Claude Code
Practical guides to Claude Code: plan mode, hooks, skills, subagents, MCP servers, headless runs, costs and running it remotely.
89 posts · page 1 of 4
MCP Transports: stdio vs Streamable HTTP (and What the 2026 Spec Changed)
MCP servers talk to clients over stdio (a local subprocess) or Streamable HTTP (a remote endpoint). How each works, when to choose which, how to add both to Claude Code, why the old HTTP+SSE transport is deprecated, and what the stateless 2026-07-28 specification means for building and hosting HTTP servers.
Is Claude Code Free? What You Actually Need to Use It
The Claude Code software is free to install, but using it needs a paid Claude plan (Pro, Max, Team or Enterprise) or an API account billed per token. What each option costs, what the cheapest realistic setup is, and what the "free Claude Code" guides online are really doing.
Claude Opus 5.5 Released: Near-Fable Performance at a Lower Price
Anthropic released Claude Opus 5.5 on 22 September 2026, the first model in the Claude 5.5 family. It's priced at $4/$20 per million tokens (down from $5/$25 for Opus 5), has a 1M-token context window and 128k output, always-on adaptive thinking, and is now the default model in Claude Code.
Claude Fable 5.1 and Mythos 5.1: Anthropic's Top Models Get an Update
On 1 September 2026 Anthropic released Claude Fable 5.1 (generally available) and Claude Mythos 5.1 (limited availability). Fable 5.1 costs $10/$50 per million tokens with unusually cheap $0.25 cache reads, a 1M-token context and 128k output. What it's for, what's restricted, and how to use it in Claude Code.
Claude Desktop App: AGENTS.md in Code, Wider Cowork Folder Access, and macOS 13 Required
The Claude desktop app's September and early October 2026 releases added AGENTS.md support in the Code tab, Opus 5.5 and Sonnet 5.5, attaching your home folder or whole drives to Cowork, built-in browser controls, file comments and Office previews in Code, Google Docs creation from Chat — and moved to Electron 44, which requires macOS 13 or later.
Claude Code vs Cowork: Which Claude Agent Should You Use?
Claude Code and Claude Cowork are both Anthropic agents that do the work instead of just answering. Claude Code is built for software; Cowork is built for files, documents, spreadsheets and the web. How they differ on what they touch, where they run, safety and usage — and how to pick.
Ultrathink in Claude Code: What It Does Now, and How Effort Levels Work
Ultrathink still works in Claude Code, but it no longer works the way old guides say — and "think hard" is no longer a keyword at all. How effort levels (low to max) actually control reasoning, how to set them with /effort, and when ultrathink is still worth typing.
Claude Code Routines: Scheduled, API and GitHub-Triggered Agents in the Cloud
Routines are saved Claude Code tasks — a prompt, repositories and connectors — that run on Anthropic's cloud or an organization's self-hosted environment. How to create one with /schedule or the web, use schedule, API and GitHub triggers, and manage limits and security.
Claude Code "Prompt Is Too Long": Why It Happens and How to Fix It
"Prompt is too long" and "Context limit reached" mean the conversation no longer fits in the model's context window. What fills it up, how to see what's using space with /context, and the fixes: /compact, /clear, smaller reads, fewer MCP tools and better session habits.
Claude Code Output Styles: Concise, Explanatory, Learning and Your Own
Output styles change how Claude Code talks and works for a whole session: shorter answers, explanations of each change, or leaving pieces for you to write. The five built-in styles, how to switch with /output-style, and how to write a custom style file.
Claude Code in Early October 2026: Haiku 5.5 Default, MCP 2026-07-28, Retry Controls and More
A roundup of Claude Code releases from 2.1.287 to 2.1.295 (1–8 October 2026): Haiku 5.5 as the default Haiku model, the new MCP protocol by default for stdio servers, 529 retry tuning, plugin install from a marketplace in one command, an effort setting for subagents, 1M context defaults on cloud providers, and fixes worth updating for.
