튜토리얼
Dev.to에서 수집한 Claude Code 학습 가이드와 튜토리얼입니다.
최근 30개 콘텐츠
Fable 5.1 cut cache reads by 75%. Cost per task went up 20% anyway.
In the same week that Claude Fable 5.1 shipped, two things happened that look like they cannot both...
2026-09-07 · 출처: devtoI parsed 559 public CLAUDE.md files. Most of what's in them isn't rules.
I've been building a tool that checks whether Claude Code actually followed the rules in your...
2026-09-05 · 출처: devtoReact, Next.js, Svelte, Zod: none of them can tell AI who they're actually for
Your coding agent is good at reading code. Point Claude Code or Cursor at a repo and it...
2026-09-05 · 출처: devtoSame skeleton, different last gate: reading Anthropic's commerce-agents with my own agent open in the other window
Anthropic shipped commerce-agents: a reference shopping agent and merchant agent, three runtime...
2026-09-05 · 출처: devtoI tested Claude Code's memory against mine. They are not doing the same job.
Proof over claim Last time I described the hour a platform shipped the feature I had spent months...
2026-09-04 · 출처: devtoStreamline Publishing with a Claude Code Skill
A Claude Code skill that turns one markdown file into dev.to, AWS Builder Center, Medium and LinkedIn versions, checks them before they ship, and posts the ones with an API — plus the debugging tools
2026-09-04 · 출처: devtoClaude Code journal plugin: Notion session summaries at a glance
The /journal skill from my breadcrumbs post is now a Claude Code plugin anyone can install. One glanceable callout per topic, colored by season with an icon for the weekday, three Notion calls per run
2026-09-04 · 출처: devtoWhy my AI agents needed a rivalry
Mixing Gemini and Claude for better code The single-agent mirage A few weeks ago, I...
2026-09-04 · 출처: devtoBlock Zero: Oh, no! Claude, Kiro and I over-engineered the throwaway.
A lesson in overcorrection, from an AI-assisted builder who is scared stiff of shipping spaghetti and...
2026-09-02 · 출처: devtoMy Claude Code config costs 9,857 tokens before I type anything
I installed 107 skills, 38 agents and 15 commands into Claude Code over a few months. Standard stuff...
2026-08-31 · 출처: devtoI built an RPG that teaches Claude Code by making you actually use it
claude-quest is an in-terminal RPG for learning the Claude Code CLI. missions live in real sandbox directories, and progress is graded by checking what you actually did, not by quizzing you.
2026-08-30 · 출처: devtoHow I Triaged 8,400 Production Errors Into 11 Real Bugs With Claude Code
TL;DR My error tracker had 8,400 events a week across ~340 distinct issues, and nobody on...
2026-08-30 · 출처: devtoHow I Migrated 40 REST Endpoints to GraphQL With Claude Code in 12 Days
TL;DR I moved 40 REST endpoints to GraphQL in 12 days using Claude Code as the grunt-work...
2026-08-30 · 출처: devtoWe said a Claude Code subagent costs 436k tokens. A cleaner measurement says 54k — here is what fooled us
Two weeks ago we published a number: a Claude Code subagent costs ~436,000 tokens before it reads a...
2026-08-30 · 출처: devtoClaude API Workspace Verification: Catch Misrouted Requests Before Attribution
Claude API workspace verification is a small check that closes an awkward observability gap. A...
2026-08-30 · 출처: devtoClaude Structured Outputs Refusal Handling: Stop Parsing HTTP 200 Refusals
Claude structured outputs refusal handling belongs before domain deserialization. A successful HTTP...
2026-08-29 · 출처: devtoClaude Code as Creative Director
For the past six months I ran a git repository as a one-person film studio. The crew was Claude,...
2026-08-29 · 출처: devtoRunning Claude Code in 4 Parallel Sessions Led to 'Team Development' — 7 Recipes to Prevent Collisions
What happens when parallelized coding agents using git worktree start modifying the same microservices simultaneously? Along with a real-life story of narrowly avoiding a deployment rollback incident,
2026-08-29 · 출처: devtoIs Claude Getting Dumber? You May Be Looking at the Wrong Part
Claude keeps improving on benchmarks while many experienced users say the product feels worse. Both reports can be accurate.
2026-08-28 · 출처: devtoA Claude Code subagent costs ~436k tokens before it reads a single file: measured, with the break-even math
Every guide to Claude Code subagents tells you the same two things: they isolate context, and they...
2026-08-27 · 출처: devtoStop asking your AI agent to follow rules. Enforce them.
I moved the grep-able half of my coding rules from prompts to Claude Code hooks. Rule adherence went from probabilistic to 100% — and suddenly running Haiku as a builder stopped being reckless.
2026-08-27 · 출처: devtoValidating OpenAI & Anthropic Tool-Calling Schemas
A practical guide to writing and validating JSON Schemas for OpenAI function calling and Anthropic tool use - common mistakes, a pre-deploy checklist, and a worked example.
2026-08-27 · 출처: devtoStop chasing fads. Operate Claude like a startup founder.
I am running an AI-native startup. Early on though, I would spend so much time staying ahead of every...
2026-08-25 · 출처: devtoHow I Backfilled 1,200 Tests Into a 5-Year-Old Codebase With Claude Code
TL;DR I inherited a 5-year-old TypeScript service with 6% test coverage and spent three...
2026-08-24 · 출처: devtoRate Limits Cost Me a Whole Night of Work — Here's the 46-Line Script That Fixed It
Every heavy Claude Code user eventually hits the wall: the 5-hour rate limit block. I'm Lily. I lost...
2026-08-24 · 출처: devtoClaude Enters Live Life Sciences Workflows With Early Lab Results From Anthropic
Anthropic has published early evidence of Claude operating in live life sciences research workflows,...
2026-08-23 · 출처: devtoHow I Built My First MCP Server for Claude Code: 5 Lessons Learned
TL;DR I spent a weekend building my first MCP server so Claude Code could query our...
2026-08-22 · 출처: devtoYour MCP server is configured but Claude can't see it: reading claude mcp list status
You ran claude mcp add, it printed Added ..., and Claude still acts like the server does not exist....
2026-08-22 · 출처: devtoOpus 5: Review bottleneck
The pitch for Opus 5 was that the model checks its own work now. Anthropic's Opus 5 guidance says as...
2026-08-21 · 출처: devtoWhen your MCP tool fails: errors, hangs, and empty results — what Claude Code actually does with each
Yesterday I posted a one-liner on Bluesky: an MCP tool that errors teaches the model something, one...
2026-08-20 · 출처: devto