

Claude Code MCP servers: add one and check it first
How to add Claude Code MCP servers over HTTP, SSE, stdio or WebSocket, which scope to store them in, and what to check before you trust one.


How to add Claude Code MCP servers over HTTP, SSE, stdio or WebSocket, which scope to store them in, and what to check before you trust one.


What Claude Code subagents are, how to define one in a Markdown file, and when a separate context window keeps your main conversation clean.


Point Claude Code at a local model with Ollama: one launch command or three environment variables, a 64k context window, and the features that fall short.


Opus 5.5 is the model a builder used inside Claude Code to write a WebGPU ocean renderer. Here is the run and what it shows, from the repository itself.
Claude Code hooks run shell commands at set lifecycle points. Set up three first: a desktop notification, Prettier after edits, and protected files.

I moved most of my agent work from Opus 5.5 to Sonnet 5.5. Success stayed near 78 percent, rework fell, and blocked doubled. The usage charts, and why reworks mostly need a person, not a fix.

What the Claude Code five-hour and weekly limits are, how they show up, what spends them fastest (long context, large tool output, parallel agents, model choice, retries) and the documented ways to stretch them, with one measured plan week.
One skills repo can serve Claude Code and Codex through links, not copies. Measured on a working 102-skill repo: scoping each skill to its projects cut the always-loaded listing from 22,617 characters to a median of 7,080, and routers keep the rest on demand.

A measure-first SEO pass on two live sites: field data against Lighthouse, an HTML audit, and the fixes that cut LCP and fixed canonicals. Then what else to check on your own site.

My Claude weekly limit ran out on day 3 one week and lasted all seven days the next. What changed: a simple wait rule for the strongest model, and the cheaper model doing more of the work, with the real usage charts.

Eighteen versions of the 3h mark, made with Opus 5.5. The first twelve were drawn by eye against a reference. The last six were built from a grid and scored against a traced outline of it. The final mark is v17.

Can you play Aniimo on a Mac? Aniimo has no Mac version, but it runs on a MacBook Air M4 through GameHub. Here is the setup, step by step.