Best of Claude Code — March 2026

1. 1
   Article

   daily.dev·9w

   How we built a Linear coding agent: the hard parts

   daily.dev built Huginn, a coding agent integrated into Linear that automates the full workflow from ticket to PR. The post covers the hard engineering problems encountered: wrapping Claude Code and Codex as child processes with their undocumented streaming formats, building a three-tier fallback parser for structured LLM output, debugging session continuity failures caused by working directory changes, and using Linear labels as a crash-resilient state machine. The team also describes their 'Digital Twin Universe' (DTU) testing approach — in-memory replicas of Linear, GitHub, and KMS running in Docker containers — which made a 99% AI-generated codebase viable. Known limitations include ongoing output parsing fragility, rough BYOK credential handling, and poor fit for tight iterative or architecturally complex tasks.

   66

   6
2. 2
   Video

   Awesome·12w

   An AI CEO finally said something honest...

   A critical take on the AI coding hype cycle, prompted by a tweet from the creator of Open Code Agent. The core argument is that code was never the real bottleneck in software development — product thinking, prioritization, and system reasoning were. Lowering the cost of shipping features removes healthy constraints that forced teams to make sharp decisions and kill bad ideas early. Drawing on the Jevons paradox, the piece argues that cheaper code generation will expand software complexity rather than reduce developer demand. It also highlights IBM tripling entry-level hiring, Sam Altman acknowledging AI-washing layoff trends, and the irony of Claude Code's head declaring 'coding is solved' while Anthropic offers $50K signing bonuses for engineers.

   46

   7
3. 3
   Article

   The Miners·11w

   Figma MCP Builds Exactly What You Ask – Nothing More

   Two developers ran real-world experiments using Figma's MCP with Claude Code to convert Figma designs into code. Key findings: the tool is highly literal and does exactly what you ask — no more. Specificity in prompts is critical; vague requests yield inconsistent results. Visual translation from Figma to code is accurate, but structural best practices (file separation, responsiveness, component organization) must be explicitly requested. Applying changes to an existing codebase works better than greenfield generation because Claude has structural context to follow. A major practical blocker is Figma's MCP quota on the free tier (~6 requests/month), which severely limits experimentation. Design library mapping is also a current weak point.

   37

   1
4. 4
   Article

   Product Hunt·9w

   Maestri: An infinite canvas where coding agents work in concert

   Maestri is a native macOS app built by a solo developer that provides an infinite canvas for managing multiple AI coding agents simultaneously. Each terminal session is a visual node that can be freely positioned alongside notes and sketches. The standout feature is agent-to-agent communication: drag a line between two terminals and the agents collaborate directly via PTY orchestration — no APIs or middleware required. Claude Code can talk to Codex, Gemini can delegate to OpenCode, etc. An on-device AI companion called Ombro (powered by Apple Intelligence) monitors all activity and summarizes what happened while you were away. Built in Swift with a custom canvas engine, it requires no account, collects no telemetry, and is priced at $18 lifetime for Pro with one free workspace.

   34
5. 5
   Article

   Reid Burke·11w

   Worktrunk — Git Worktree Manager for AI Agent Workflows

   Worktrunk is a CLI tool that simplifies Git worktree management, specifically designed for running multiple AI coding agents in parallel. It wraps Git's native worktree feature with three core commands (switch, list, merge/remove) to eliminate repetitive path and branch typing. Key features include hooks for automating setup tasks, LLM-generated commit messages, an interactive worktree picker with live diff previews, build cache sharing between worktrees, and direct integration with Claude Code and Codex. Installation is available via Homebrew, Cargo, Winget, or AUR.

   27

   1
6. 6
   Article

   On Test Automation·11w

   Writing tests with Claude Code - part 1 - initial results

   An exploration of using Claude Code to generate API tests for a Spring Boot banking application, starting from scratch with only a prompt. Claude produced 23 passing tests in minutes, achieving 95% line coverage and 91% mutation coverage as measured by PITest. However, analysis revealed gaps: several critical code paths were missed (HTTP 500 handling, empty account list, boundary values), and 4 of the 23 tests (17%) were dead weight that didn't uniquely contribute to coverage. The author emphasizes that evaluating AI-generated tests requires domain knowledge, testing experience, and tools like mutation testing — simply accepting passing tests at face value risks a test suite full of holes.

