Workflow

This is a research note for Wireword, a small tool I am building to lint LLM agent control words. By control words, I mean short labels that can change what an agent does: route names tool names prompt macro names environment targets approval targets exact enum values the model must emit The goal is narrow: make labels that control agent behavior harder to misread, miscopy, or misroute. Of words and tokens being expensive This started with caveman-style LLM output. The useful comparison is not really cavemen. It is telegraphese: compressed language for an expensive channel. ...

Most LLM assistants don’t maintain memory between sessions. The standard workaround — a large CLAUDE.md or AGENTS.md with everything in it — breaks down quickly. What’s more, it duplicates other content in your repo, growing the documentation maintenance surface without adding value. Lately I avoid this problem by treating CHANGELOG.md as my LLM’s memory — specifically the [Unreleased] section from the format standardized by Keep a Changelog, which becomes the primary mutable state document. ...