#claude_code

What jumps out to me is not the 200KB threshold itself, but the fact that the “obvious” optimization turned out to be the wrong one once the project got big enough. That feels very real. We all reach for `--incremental` because it sounds like the kind of thing that should help an agent loop stay tight. And for a while it probably does. But this article is a reminder that cache files are not free, and in a hook that runs constantly, the cost of loading state can quietly eat the benefit of reusing

What struck me first is how much of this release is about making Claude Code stop tripping over itself. That’s not glamorous, but it’s the kind of work that tells you where the product actually is: past the “look, it can code” phase and deep into “please don’t corrupt my session, my plugin install, or my prompt cache.” The obvious headline in this entry is AGENTS.md support. I’d actually try that immediately, because it’s a small but telling quality-of-life change: if a project doesn’t have CLAU

What jumps out to me is not that Unity has a Claude Code plugin, but that it exists as a package of opinions. That feels like the real product here. The useful part is probably not “AI can now talk to Unity,” which was inevitable, but that Unity is trying to bottle up the platform knowledge that generic coding agents keep missing. I buy the premise. Anyone who has watched an LLM “help” with a game project knows the failure mode: it picks the nearest familiar pattern instead of the project’s actu

What jumped out at me is how ordinary the underlying problem is, and how much ceremony the author builds around it. The basic complaint is fair: terminal output is a lousy medium for anything nuanced, and once an agent starts giving you multi-step reasoning, test results, or implementation notes, plain text gets tiring fast. But I’m not convinced the leap from “terminal text is awkward” to “HTML files fix this” is as universal as the article makes it sound. If I were doing this day to day, I’d p

What surprised me is not that Claude Code spends tokens on background stuff. That part is obvious once you think about it. What surprised me is how much of the advice here is basically, “audit the defaults you forgot you enabled months ago.” That’s less of a Claude problem than a reminder that dev tools quietly accumulate context like a junk drawer. The article’s real value is the nudge to stop blaming your prompts for every usage spike. If you’re hitting limits fast, the first thing I’d check i

This is one of those features that sounds small until you’ve spent an afternoon juggling three Claude Code sessions and manually copying context between them like it’s 2014. The interesting part to me is not “messaging” as a concept. It’s that Anthropic is acknowledging a very real workflow: people are already using Claude Code as a parallel worker, not a single linear assistant. What I like here is the restraint. The messages are summaries, not a way to smuggle entire histories or files between

What makes this story interesting from a Claude Code perspective is not the medicine itself, but the workflow: a user takes a messy real-world artifact, a DICOM MRI export, and asks Claude to reason over it with code execution, package installs, and an arbitration pass. That is exactly the kind of task where Claude Code can feel magical and unnerving at the same time. The blog post captures both sides very honestly. The author had right shoulder pain and was sent for an MRI by an orthopedist. Th

Claude Codeには、公式ドキュメントに載っていない設定や拡張ポイントがかなりある hooksは単なる「前後処理」ではなく、実行中のコマンドを書き換えたり、権限判定を差し込んだりできる `once`、`async`、`asyncRewake` など、フックの動きを変える隠し気味の設定がある Skillsにはモデル指定や実行強度、スキル中だけ有効なhooksなど、かなり柔軟な機能がある Custom agentsには永続メモリのような仕組みがあり、使い方次第で“学習するエージェント”っぽいものが作れる ただし、こうした機能は未文書化だったり実験的だったりするので、将来の版で変わる可能性が高い この記事は、Claude Code のソースコードを読んだら、公式ドキュメントに書かれていない設定がいろいろ見つかった、という内容です。 率直に言うと、こういう“中身を覗いた人だけが知っている小技集”は、かなりワクワクします。AIツールって、見た目はシンプルでも、裏側には結構な仕掛けが隠れているんですよね。 元記事の筆者 André Figueira は、Claude Code のソー

Claude Codeは、ただプロンプトを投げる道具ではなく、継続的に育てるエージェントとして使うと強い 重要なのは、Claudeに自分で検証させる仕組みを作ること `.claude/` 配下には、`CLAUDE.md`、`CLAUDE.local.md`、Skills、subagents、rules などの役割分担された設定がある `CLAUDE.md` は長く書くより、ミスを防ぐための短いルール集にするのがコツ `CLAUDE.local.md` は、自分専用の改善メモとして使うと日々の作業がかなり楽になる Skills は「何でもできるAI」を「特定作業に強いAI」へ変える仕組み subagents、plugins、MCP、`/goal` など、あまり使われていない機能にもかなり実用的なものがある Anthropicチーム自身のワークフローには、短く、厳密で、改善が積み重なる設計がはっきり見える 元記事は、Claude Codeを“ちょっと便利なAI補助”で終わらせず、**毎日使う前提の開発ツールとしてどう育てるか*

For Claude and Claude Code users, this is one of those quietly important infrastructure stories: Anthropic is not just shipping model updates, it’s actively reshaping access to make the product usable at scale. If you’ve hit usage caps, peak-hour throttling, or watched multi-agent workflows chew through your allowance, this announcement matters more than most model-launch headlines. Anthropic announced a deal with SpaceX to use the full compute capacity of SpaceX’s data center in Memphis, Tennes

Claude Code’s new routines feature is interesting because it moves from “helpful coding assistant” territory into scheduled, event-driven automation. For Claude / Claude Code developers, that’s a meaningful shift: you can now package prompts, repositories, connectors, and triggers into something that runs in Anthropic-managed cloud infrastructure without your laptop open. Routines are in research preview, so behavior, limits, and the API surface may change. A routine is a saved Claude Code confi