   27

   1
7. 7
   Article

   Agentic Digest·12w

   Claude Code overtakes Copilot in 8 months, Opus 4.6 hallucinates a Vercel deployment

   Claude Code has surpassed GitHub Copilot in usage after just 8 months, with Anthropic reporting $19B annualized revenue and 4% of all public GitHub commits attributed to Claude Code. A notable production incident at Vercel revealed Claude Opus 4.6 hallucinating a GitHub repo ID and deploying a random OSS codebase to a user's team, highlighting agentic failure risks with powerful APIs. Google released Gemini 3.1 Flash-Lite with 2.5x speed improvement and infrastructure-tier pricing. Meta poached the head of Qwen Code while Alibaba split the Qwen team, potentially setting back open-source LLM development. Additional notable items include Codex for Windows shipping, Cursor MCP Apps rendering interactive UIs, Claude Code YOLO mode risks, and Jeremy Howard warning about skill erosion from over-reliance on AI coding tools.

   24
8. 8
   Article

   SwirlAI·11w

   Agent Skills: Progressive Disclosure as a System Design Pattern

   Agent Skills is an open standard released by Anthropic in December 2025 that uses a simple SKILL.md file format to give AI agents modular, progressively loaded capabilities. The format applies the progressive disclosure design pattern to agent context management: at startup only skill names and descriptions are loaded (~80 tokens each), full instructions are activated when relevant, and supporting scripts/docs are pulled in only during execution. This three-tier architecture solves the context window degradation problem ('lost-in-the-middle') while making agent behavior configurable by non-technical users. OpenAI, Google, GitHub Copilot, and Cursor all adopted the standard within weeks of its release. The pattern generalizes beyond coding agents to any system needing broad capability with focused execution, and AI Engineers building non-coding agents must implement the same discovery-activation-execution pipeline themselves.

   24

   2
9. 9
   Video

   Dan Vega·10w

   Building a Terminal UI for Spring Initializr with Java

   A developer built a terminal UI (TUI) for Spring Initializr using Java and the newly announced Tamboo UI framework. The tool replicates the Spring Initializr web experience in the terminal, with features like fuzzy dependency search, favorites, project exploration, and post-generation hooks that can automatically open an IDE (like IntelliJ) and launch Claude Code in the new project directory. The native executable is built with GraalVM for fast startup and low memory usage, and binaries for macOS, Windows, and Linux are distributed via GitHub releases.

   24

   1
10. 10
    Article

    Agentic Digest·10w

    Claude Code gets 1M context for free, GitHub pulls premium models from student Copilot

    Anthropic silently expanded Claude Opus 4.6 and Sonnet 4.6 to support 1M token context by default at no extra API cost, removing a key constraint for Claude Code users working with large codebases. GitHub moved in the opposite direction, stripping premium models (GPT-5.4, Claude Opus 4.6, Sonnet 4.6) from its free Copilot Student plan citing sustainability, drawing nearly 2,900 downvotes. A live benchmark of 22 code review tools ranked Claude first on quality but last on cost at $23.60 per review — roughly 1,100x more expensive than the most efficient tool. NanoClaw, an open-source agent framework endorsed by Andrej Karpathy with 22K GitHub stars, formalized a Docker partnership to run agents in isolated MicroVM sandboxes. Other notable items include Chrome v146 shipping native MCP support, shadcn/cli v4 with coding agent context features, AWS SAM integration for the Kiro IDE, and a documented case of an AI agent autonomously publishing a blog post attacking a maintainer who rejected its PR.

    19

    2
11. 11
    Video

    Theo - t3․gg·12w

    Cursor, Claude Code and Codex all have a BIG problem

    A developer and early investor in Cursor argues that AI coding tools like Cursor, Claude Code, and Codex are plagued by poor UX and instability because they were built using early, weaker AI models—a form of premature 'vibe coding' that created low-quality codebases with compounding technical debt. The core thesis is that codebase quality peaks around the 6-month mark and only degrades after that, and bad patterns spread exponentially faster than good ones, especially when AI agents copy existing code. Practical advice includes: tolerate zero bad patterns, aggressively delete and rewrite bad code (now cheap with AI), keep unrelated features in separate repos, spend more time in planning mode with models, and use the latest models. A proposed future pattern is maintaining two parallel codebases—a 'slopfest' prototype version for rapid experimentation and a clean production version—similar to how Vampire Survivors maintains both a Phaser.js prototype and a C++ production build.

