Articles
Industry news, technical articles, and product introductions
📚 Claude Tutorials Hub
40+ step-by-step Claude guides — prompt engineering, Claude Code, API, agents. Browse by topic →
Loading...
Turn a Home Mac mini Into an Always-On Claude Code Workstation: claudecodeui + SSH Reverse Tunnel, Take Over Sessions From Any Browser
A Mac mini at home runs Claude Code around the clock — but how do you take over a session from a browser when you're away? This is a real setup that has been live for a week and in daily use: claudecodeui as the web UI (chosen over the official web version, ttyd, and code-server), an SSH reverse tunnel pushing it to a VPS, and nginx adding TLS plus login rate limiting to turn it into an ordinary URL. Includes full configs, real operating numbers (five days of tunnel uptime with zero drops, 170MB RSS), a <synthetic> placeholder bug hit and fixed within the first week, and an honest for-and-against on why not Tailscale.
claude-codeclaude-code-lab+7
claudeAug 29, 202612 min
153You Set ANTHROPIC_BASE_URL. Claude Code Ignored It.
I exported ANTHROPIC_BASE_URL in .zshrc to point at a self-hosted API gateway, and Claude Code kept talking to Google Vertex anyway. On the same machine, a launchd-managed web UI insisted it wasn't authenticated at all. Neither bug was in the gateway — both were in the gap between 'I set the env var' and 'the process actually has it.'
claude-codebug-postmortem+2
pitfallsAug 24, 20264 min
229Claude Didn't Write That Printer Driver: 14KB of Glue, a Linux Container, and HP's Own Binary
A tweet claiming Claude wrote a macOS driver for a Windows-only HP printer pulled 2.62 million views. Pull the repo and you find 6,497 bytes of shell, 7,638 of Python, 550 of Dockerfile — not one line of C. The actual encoding is done by rastertospl, a binary from HP's official Linux driver, running in a Linux container on the Mac. Hacker News caught this. But debunking isn't the point: the genuinely valuable parts of that four-hour session (reading the printer's own error pages, escaping the CUPS sandbox, writing USB directly) and the fact that the decisive turn came from the human, not from Claude, are a precise measurement of where AI's grunt-work ability currently ends.
claude-codeopen-source+6
claudeAug 19, 202611 min
197Fable 5 Has a 1M Context Window, So Why Does the Status Line Say 200k? Capture the Data Before You Swap the Tool
Claude Fable 5 officially ships with a 1M-token context window, yet the Claude Code status line kept showing 200k as the denominator. The first instinct — 'let's switch to a better statusline' — was wrong. This postmortem walks through the full debugging process: one line of tee to capture the statusline's stdin, hard evidence that the official field misreports 200000 for new models, and a model-table fix. Plus a general lesson: swapping tools never fixes a broken data source.
llmclaude-code+3
pitfallsAug 14, 20264 min
240I Put My Opus 5 Config on the Recommended Diet, Then Ran 18 A/B Trials: 21% Cheaper, and I Can't Prove It's Better
"Opus 5 verifies itself, so delete your fallback prompts" is advice you hear everywhere. I took it, then isolated both configs with CLAUDE_CONFIG_DIR and ran 18 headless trials on identical tasks. Output tokens dropped 21% and wall clock 20-29%, with zero counterexamples. But two of the rewritten rules never fired at all, and one result points the other way: the old config's most thorough run covered a strict superset of what the new one found. Why cheaper and better are separate questions.
prompt-engineeringclaude-code+4
claudeAug 5, 20266 min
183Claude Code Skills: Turn Repeated Workflows into a Slash Command with SKILL.md
Skills are the most underrated feature in Claude Code: write a workflow into a SKILL.md file and invoke it with a slash command, or let Claude load it automatically when the task matches. This guide covers the file structure, frontmatter, auto-trigger mechanics, how skills differ from CLAUDE.md, hooks, and subagents, plus three ready-to-copy examples.
claude-codeslash-commands+4
claudeJul 28, 20263 min
190Claude Code Plan Mode: Research First, Code Later, Rework Less
Plan Mode is Claude Code's read-only planning mode: Claude researches your codebase and presents an implementation plan, and only touches code after you approve. This guide covers how to enter it (Shift+Tab cycling), what it actually blocks, which tasks deserve it, and four techniques that make planning genuinely improve output quality.
claude-codeai-coding+4
claudeJul 28, 20264 min
168They Ran a Lights-Off Software Factory for Four Months. Then a Cofounder Rewrote It by Hand
An essay titled 'Why Software Factories Fail' hit 390 points on Hacker News. Author Dex Horthy is no AI skeptic — he built his reputation teaching people to use coding agents. In July 2025 he ran a no-human-reads-the-code factory at his own company; after the third incident, his cofounder spent two weeks rebuilding the codebase by hand. His root cause: in the RL loop that trains coding models, eroding maintainability carries no penalty. A model-training problem, not a skill issue.
claude-codeai-coding+7
ai-tutorialsJul 27, 202610 min
300Anthropic Deleted 80% of Claude Code's System Prompt. The Evals Didn't Move.
'We removed over 80% of Claude Code's system prompt' — and the evals didn't move. The popular takeaway ('write shorter prompts') is wrong: what got deleted was constraints, not information. A usable dividing line, plus the API-layer mechanics the official post left out and the two real disagreements from 343 HN comments.
prompt-engineeringclaude-code+5
ai-tutorialsJul 27, 202613 min
314Claude Code 踩坑实录：两个 AI 幻觉真实案例与 hook 日志交叉验证法
Claude Code (Opus 4.8) 一天内两次真实翻车：rg -rn flag 误用被 AI 判定为提示注入、凭空忏悔一次从未发生的文件删除——问题由 Fable 5 排查定案，Opus 4.8 多次测试未能自主发现。本文还原排查过程，并给出用 PostToolUse hook 建立真相基线日志的模型无关防御方案。
debuggingclaude-code+4
ai-tutorialsJul 20, 20265 min
15510 Advanced Claude Code Techniques: Session Recovery, Checkpoint Rewind, and Headless CI
From named sessions and the /rewind time machine to context slimming, path-scoped rules, auto memory, and wiring Claude Code into CI with headless mode — 10 advanced techniques straight from the official docs that most users never open, each with the exact commands and when to use them.
claude-codeheadless+4
claudeJul 20, 20265 min
207Claude Code's 2026 Features: Agent Teams, Nested Subagents, Fast Mode — and When Each Is Worth It
The first half of 2026 pushed Claude Code well beyond the single-session workflow: multi-agent teams, subagents that recurse up to 5 levels deep, background sessions with Agent View, and an Opus-class Fast Mode. Based on the official docs and changelog, here is what each feature does, how to turn it on, and when it's actually worth using.
claude-codeagent-teams+4
claudeJul 20, 20265 min
684