154 independent guides

Editorial content to understand Claude Code.

Security, architecture, DevSecOps, prompting. Long-form guides written by experts, sortable and filterable.

Filter by themeSee the latest

Featured and latest articles

Featured

Understanding Claude Code internals through leaks

What leaked system prompts reveal about Claude Code's internal architecture, and what we can transfer to write sharper CLAUDE.md files and skills.

  • Guide
  • Tooling
Read article
  • Guide
  • Performance

Claude Opus 5.5: Fable 5.1-level work for 40% less than Opus 5

Anthropic released Claude Opus 5.5 on September 22, 2026: lower prices, $0.20 cache reads, faster output and a new…

  • Guide
  • Security

Fable 5.1 and Mythos 5.1: one model, two levels of safeguards

Released September 1, 2026, Claude Fable 5.1 and Mythos 5.1 are the same model with different protections. Cache reads…

  • Comparison
  • Performance

GPT-6 vs Opus 5.5: what the prices and numbers really say

OpenAI launched GPT-6 Astra on September 3, 2026, then Sol and Luna on the 22nd, the same day as Opus 5.5. Official…

  • Tutorial
  • Productivity

Cross-session messaging: your Claude Code sessions can finally talk to each other

Since August 2026, one Claude Code session can message another with ListAgents and SendMessage. How it works,…

  • Tutorial
  • Tooling

claude plugin eval: finally measure what your plugin brings

Since v2.1.269 (September 2026), Claude Code can test a plugin on a suite of cases and compare it against a session…

Most read in the last 30 days

Matomo stats, refreshed on 2026-05-27

  • Use case
  • Security

Leaked Anthropic API key? Step-by-step recovery (2026)

Your Anthropic API key sk-ant was leaked in a commit, screenshot, or log? Revoke it now, rotate it, audit the damage.…

  • Comparison
  • Tooling

Claude Design vs Figma: who wins the AI design race in 2026?

Claude Design (Anthropic Labs, April 2026) takes on Figma AI directly. Honest comparison: conversation vs canvas,…

  • Tutorial
  • Security

Claude Code Security: 8 best practices + copy-paste checklist

Least privilege, MCP vetting, sandboxed config profiles, secrets scanning: 8 best practices with a ready-to-use…

  • Reference
  • Tooling

The real costs of Claude Code

Transparent analysis of Claude Code costs: subscriptions, API pricing, hidden costs, and tips to optimize your…

  • Guide
  • Productivity

Prompting guide

Complete guide to prompting with Claude Code: learn to write effective prompts, master communication techniques, and…

  • Guide
  • DevSecOps

CI/CD and cybersecurity in 2026: why it's now non-negotiable with AI agents

With the explosion of AI-generated code, a robust CI/CD is no longer a bonus: it's the defense line. Practical guide…

Articles

All articles

Filter by theme to find the guide that matches your interest.

Type
Domain

39 articles

  • Tutorial
  • Tooling

Getting started with Claude Code

Complete guide to get started with Claude Code: from installation to your first project. Everything you need to know…

  • Use case
  • Tooling

Claude Code design stack: a 1-month review

The best design skills for Claude Code in 2026: Impeccable, UI UX Pro Max, Taste Skill, Huashu Design + Playwright…

  • Guide
  • Tooling

Complete MCP guide

Complete guide to the Model Context Protocol (MCP): understand, install, and use MCP servers with Claude Code. From…

  • Use case
  • Tooling

Redoing a card with Impeccable and Playwright: the full demo

Claude Code design refactor example: we take a real Codex card and rebuild it with Impeccable and Playwright MCP, with…

  • Guide
  • Tooling

Claude Code Skills: complete guide (concept, create, examples)

Everything about Claude Code Skills: concept, step-by-step creation, real examples, official library. Automate your…

  • Guide
  • Productivity

Prompting guide

Complete guide to prompting with Claude Code: learn to write effective prompts, master communication techniques, and…

  • Guide
  • Architecture

Vision and future of Claude Code

The future of Claude Code and AI-assisted development: upcoming features, industry trends, and how to prepare for the…

  • Reference
  • Tooling

The real costs of Claude Code

Transparent analysis of Claude Code costs: subscriptions, API pricing, hidden costs, and tips to optimize your…

  • Reference
  • Productivity

Myths and misconceptions about Claude Code

Debunking the most common myths about Claude Code: what it really can and can't do, realistic expectations, and honest…

  • Tutorial
  • Security

Claude Code Security: 8 best practices + copy-paste checklist

Least privilege, MCP vetting, sandboxed config profiles, secrets scanning: 8 best practices with a ready-to-use…

  • Use case
  • Security

Leaked Anthropic API key? Step-by-step recovery (2026)

Your Anthropic API key sk-ant was leaked in a commit, screenshot, or log? Revoke it now, rotate it, audit the damage.…

  • Comparison
  • Tooling

Claude Design vs Figma: who wins the AI design race in 2026?

