code, Cursor, Augment, Google Antigravity, and Windsurf (Wiz Research, The Hacker News). The trick behind it is over 40 years old. It is called a symlink. Once you understand what a symlink is, the whole story makes sense — and so does why fixing it is harder than it sounds. ...

Anthropic shipped a Claude Security plugin for Claude Code. It runs a team of agents over your repository, hunts for vulnerabilities, and writes a report. “AI finds bugs in your code” is a claim you should be suspicious of. So instead of reading the announcement, I read the plugin’s source. The interesting part is not the scanning. It is that the plugin does not let its own model decide how much to trust the results. ...

Anthropic launched Claude Opus 5 on July 24, 2026. The headline number: it nears Fable 5’s capabilities at half the price. For developers who run Claude every day, that changes the math. This is not a hype recap. Below is what shipped, what it means for your workflow, and how to start using it today. ...

Claude Code is not an editor. It is not an extension. It is a terminal agent that reads your code, writes code, runs commands, and handles git — all from your terminal. When I first tried it, I thought “why would I use a terminal tool when I have Cursor?” After one week, I understood. Claude Code does things that no IDE-based tool can match. Here is my honest review after months of daily use. ...

This is the capstone article. Everything from 14 projects comes together. We started this series with a CLI todo app that took 35 minutes. Then we built REST APIs, Chrome extensions, full-stack blogs, SaaS dashboards, and mobile apps. Each project taught us something about working with Claude Code. Now the question: can we take a real product idea — something that could make money — from concept to deployed, production-ready app in a single working day? ...

Mobile development is hard. Cross-platform mobile development is harder. Kotlin Multiplatform sits in the middle — shared business logic with native UI on each platform. The Gradle configuration alone can take hours. Can Claude handle it? This is the most technically challenging project in the entire series. KMP has expect/actual declarations, platform-specific dependency injection, multiplatform Gradle config, and two completely different UI frameworks (Jetpack Compose for Android, SwiftUI for iOS). ...

Every article so far has used one Claude Code session. One terminal, one conversation, one context. That works for small projects, but what about larger codebases where different parts can be built in parallel? Claude Code supports multiple agents working on the same project. You can have one agent building the backend, another building the frontend, and a third writing tests — all at the same time. This article tests whether multi-agent development actually works. Does it save time? What happens when agents step on each other’s code? How do you coordinate? ...