--- title: DESIGN.md, BRAND.md and skills description: The files around the MCP server that agents read: BRAND.md, the agent skills, the brand as files in a repository, llms.txt, and DESIGN.md. --- > Source: https://www.heyarchetype.com/docs/agents/files The MCP tools give an agent your brand on request. The files on this page make sure it asks, and give it the brand where it can't connect: a front page that routes each task, skills that teach the habit, a folder in your repository, and plain-text guides for agents that haven't connected yet. ## BRAND.md BRAND.md is your brand's own front page, written by your team in **Knowledge** under **Start here**. It says what the company is, the rules every task follows, and which items each kind of work needs. It opens the brief, the response an agent gets when it calls `get_brand` with no arguments. References in it, written as `[[kind:Name]]` (such as `[[template:Instagram Story]]`), reach the agent as the exact call that fetches each item. Until someone edits the starter file, it isn't served, so an agent never reads a skeleton as your brand's word. See [Knowledge](/docs/brand/knowledge) for how to write it. ## Agent skills A skill teaches an agent when to reach for the tools and what counts as done. Archetype publishes four. They hold no brand data, so they are public, and one install works for every brand you connect. | Skill | What it does | | --- | --- | | `brand-build` | Build inside the brand: orient, fetch by handle, use the brand's own values verbatim, check the result, report every gap. | | `brand-audit` | Grade work against the brand's authored values and return a worst-first fix list with exact targets. | | `brand-import` | Bring a repository's tokens and real rendered components into the brand in one reviewed bulk import. | | `repo-sync` | Connect a repository: tokens pulled from the brand, components pushed from code, kept in step by CI. | Each one is a `SKILL.md` file at `https://www.heyarchetype.com/skills//SKILL.md`, so it works in any agent that supports the convention. **Settings → Agents**, **MCP** tab, step 2 (**Add the skills**, optional) gives the install commands for Claude Code and Codex, and links to the files for other clients. For Claude Code: ```bash title="Terminal" mkdir -p ~/.claude/skills/brand-build && curl -sL https://www.heyarchetype.com/skills/brand-build/SKILL.md -o ~/.claude/skills/brand-build/SKILL.md ``` For Codex, use `~/.agents/skills/` instead. Connect the MCP server first: the skills call its tools, so without it they have nothing to do. ## The brand as files in a repository An agent working in a repository reads its files whether or not it calls a tool. The `archetype/` folder puts the brand there: | File | What it holds | | --- | --- | | `archetype/AGENTS.md` | The rules agents follow: use the tokens, check for a component first, read `brand.md` before writing copy, report gaps. | | `archetype/brand.md` | The brief as a file: BRAND.md, tokens, logo rules, voice, and an inventory of everything else. | | `archetype/tokens.css` | Every token as a CSS custom property. | | `archetype/tailwind.css` | The same tokens as a Tailwind 4 theme, when the brand has tokens to declare. | | `archetype/tokens.json` | The tokens as W3C Design Tokens (DTCG) JSON. | | `archetype/components/` | An index plus one file per component, with its real markup and CSS. | | `archetype/documents/` | The text of the brand's PDFs, one file each. | | `archetype/README.md` | How to install and refresh the folder. | The [CLI](/docs/developers/cli) writes and refreshes it with `npx archetype-os pull`, and points your root `AGENTS.md` at `archetype/AGENTS.md`. Without the CLI, download the folder as a zip: in **Settings → Agents**, open the **Repository** tab, choose **Do it by hand instead**, and use the download under **No CLI? Unzip this at your repo root.** (It shows when **Tokens** is picked and **Automatic updates** is off.) Scripts can fetch the same files over HTTP with an API key from **Settings → Agents → API**, sent as `Authorization: Bearer `: | Endpoint | Returns | | --- | --- | | `GET /api/brands//brand.md` | The brief as Markdown. | | `GET /api/brands//tokens.json` | All tokens as DTCG JSON. | | `GET /api/brands//fonts.css` | `@font-face` rules for the brand's typefaces. | | `GET /api/brands//bundle.zip` | The whole `archetype/` folder as a zip. | | `GET /api/brands//bundle.json` | The same files as JSON, which is what the CLI reads. | > [!NOTE] > A folder is a copy. It is current when you pull it, and the MCP server is always current. Use both: the folder keeps the rules in context, the server serves everything else live. ## llms.txt and llms-full.txt Two public plain-text files describe Archetype to agents that haven't connected yet: - `https://www.heyarchetype.com/llms.txt` is the index: what Archetype serves, every page of these docs as markdown, the skills, and the MCP address. - `https://www.heyarchetype.com/llms-full.txt` is the full integration guide in one fetch: setup for every client, every tool with its arguments, the `get_brand` domains in full, how to write with `update_brand`, the HTTP endpoints, the CLI, and the CI check. Both are generated from the same source as the server, so the tool reference in them always matches what the server answers. Every docs page is also served as markdown at its address plus `.md`, such as `/docs/agents/tools.md`. ## DESIGN.md DESIGN.md is an open format from Google Labs, still marked alpha: one file at the root of a repository, with design tokens in YAML at the top and prose under them on how to use them. Agents such as Claude Code, Cursor and Codex read it when `AGENTS.md` or `CLAUDE.md` points at it. Archetype's [DESIGN.md generator](/design-md) turns any website into one, free and with no account. It reads one page and its stylesheets, calls no AI model, and only writes values the site declares. A single file holds values, not parts: your real components, logos, templates and voice aren't in it, and nothing checks what the agent built. For a brand you keep in Archetype, the `archetype/` folder and the MCP server cover that ground and stay current when the brand changes. ## Next steps :::cards - [Connect an agent](/docs/agents/connect): Add the MCP server that the skills and files point to. - [The CLI](/docs/developers/cli): Pull the brand into a repository and keep it current. - [Knowledge](/docs/brand/knowledge): Write BRAND.md and the rest of the brand's written half. :::