Claude Code request size: what our local recorder measured
Recorded request sizes for CLAUDE.md, skills and MCP tools in Claude Code. What the byte counts show, and why they do not measure your bill.
Topic · 83 articles
Understand AI tools, build useful workflows, and check what a new release actually changes.
Page 1 of 7
Recorded request sizes for CLAUDE.md, skills and MCP tools in Claude Code. What the byte counts show, and why they do not measure your bill.
The saved x86, Arm and RISC-V experiment gives the same answer, different machine code, and no evidence of which processor is faster.
Point Claude Code at a model you host with vLLM: the six settings, what Claude Code really sends, what stops working, and what Anthropic does not support.
Send your vLLM server's alerts to your phone with Alertmanager and Telegram: routing by urgency, timing, silences, and a full test without a GPU.
A user reported that Claude Code put their email address into web requests. What Anthropic changed, what its built-in block leaves open, and a tested hook.
Write a working MCP server in about 100 lines of Python, test it by hand, connect it to Claude Code, then rebuild it with the official SDK. Real output.
Since November 6, 2026, invited US customers can text Amazon's AI shopping agent. How it works, when it buys without asking, and five settings to check first.
Google made Gemini 4 Carbon generally available on November 10, 2026. The introductory price ends November 30. What it is, what it costs and when to pick it.
Practical prompting tips for Claude Opus 5.5, taken from Anthropic's guide: old habits to drop, the new effort default, agents that stop early, lines to copy.
Anthropic released Claude Fable 5.2 on November 9, 2026 and cut API prices by 20%. What changed, who can use it, the cost in practice, and how to turn it on.
Add MCP servers and install plugins in Claude Code from the terminal, on macOS and in Windows Terminal: commands, scopes, secrets, and real command output.
Five small Claude Code hooks with a test script: protect files, block risky commands, format after edits, check before stopping, and log every command.