    19

    3
12. 12
    Article

    Tech World With Milan·9w

    Agentic code workflows with Nick Tune

    Nick Tune, Senior Staff Software Engineer at PayFit, shares his advanced agentic coding workflow built around deterministic, state-machine-driven processes. Key practices include modeling the dev workflow as a typed state machine with unit-tested transitions, using PRD expert agents for structured planning before writing any code, enforcing architecture rules via lint and dependency-cruiser checks rather than relying on AI compliance, running layered code reviews with CodeRabbit and local review agents, and driving Claude through a strict TDD red-green cycle with verified pre/post-conditions. The approach prioritizes determinism over prompt-based trust, using pre-commit hooks and banned commands to prevent AI from bypassing guardrails.

    33
13. 13
    Video

    Matt Pocock·9w

    Claude Code tried to improve /init... Is it any better?

    A hands-on evaluation of Claude Code's updated /init command, tested against a real React/TypeScript repo. The author walks through the new interactive setup flow that asks about claude.md files, skills, and hooks, then critically interrogates each suggestion Claude makes. Key findings: the new init is more interactive and minimal than before, but still tends toward sycophancy rather than pushing back on the developer. The author ends up with a nearly empty claude.md and one useful skill for installing Effect packages, arguing that most suggestions were either redundant (discoverable from code), already handled by hooks, or too rare to justify burning the LLM's instruction budget.

    26

    3
14. 14
    Article

    Planet Python·9w

    Do you teach Python? Then check out course-setup

    A Python instructor shares course-setup, a PyPI utility suite built to automate the repetitive classroom prep work of creating Git repos, connecting them to GitHub, launching Jupyter/Marimo notebooks, and auto-pushing changes so students can follow along. Originally a manual 10-minute setup routine, it was significantly expanded using Claude Code with AI agents writing most of the code. Features include multi-day scheduling, Israeli weekend support, course retirement/unretirement, and daily zipfile archiving. Available on PyPI and GitHub.

    17
15. 15
    Article

    Daily Dose of Data Science | Avi Chawla | Substack·9w

    Anatomy of the .claude/ Folder

    A comprehensive guide to the .claude/ folder structure used by Claude Code. Covers CLAUDE.md (the main instruction file), CLAUDE.local.md for personal overrides, the rules/ folder for modular scoped instructions, commands/ for custom slash commands with shell injection, skills/ for auto-invoked reusable workflows, agents/ for specialized subagent personas with isolated context, and settings.json for permission control. Also explains the global ~/.claude/ directory for cross-project preferences and session memory. Includes a practical step-by-step setup progression and a full folder structure reference.

    36

    3
16. 16
    Article

    Agentic Digest·9w

    Cursor's Composer 2 runs on Kimi K2.5, Claude Code lands on Telegram and Discord

    A roundup of AI coding tool news: Cursor's Composer 2 was found to be running on Kimi K2.5 without attribution, sparking community debate about transparency. Anthropic launched Claude Code Channels, enabling Telegram and Discord integration via MCP as a direct competitor to OpenClaw. Qwen released Qwen3-Coder-Next, a 3B active parameter model claiming to outperform much larger models on SWE-Bench-Pro, alongside an open-source Qwen Code CLI. GitHub Copilot removed Claude Opus and GPT-5.4 from its student plan, drawing over 5,000 dislikes. Additional notes cover Claude Opus 4.6 finding Firefox vulnerabilities, OpenAI's faster container pool for agents, Karpathy's home automation agent, and the emerging concept of 'comprehension debt' in AI-assisted coding.

    15
17. 17
    Article

    Test·10w

    Stepping into Crazy AI World

    A reflective take on navigating the overwhelming pace of AI advancement in software development. Encourages developers to tune out hype from CEOs and social media influencers, accept the new reality, and focus on practical steps: experimenting with AI coding agents like Claude Code, Codex, and Gemini CLI, learning to configure agent guidelines (AGENTS.md, CLAUDE.md), and exploring Spec Driven Development (SDD) as a workflow for AI-assisted coding.

    14

    1
18. 18
    Article

    Towards Data Science·10w

    The Basics of Vibe Engineering

    Vibe engineering — building software by directing AI agents rather than writing code manually — is explored through the lens of what still requires human input. Planning, architecture, and system thinking remain essential; AI handles implementation. Claude Code has emerged as the dominant AI coding tool, surpassing Cursor and Codex in community mindshare. Key risks include hallucinated outputs (fabricated API endpoints, accidental data deletion), model drift outside user control, and potential skill atrophy from reduced hands-on coding. The author argues engineering is shifting up a layer of abstraction toward system judgment rather than disappearing entirely.

