Tips

Tools Full comparisons and context in my 2026 AI tech stack post. This is just what you need installed to follow the workflow below. Claude Code If you’re new, start with the cheat sheet and Anthropic best practices. Security — set this up first: Claude Code Security Hooks — 7-layer prompt injection defence, read guards, canary files Lock down your .env and any git-secret files in .claude/settings.local.json before anything else MCP: Context7 — library/API docs on demand DeepWiki — open source repo documentation Skills: ...

Introduction I came across caveman-compression — a tool that compresses text into a token-efficient “caveman” format before sending it to an LLM. The pitch is simple: It can cut 30-65% of tokens depending on the content, which at Claude Opus prices adds up fast. I immediately wanted to wire it into Claude Code so compression would happen automatically on every prompt. The obvious hook was UserPromptSubmit. ...

Just a quick one here, but I used this a lot today and realised after chatting to some other devs that a lot of people don’t know about this trick. That trick is: History Expansion Let’s say you are SSH’d (or SSM’d on AWS if you want to be more secure) onto a Linux box and you want check the status of a service with systemctl status cassandra.service You see that the service is exited for some reason, and you want to restart it after determining that’s all that is needed. ...