Best of Claude Code — February 2026

  1. 1
    Article
    Avatar of daily_updatesdaily.dev Changelog·13w

    A live leaderboard for AI coding tools

    The Arena is a real-time leaderboard on daily.dev that tracks developer mindshare for AI coding agents and LLMs using a custom metric called the D-Index, which combines mention volume and sentiment. It covers tools like Cursor, Claude Code, Copilot, Codex, Windsurf, and LLMs like Claude, GPT, DeepSeek, and Gemini. Five spotlight crowns highlight category leaders including Developer's Choice, Most Loved, Fastest Rising, Most Discussed, and Most Controversial. Rankings refresh every 60 seconds and include sentiment scores, 24h mention volume, momentum indicators, and 7-day sparklines. A live highlights feed surfaces notable developer posts with sentiment context.

  2. 2
    Video
    Avatar of designcourseDesignCourse·13w

    Claude Code Skills are the Future of Frontend

    A demonstration of Claude Code's custom 'skills' feature applied to frontend development, specifically creating a reusable Three.js shader hover effect skill. The author shows how to define a skill that prompts for configuration options (effect type, intensity, animation style) and then applies chromatic aberration, wave, or distortion WebGL effects to gallery images in a vanilla HTML project. The broader argument is that building a library of such reusable AI skills will replace manual Stack Overflow research and become the dominant workflow for frontend developers.

  3. 3
    Article
    Avatar of hnHacker News·13w

    What Claude Code Actually Chooses — Amplifying

    A study of 2,430 Claude Code interactions across real repositories reveals that the AI coding assistant strongly prefers building custom solutions over recommending third-party tools — appearing as the top choice in 12 of 20 categories. When it does pick tools, choices are decisive: GitHub Actions (94%), Stripe (91%), shadcn/ui (90%). Deployment is stack-determined: Vercel for JS, Railway for Python, with traditional cloud providers getting zero primary picks. Significant generational shifts exist between model versions, notably Prisma→Drizzle for JS ORM, Celery→FastAPI BackgroundTasks for Python jobs, and Redis→Custom/DIY for caching in newer models.

  4. 4
    Video
    Avatar of t3dotggTheo - t3․gg·13w

    Delete your CLAUDE.md (and your AGENT.md too)

    A study found that CLAUDE.md and AGENT.md context files used with AI coding agents either marginally improve performance (+4%) when developer-written, or slightly hurt it (-3%) when LLM-generated, while increasing costs by over 20%. The core argument is that modern LLMs are already good at exploring codebases autonomously, so bloated context files distract rather than help. Best practice is to keep these files minimal—only documenting consistent failure patterns the agent exhibits—and to focus instead on improving codebase structure, tests, and tooling. The author also shares unconventional prompting tricks like intentionally misleading agents to steer behavior, and recommends deleting auto-generated init files entirely.

  5. 5
    Video
    Avatar of mattpocockMatt Pocock·13w

    Never Run claude /init

    Running `claude /init` generates a CLAUDE.md file that bloats the agent's system prompt with auto-discovered codebase documentation. This wastes tokens on every request, distracts the agent with irrelevant context, and quickly goes out of date as code changes. Research confirms that unnecessary requirements in context files make tasks harder. Instead, agents should rely on their built-in explore phase to discover context just-in-time. The only content worth putting in CLAUDE.md is truly global, non-obvious setup information (e.g., 'you are on WSL on Windows') — keep it to a minimum and let the file system and source code serve as the real source of truth.

  6. 6
    Article
    Avatar of lnLaravel News·13w

    Chief: Run Claude Code on Large Projects with Task-Based Workflows

    Chief is a CLI tool designed to extend Claude Code's capabilities for large projects by breaking work into discrete tasks. Each task runs in its own context window, avoiding the limitations of a single long-running session. Progress is persisted to disk between runs, allowing work to be stopped and resumed. Chief can be installed via Homebrew or a curl install script.

  7. 7
    Article
    Avatar of elixirstatusElixirStatus·12w

    150,000 Lines of Vibe Coded Elixir: The Good, The Bad, and The Ugly

    A founder shares lessons from building 150,000 lines of production Elixir entirely with AI (Claude Code). Elixir's small, terse, immutable nature makes it well-suited for AI coding agents—fewer decisions, fewer tokens, fewer hallucinations. The Tidewave MCP tool extends agent capabilities with live logs and DB access. Key downsides: AI defaults to imperative, defensive Ruby-style code rather than idiomatic Elixir; it cannot debug OTP/async issues or understand Ecto sandbox transaction isolation, causing it to chase red herrings in tests. Architecture decisions still require human oversight. Despite the friction, productivity gains are described as massive.

  8. 8
    Article
    Avatar of vigetViget·13w

    Pointless explorations of Obsidian & Claude Code

    A three-person team at Viget used their internal hackathon to explore integrating Claude Code with Obsidian vaults for knowledge work automation. They built an Obsidian plugin that auto-summarizes web clips (including YouTube transcripts), enables multi-file LLM synthesis, and adds multi-select to the file explorer. The stack used TypeScript, Vercel AI SDK, and youtubei.js. A key takeaway was the 'compound engineering' workflow: after each session, updating CLAUDE.md with lessons learned to prevent repeated mistakes. Claude Code took them from a three-bullet plan to a working MVP in ~30 minutes, though they note it requires tighter guardrails for high-stakes projects.

  9. 9
    Article
    Avatar of jetbrainsJetBrains·14w

    Write Modern Go Code With Junie and Claude Code

    JetBrains has released a plugin called go-modern-guidelines that helps AI coding agents like Junie and Claude Code generate modern, idiomatic Go code. The problem it solves: AI models tend to produce outdated Go patterns due to training data cutoffs and frequency bias toward older code. The plugin reads the Go version from go.mod and instructs agents to use features available up to that version—for example, using slices.Contains() instead of manual loops, or errors.AsType[T]() instead of the older errors.As() pattern. In Junie 2xx.620.xx+, it works out of the box. For Claude Code, it requires installing via a few slash commands in a session.

See all Claude Code archives