Claude Code Mods: Customise Behaviour and UI With a Few Lines of TypeScript
Anthropic launched mods for Claude Code on 1 October 2026: small TypeScript modules, shipped inside plugins, that can rewrite prompts, block or retry tool calls, redact secrets, draw custom UI and add commands. How they work, how to install one with /plugin, and the security caveat — mods run with Claude Code's full access.
Claude Code /loop: Run a Prompt on Repeat (and Let Claude Pick the Interval)
/loop re-runs a prompt inside your Claude Code session — every 5 minutes, at an interval Claude chooses, or with a built-in maintenance prompt that babysits your PR. Syntax, self-paced loops, loop.md, one-time reminders, the 7-day expiry, jitter, and when to use routines instead.
Claude Code With Local Models (Ollama, LM Studio): How It Works and the Catch
You can point Claude Code at a local open-weight model through an Anthropic-compatible endpoint such as Ollama's. How the setup works with ANTHROPIC_BASE_URL, what hardware and context you need, why tool calling and quality suffer, what Anthropic does and doesn't support, and when it's worth it.
Claude Code in JetBrains IDEs: IntelliJ, PyCharm, WebStorm and More
How to use Claude Code in IntelliJ IDEA, PyCharm, WebStorm, GoLand, PhpStorm and Android Studio: install the CLI and the plugin, connect with /ide, see diffs in the IDE's viewer, share selections and diagnostics, and fix the common Esc-key and WSL problems.
How to Use Claude Code in Cursor (Extension or Terminal)
You can run Claude Code inside Cursor — either with Anthropic's extension, which installs in Cursor and other VS Code forks, or by running the claude CLI in Cursor's terminal. How to set up each, how they differ, and whether paying for both Cursor and Claude makes sense.
Claude Code Hooks Can Now Fail Closed — and Prompt Hooks Got a Security Fix
Claude Code 2.1.295 (8 October 2026) adds onFailure: "block" for command and HTTP hooks, so a hook that crashes or times out blocks the action instead of silently allowing it. 2.1.294 fixed prompt and agent hooks written as instructions sometimes allowing what they should block. What to update.
Claude Code /goal: Keep Claude Working Until the Job Is Actually Done
/goal sets a completion condition and Claude keeps taking turns until a separate model confirms it's met — no prompting each step. How to write conditions the evaluator can verify, how evaluation and check-ins work, combining it with auto mode, running it headless, and when to use /loop or a Stop hook instead.
Claude Code Fast Mode: What /fast Does and What It Costs
Fast mode makes Claude Opus answer up to 2.5x faster in Claude Code, at a higher per-token price. Which models support it, how to turn it on with /fast, why it bills from usage credits on subscription plans, and when it's worth paying for.
Claude Code Background Sessions and Agent View: Run Many Agents at Once
Agent view (claude agents) lets you dispatch Claude Code sessions that keep running in the background, peek at them, answer their questions and attach when needed. How to start background sessions with --bg and /bg, the attach/logs/stop commands, background shell jobs, worktrees, and the limits on usage and idle sessions.
Claude Code "529 Overloaded" Error: What It Means and What to Do
"API Error: Repeated 529 Overloaded errors" means Anthropic's API is at capacity for the model you're using — not that you did anything wrong or used up your plan. What a 529 is, how it differs from a 429, and the fixes: wait, switch model, and the retry settings for unattended runs.
How to Update Claude Code (and Choose Between the Latest and Stable Channels)
Native installs of Claude Code update themselves; Homebrew, WinGet, apt and npm installs don't. How to check your version, update with each method, pick the latest or stable release channel, and turn auto-updates off when you need a fixed version.
How to Uninstall Claude Code (Mac, Windows, Linux, npm, Homebrew)
Removing Claude Code depends on how you installed it: native installer, Homebrew, WinGet, apt/dnf, or npm. The exact commands for each, how to remove settings and history too, and what to do if claude still runs afterwards.
Test-Driven Development With Claude Code
Tests first is the single best way to make an AI coding agent reliable: it gives Claude a pass/fail signal to iterate against. A red-green-refactor workflow for Claude Code, prompts that stop it cheating the tests, enforcing it with hooks and /goal, and where TDD with agents falls short.