平沢 岳史| AIでもっとトガれ🔥
3.5K posts

平沢 岳史| AIでもっとトガれ🔥
@taka_start_up
エンジニア7年→東証プライム上場クリエイティブディレクター→AI事業責任者|🚀外注費ゼロ⚡経理もマーケも全部AIにシフト|AIで誰でも作れる時代、作れるだけじゃ埋もれる。自分の強みでトガれ🔥|AIでトガるための🔥売上設計🔥経費削減🔥バイブコーディング講座「AI登竜門」運営、お仕事のご相談はDMから受付中👍


Some of you noticed limits drained faster in Codex, we root caused it to an optimization that we rolled back that had an impact on cache hit rates when compacting across long running sessions. We fixed this and have now reset usage limits for all accounts. Enjoy the weekend.







Claude Code 普通に関数設計が下手だし、かなり丁寧に扱わないと会社の中が高専3年生が書いたみたいなコードで溢れると思うんだけど、なんでみんなそんなに AI コーディングやりたがるんですか

Claude-Mythos-1-preview spotted will be available in Claude Code and Claude Security. here is more detailed images you can see new plans ui too and mythos-1 with adaptive thinking




Claude Code 普通に関数設計が下手だし、かなり丁寧に扱わないと会社の中が高専3年生が書いたみたいなコードで溢れると思うんだけど、なんでみんなそんなに AI コーディングやりたがるんですか






Claude Code isn't a coding tool. (It's a programmable dev environment) Engineers open it, type a prompt, and let it write code. But the real leverage is in the system around the prompt. Here are 12 features that make Claude Code programmable: 𝟭) 𝗖𝗟𝗔𝗨𝗗𝗘.𝗺𝗱: The project's persistent memory. Stack details, conventions, and constraints load automatically at every session start. 𝟮) 𝗥𝘂𝗹𝗲𝘀: Behavioral guardrails beyond 𝗖𝗟𝗔𝗨𝗗𝗘.𝗺𝗱. Project-wide do's and don'ts that apply across sessions and contributors. 𝟯) 𝗦𝗸𝗶𝗹𝗹𝘀: Reusable instruction files stored in .claude/skills/. Write once, and Claude follows them automatically every time the task matches. 𝟰) 𝗛𝗼𝗼𝗸𝘀: Shell scripts that fire on events like PreToolUse and PostToolUse. Auto-lint, run tests, or validate output without manual intervention. 𝟱) 𝗦𝗹𝗮𝘀𝗵 𝗖𝗼𝗺𝗺𝗮𝗻𝗱𝘀: Workflow shortcuts stored in .claude/commands/. Multi-step flows triggered with a single keystroke. 𝟲) 𝗣𝗹𝘂𝗴𝗶𝗻𝘀: Bundles of skills, hooks, commands, and MCP servers packaged into one installable unit. Over 100 official plugins are in the marketplace today. 𝟳) 𝗠𝗖𝗣: Connects Claude to databases, APIs, and external services. This is how it gets real-world access beyond the codebase. 𝟴) 𝗣𝗹𝗮𝗻 𝗠𝗼𝗱𝗲: Claude drafts a step-by-step plan before touching any code. Approve or reject before anything runs. 𝟵) 𝗣𝗲𝗿𝗺𝗶𝘀𝘀𝗶𝗼𝗻𝘀: Whitelist or block specific tools on a per-session basis. Non-negotiable for anything production-facing. 𝟭𝟬) 𝗦𝘂𝗯𝗮𝗴𝗲𝗻𝘁𝘀: Spawn parallel Claude instances that divide and conquer multi-step workflows simultaneously. 𝟭𝟭) 𝗩𝗼𝗶𝗰𝗲 𝗠𝗼𝗱𝗲: Talk to Claude hands-free via /voice. Push-to-talk with the spacebar, and the command goes straight to the input field. 𝟭𝟮) 𝗥𝗲𝘄𝗶𝗻𝗱: Step back to any checkpoint in the session and restart cleanly from that point. Features 1-5 define the environment. 6-7 extend it. 8-9 control it. 10-12 change how it runs. That framing matters because the gap between using Claude Code as a chatbot and using it as a programmable system is enormous. 𝗖𝗟𝗔𝗨𝗗𝗘.𝗺𝗱 + Skills + Hooks alone can automate half the repetitive decisions in a codebase. If you want to go deeper, I wrote a detailed article covering the anatomy of the .claude/ folder, a complete guide to 𝗖𝗟𝗔𝗨𝗗𝗘.𝗺𝗱, hooks, skills, subagents, and permissions, and how to set them all up properly. The article is quoted below.







CODEX LIMITS ARE FIXED!