    13

    1
19. 19
    Article

    DEV·10w

    I Built a Browser UI for Claude Code — Here's Why

    Claudeck is a browser-based UI for Claude Code built in two weeks by a solo developer frustrated with terminal-only limitations. It connects to the Claude Code SDK in-process via WebSocket, offering 50+ features including a parallel 2x2 chat grid, cost analytics dashboard, AI workflows with multi-step pipelines, autonomous agent DAGs with a visual SVG editor, Telegram-based remote tool approval, prompt templates, file explorer, git panel, and a plugin system. Built with vanilla JS and only six npm dependencies, it runs entirely locally with no cloud or telemetry. Key gaps include no authentication, no multi-CLI support, and no live file editing.

    15

    1
20. 20
    Video

    NeetCode·12w

    Building the Future of coding, OpenCode with Dax Raad

    Dax Raad, co-creator of OpenCode, discusses the origins and philosophy behind the open-source AI coding agent. He explains why Claude Code was the first AI tool that stuck with his terminal-focused team, and how OpenCode's positioning as a model-agnostic, open-source tool drives its success more than product quality alone. Dax shares candid views on the agentic coding race, competition with Claude Code and OpenAI, acquisition offers the team has declined, and the real dynamics of code quality vs. speed trade-offs. He also reflects on how LLMs are changing developer workflows, skill atrophy risks, and whether coding is losing its fun.

    13
21. 21
    Article

    Agentic Digest·8w

    Claude Code gets computer use, GitHub Copilot injects ads into PRs

    A roundup of major AI coding and LLM news: Claude Code gains computer use capability letting it control mouse/keyboard and self-verify UI output. GitHub Copilot was caught injecting ads into over 1.5M pull request descriptions at 1,000+ insertions/day. Alibaba's Qwen 3.6 Plus Preview launched on OpenRouter with a 1M token context window at zero cost. ARC-AGI-3 benchmark results show every frontier model scored under 1% while humans scored 100%. Additional items cover a LiteLLM and axios supply chain attacks, Qodo's $70M Series B, Turborepo 2.9 performance gains, agentic coding overwork data, and red-teaming failures in live agents.

    19

    1
22. 22
    Article

    freeCodeCamp·9w

    The Claude Code Handbook: A Professional Introduction to Building with AI-Assisted Development

    A comprehensive handbook covering Claude Code, Anthropic's AI-powered software development agent. It walks through installation, VS Code setup, subscription tiers, prompt discipline, Plan Mode, feature-by-feature development, token economics, and the internal agent loop mechanics. The guide targets both experienced developers looking to multiply their output and non-technical builders wanting to create software without prior coding experience. Key practices covered include using Plan Mode for 80% of sessions, writing Product Requirements Documents, building incrementally, managing context windows, and understanding how Claude reads codebases selectively via tool calls.

    11

    1
23. 23
    Article

    Viget·10w

    Using Claude Code More Intentionally

    A practical guide to setting up Claude Code as a proper development collaborator rather than an ad-hoc chat tool. Key strategies include writing a thorough CLAUDE.md as an onboarding document, using .claudeignore to keep context clean, externalizing plans and artifacts to disk for persistence across sessions, building reusable 'skills' (markdown-defined repeatable processes stored in .claude/skills/), integrating CLI tools and MCP servers for structured external access, and using hooks to automatically run tests or commits after Claude finishes tasks. Also covers remote control via the Claude app for supervising long-running jobs and model switching (Haiku/Sonnet/Opus) to balance cost and capability. The core thesis: invest in the environment and infrastructure around Claude Code, not just the prompts.

    11
24. 24
    Article

    Avalonia UI Blog·10w

    Accelerate Showcase: Built with AI, Designed with Stitch

    A product manager at Avalonia UI built a polished desktop showcase app without writing any code manually, using Claude Code, Google Stitch for UI design, and Avalonia's DevTools and Parcel MCP servers. The workflow involved generating component skills from documentation, prompting Claude to design and implement an MVVM app targeting .NET 10 for Windows/macOS/Linux, and using the Parcel MCP server to handle cross-platform packaging including macOS code signing and notarization. The result was a shippable app produced in roughly an hour, compared to an estimated week of designer-plus-engineer effort. The post highlights where AI is genuinely useful for Avalonia: building applications with it rather than building the framework itself.

    11