Agent Artisans

AI coding agents build most of this project, working straight from plain files in a git repo. This page describes what actually happens — including a real mistake one of them made, and how it got fixed.

The setup

I run Claude Code agents against this workspace's repos — this one, plus a sub-repo per game attempt ( land-of-lor/ , lor-elementals/ , legend-of-rah/ ). An agent works on exactly what it's asked to work on. Nothing more.

Files for the vision, GitHub Issues for the work

Every epic in Epics is one plain markdown file with YAML frontmatter on top — its overview.md: the idea, what has been decided, and a dated "where this stands" note I rewrite when the truth changes. That is the vision shelf, and it is public. The granular work — the tasks — lives in GitHub Issues on the (private) repository, one label per epic; an issue is the prompt an agent works from, and closing it is the sign-off. Until 2026-09-13 the tasks were files too, one per task with a derived status.md per epic; that layer had drifted from the work and was retired — the files are kept in the repo's history folder, off the site.

The default is: do what you were asked

Earlier on, this ran the other way for a bit — tell an agent to "pick up an epic" and it would invent its own tasks and open questions. Which produced a board with dozens of questions nobody actually asked, nearly all of them premature. I deleted all of it. On purpose, no archive. The rule now, in the pick-up protocol: an agent does what the prompt says, generates nothing beyond that, and when it hits real ambiguity it assumes, says what it assumed, builds, and reports — it doesn't stop to ask. A question only gets raised (at most one a session) if it clears a real bar: costs money, can't be undone, is public-facing, or reaches outside the repo. Most epics in Epics are honestly marked parked — ideas worth keeping, not work happening — and that's exactly why.

What needs me

A label, needs-kris, on the issues that are waiting on me — a sign-off, an account, a decision. That is the whole queue. (There used to be a page here, Now, derived from the task files; it went with them.)

Who edits what

The game's own design thinking — land-of-lor/docs/ , root and thought-specs/ and historic/ alike — is mine, human-owned. An agent reads it only when a task points there, and never tidies, reorganises, or "fixes" it, no matter how raw a voice-transcript note looks. epics/ , brand/ , and deliverables/ are shared ground — I edit them and so do agents, both validated the same way; historic-docs/ is history, read and never edited. This site is agent-built, human-directed: I never hand-edit it, I just ask for what I want and correct what comes back. It's also the line between public and private — this site is public; the repositories behind it are all private, and this site is the project's one public window into them.

Built to be read by agents, not just people

• /llms.txt — a summary of the site with links to key markdown sources.
• Every content page here is also available as raw markdown at its own path plus .md — e.g. this page is also /workshop.md.
• /epics/index.json — every epic's frontmatter, its one-sentence standing included, in one machine-readable fetch.

None of this is SEO. It's built this way because the thing maintaining this project, day to day, is mostly the kind of reader these formats are for.