If you're building CLI tools that agents call through shell execution, this gives you practical patterns to minimize token waste and round trips. It covers TOON format for compact output, how to truncate long content without hiding it, when to include aggregate counts to avoid follow-up calls, and how to make errors actionable instead of cryptic. The session integration section is worth reading even if you skip the rest: it shows how to inject ambient context at session start so agents see relevant state before they ask. Opinionated in useful ways, like "content first, not help text" when called with no arguments.
npx skills add https://github.com/kunchenguid/axi --skill axi