#Claude Code
668 related articles
Claude Code Burns 15% of Its Tokens Every Turn Just to Display Three Words
A Hacker News discussion notes that Claude Code spends ~15–20% of its tokens on a three-word status line. This article analyzes how the status line is injected into context, its impact on cost and the context window, and how developers can audit token overhead.
Claude Code in Practice: Building a Zero-Code Clip Factory That Turns Long Videos into Vertical Shorts Automatically
Bilibili creator Wukong uses Claude Code to build a zero-code clip factory, automatically turning a 35-minute long video into 10 vertical shorts. Full workflow from Plan Mode, Whisper transcription, claude.md rules, hook QA to subagent review and plugin distribution, with real measured data.
Claude Code in China: A Practical Guide from Installation to Real-World Coding
A Bilibili live class explains Claude Code in China: installation and integration, built-in commands, MCP configuration, SQL skills, and the DRMD file, plus a stable login workaround to avoid account bans and help developers avoid pitfalls.
Claude Code Setup and Practical Guide for Users in China: Bypassing Bans and Full MCP Integration Explained
A Bilibili livestream class explains Claude Code use in China: from installation and integration to MCP tool configuration, SQL skills, and built-in commands, plus causes of account bans and login-bypass ideas, with a six-module learning roadmap.
Claude Code in Practice: Mastering AI Coding Agents, MCP, and Skills
A deep dive into Claude Code: slash commands, claude.md context budget, four permission modes and Hooks security, MCP servers vs. Agent Skills, and Anthropic's TDD autonomous workflow.
A Step-by-Step Claude Code Tutorial from Bilibili: From Domestic Installation to Real-World Pitfalls
Breaking down a Bilibili Claude Code practical course: installation and integration in China, built-in commands, MCP configuration, skills, and config files—plus account-ban causes and stable-usage ideas, with tool selection advice and audience analysis.
Claude Code Usage Surges 8x: Error Retries Count Against Paid Quota, Anthropic Refuses Compensation
Claude Code usage surged roughly 8x in a single day. Anthropic support confirmed that retries triggered by service errors count against paid subscription quotas and explicitly refused refunds or compensation. This article covers the incident data, the official response, and practical advice for developers.
Writing Code with Claude Code Means Passing a Network Admin Exam First: The Pain of Configuring AI Programming Tools
Claude Code's real barrier isn't coding ability but account, network, and regional configuration. Why AI programming tools are painful to set up — and how developers should choose pragmatically.
Who Reviews AI-Written Code? Claude Code Reveals Its Six-Layer Review Process
Claude Code reveals its AI code review process: 90% of code is AI-generated, using three strategies—prove-it-first before submitting, six layers of tiered approval sieves, and capping review rounds—to cut rollback rates by over 40% while merged changes doubled.
Build an MCP Server in 30 Lines of Python and Connect It to Claude Code
Package finance tools into an MCP server in about 30 lines of Python and connect it to Claude Code via stdio. This article breaks down MCP's three roles and its Tools, Resources, and Prompts capabilities, explains decorators and type hints, the MCP Inspector self-test workflow, and the claude mcp add command format and scope settings.
Claude Code ultrathink Upgrade: Maxing Out Per-Turn Reasoning Effort at xhigh
Starting with Claude Code 2.1.311, typing ultrathink raises a single turn's reasoning effort to xhigh, covering Opus 5.5, Sonnet 5.5, Haiku 5.5, and Fable 5.1. This article explains when it takes effect, its caps, and the impact on development workflows.
Claude Code v2.1.311 Update Analysis: Long-Context Compaction and MCP Stability Fixes
Claude Code v2.1.311 fixes long-context interruption past 200K tokens, MCP unresponsive interrupt failures, unavailable subagent tools, and large-file edit lag, and adds idle session hold parameters for self-hosted runners.
When You Say "Make No Mistakes": The Vibe Coding Truth Behind Claude Code's Dark Humor
A viral Claude Code joke reveals the real trap of Vibe Coding: when users demand AI "make no mistakes" without defining acceptance criteria, AI may satisfy the instruction in completely unexpected ways. This article breaks down goal definition, acceptance conditions, and permission boundaries from a software engineering perspective, offering actionable principles for AI programming collaboration.
CleanYourTV: Safely Streamline Your TV with Claude Code
CleanYourTV is an Android TV slimming solution combining Claude Code and ADB scripts to disable ads and telemetry over Wi-Fi. This article analyzes how it works, potential risks, and provides a safety checklist including package list backup and command-by-command review steps.
Claude Code's Most Powerful SEO Skill Pack: 26 Sub-Skills + 19 Subagents
GitHub open-source project claude-seo provides 26 SEO sub-skills and 19 subagents for Claude Code, covering technical SEO, E-E-A-T, Schema, GEO/AEO, Agent Readiness, backlinks, and local SEO, with PDF/Excel reports and Google API integration.
Claude Code Deep Configuration Guide: From Model Selection to Skills in Practice
Based on Tech With Tim's three-hour hands-on course, a systematic walkthrough of Claude Code's model and effort level choices, permission modes, CLAUDE.md conventions, Skills scoping, subagents and Hooks configuration, plus advanced usage like context compaction and parallel sessions—helping you turn a default install into a genuinely efficient workspace.
Claude Code Beginner's Guide: Desktop Setup and 6 Key Settings to Avoid Pitfalls
Claude Code desktop tutorial: paid tier, Opus planning and Sonnet building, workspace folders, approval rules, claude.md, compact sessions, and four project demos.
Stop Stuffing 20,000 Lines into CLAUDE.md: 10 Skills That Slash Context Costs
Instead of stuffing 20,000 lines into CLAUDE.md, use a progressively disclosed skill system. We break down 10 Claude Code skills — Addy Osmani Agent Skills, Graphify semantic knowledge graphs, Superpowers subagent orchestration, LSP plugins, and more — to cut token costs and improve code quality.
Claude Code Step-by-Step Practical Tutorial: From Installation to Permission Modes, Avoiding Account Bans
Claude Code beginner practical tutorial: detailed npm installation steps, using CC Switch to bypass official login and avoid bans, API Key configuration, and the efficiency difference between permission modes and natural language prompts, helping zero-foundation developers get started quickly.
Claude Code MCP Tasks: A New Paradigm for Long-Running Tasks and Proactive Questioning
Claude Code supports MCP Tasks and elicitations, enabling tool calls to run as long tasks and ask users questions mid-execution. This article explains the conditions, current gaps, and required server changes.