agentleFS
daromsartofdaromsartof/daroms-speed-site/docs/llms.txt

daroms-speed-site

llms.txt0 starsChanged 2 days agoMITView on GitHub

A Next.js framework and Claude Code workflow that turns a brief into a varied, production-grade website at low token cost.

The file

Files
llms.txt
# daroms-speed-site

> A Next.js framework and Claude Code workflow that turns a brief into a varied, production-grade website at low token cost.

## Docs

- [daroms-speed-site](https://daromsartof.github.io/daroms-speed-site/index.md): A Next.js framework and Claude Code workflow that turns a brief into a varied, production-grade website at low token cost.
- [Getting started](https://daromsartof.github.io/daroms-speed-site/getting-started.md): Create a site with one command, open it in Claude Code, and let the /dss-site skill take it from brief to deploy.
- [Demo: Clear to Board](https://daromsartof.github.io/daroms-speed-site/demo.md): A real site built by the dss agent from one brief: an independent guide to Europe's ETIAS and EES rules, with an in-browser checker that spots fake ETIAS websites.
- [For AI agents](https://daromsartof.github.io/daroms-speed-site/agents.md): The operating manual for an agent (Claude Code or any coding agent): what to read, how to start a site, the contract every site follows and the checks to run before saying done.
- [Architecture](https://daromsartof.github.io/daroms-speed-site/architecture.md): Versioned infrastructure in core packages, owned visual code in the site, data files the CLI rewrites, generated files nobody edits.
- [Design DNA](https://daromsartof.github.io/daroms-speed-site/design-dna.md): Each site rolls a deterministic, accessible design identity that avoids the combinations of recent sites and the usual generated-site tells.
- [AI layer](https://daromsartof.github.io/daroms-speed-site/ai-layer.md): How dss keeps Claude Code fast and cheap: small always-on context, rules by path, forked workers, guard hooks, a router and a shared brain.
- [Modules and data](https://daromsartof.github.io/daroms-speed-site/modules.md): Optional features install site-owned code, environment documentation, CSP sources and manifest entries, and plug into generated slots.
- [Deploy, security and SEO](https://daromsartof.github.io/daroms-speed-site/deploy.md): Static by default, secure headers and CSP from the manifest, previews never indexed, one command per target.
- [Visual edits with AimKit](https://daromsartof.github.io/daroms-speed-site/aimkit.md): Pick an element in the browser, type the change, and Claude Code opens the exact file and line.
- [Factory: brain, sites, batch, upgrades](https://daromsartof.github.io/daroms-speed-site/factory.md): What makes dss a production line: a memory shared by all sites, a registry, batch creation, upgrades and releases.
- [CLI reference](https://daromsartof.github.io/daroms-speed-site/cli.md): Every dss command, generated from the CLI itself. In a site run them as `pnpm dss <command>`.

## Catalog

- [Catalog](https://daromsartof.github.io/daroms-speed-site/catalog.md): tokens, components, sections, modules, archetypes, font pairs, package APIs

## Optional

- [Everything in one file](https://daromsartof.github.io/daroms-speed-site/llms-full.txt): all pages, the CLI reference and the catalog
- [Source code](https://github.com/daromsartof/daroms-speed-site): the framework repository

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.