Claude Design (Anthropic Labs, April 2026) takes on Figma AI directly. Honest comparison: conversation vs canvas,…

  • Use case
  • Security

Never give Claude Code your API keys or vault files: what can actually go wrong

Sharing an API key or vault file with Claude Code can lead to exfiltration, log leaks, or public commits. Practical…

  • Guide
  • DevSecOps

CI/CD and cybersecurity in 2026: why it's now non-negotiable with AI agents

With the explosion of AI-generated code, a robust CI/CD is no longer a bonus: it's the defense line. Practical guide…

  • Use case
  • Productivity

Garry Tan's gstack: a critical review after one month of use

Critical review of Garry Tan's Claude Code stack (YC CEO). 35 commands, solo-founder philosophy, what works and what…

  • Comparison
  • Architecture
  • Productivity

Orchestrate a team of Claude agents like an organization

A dated tour of the tools that turn Claude sessions into a team of agents: native Claude Code, Paperclip,…

  • Guide
  • Productivity

Karpathy-Style CLAUDE.md: Analysis and FR Adaptation

A close read of the so-called Karpathy CLAUDE.md: four principles against Claude Code drift, what transfers to a team…

  • Guide
  • Productivity

Why your tokens cost more in some languages

For the same content, a sentence in French, Japanese or Hindi doesn't cost the same number of tokens as in English.…

  • Comparison
  • Tooling

Claude Sonnet 5 and Fable 5: what actually changes for Claude Code users

Claude Sonnet 5, a real complement to Opus 4.8: pricing, context window, tokenizer, adaptive thinking. And why Fable…

  • Guide
  • Tooling

Fable Is Back: What You Must Know

Fable 5 redeployed on July 1, 2026 after three weeks of suspension: full timeline, new safety guarantees, and access…

  • Reference
  • Tooling

LLM Benchmarks: Reference Tables by Category

Terminal-Bench, SWE-bench, GPQA Diamond, Arena: scores for major LLMs organized by category, each with its source,…

  • Comparison
  • Tooling

GPT-5.6 vs Claude Sonnet 5: the real comparison for Claude Code developers

GPT-5.6 (Sol, Terra, Luna) launched on July 9, 2026. Pricing, context window, TerminalBench and SWE-bench scores, and…

  • Comparison
  • Tooling

Opus 5, GPT-5.6, Kimi K3: three launches, three rankings that contradict each other

Claude Opus 5 (July 24, 2026), GPT-5.6 (July 9) and Kimi K3 (July 27) shipped weeks apart. Pricing, benchmarks, and…

  • Guide
  • Tooling

Kimi K3: the first open model in the 3T class, and what actually changes

Moonshot AI released Kimi K3 in late July 2026: 2.78 trillion parameters, a license with commercial thresholds, and…

  • Reference
  • Architecture

What Kimi K3's tech report teaches about building a frontier model in 2026

KDA, NoPE, Stable LatentMoE, Per-Head Muon: a deep dive into Kimi K3's architecture choices, the first open-weight…

  • Guide
  • Tooling

How to Read an LLM Benchmark Without Getting Fooled: The Survival Guide

SWE-bench, BrowseComp, WebDev Arena: every model announcement comes with its share of impressive scores. Nine real…

  • Comparison
  • Architecture

Open Weights vs Closed Models: Where the Gap Really Stands in July 2026

Kimi K3 tops the open-weight pack on the Intelligence Index, but licensing, hardware, and operations tell a different…

  • Guide
  • Productivity

Real Cost Per Task: What the Per-Token Price Doesn't Tell You

Tokenizer, reasoning budget, caching, long context, batching: the levers that actually determine the real bill for a…

  • Guide
  • Performance

Claude Opus 5.5: Fable 5.1-level work for 40% less than Opus 5

Anthropic released Claude Opus 5.5 on September 22, 2026: lower prices, $0.20 cache reads, faster output and a new…

  • Guide
  • Security

Fable 5.1 and Mythos 5.1: one model, two levels of safeguards

Released September 1, 2026, Claude Fable 5.1 and Mythos 5.1 are the same model with different protections. Cache reads…

  • Comparison
  • Performance

GPT-6 vs Opus 5.5: what the prices and numbers really say

OpenAI launched GPT-6 Astra on September 3, 2026, then Sol and Luna on the 22nd, the same day as Opus 5.5. Official…

  • Tutorial
  • Productivity

Cross-session messaging: your Claude Code sessions can finally talk to each other

Since August 2026, one Claude Code session can message another with ListAgents and SendMessage. How it works,…

  • Tutorial
  • Tooling

claude plugin eval: finally measure what your plugin brings

Since v2.1.269 (September 2026), Claude Code can test a plugin on a suite of cases and compare it against a session…

  • Guide
  • Security

Auto mode is now Claude Code's default: what you need to know

Since August 14, 2026, new Claude Code sessions start in auto mode on Pro, Max and Team, then on every plan from…

  • Guide
  • Security

Claude's invisible watermark: how it works and what it means for you

To comply with the EU AI Act, Anthropic adds an invisible watermark to text from its new models. How it works, its…

  • Guide
  • Security
  • DevSecOps

Anthropic's threat report (September 2026): your AI API keys are now a target

The report published September 10, 2026 describes attackers stealing AI API keys to use them against other targets.…

  • Reference
  • Productivity

What's new in Claude Code, August and September 2026: the useful recap

/design, a live /diff panel, /skill-doctor, cache diagnostics in /cost, fork mode, the Concise style, the end of…

  • Guide
  • Security
  • Tooling

Why Claude Code sometimes switches models mid-session

Fable 5.1, Opus 5.5 and Opus 5 fall back to another model when a request touches cybersecurity or biology. How this…

  • Comparison
  • Productivity

Plan mode vs Thinking mode in Claude Code: the key differences

Plan mode makes Claude propose a plan before touching code. Thinking mode makes Claude reason longer internally. Two…