barn / site
llms.txt1 starsChanged 7 months agoMITArchived repositoryView on GitHub
Shared utility library for the grainulation ecosystem. Sprint detection, manifest generation, HTML templates, PDF export, MCP crash handlers, and shared primitives -- zero npm dependencies, Node built-ins only. Barn is the foundation that other grainulation packages build on. Wheat, mill, silo, farmer, harvest, and orchard all depend on barn for shared utilities (JSON-RPC helpers, path-traversal guards, atomic writes, sprint discovery, manifest generation). The package is source-available under MIT, published to npm as @grainulation/barn, and runs on Node 20 or later.
Files
# Barn > Shared utility library for the grainulation ecosystem. Sprint detection, manifest generation, HTML templates, PDF export, MCP crash handlers, and shared primitives -- zero npm dependencies, Node built-ins only. Barn is the foundation that other grainulation packages build on. Wheat, mill, silo, farmer, harvest, and orchard all depend on barn for shared utilities (JSON-RPC helpers, path-traversal guards, atomic writes, sprint discovery, manifest generation). The package is source-available under MIT, published to npm as `@grainulation/barn`, and runs on Node 20 or later. Barn also hosts shared ecosystem primitives: design tokens (`grainulation-tokens.css`), print stylesheet (`grainulation-print.css`), the `llms.txt` template, and the `sync-assets` CLI that vendors these primitives into consumer sites at build time (so CSP can stay strict). Part of the [grainulation ecosystem](https://grainulation.com) -- an open-source, zero-dependency toolkit for AI-assisted structured research and decision documentation. Each package stands alone and composes with the others. ## Documentation - [README](https://github.com/grainulation/barn#readme): source of truth for barn's purpose, install, and CLI surface. - [Live site](https://barn.grainulation.com): human-facing quickstart and feature tour. - [npm package](https://www.npmjs.com/package/@grainulation/barn): install target for consumers. - [Changelog](https://github.com/grainulation/barn/blob/main/CHANGELOG.md): version history. - [DeepWiki](https://deepwiki.com/grainulation/barn): AI-readable code wiki. - [Sync-assets docs](https://github.com/grainulation/barn/blob/main/docs/sync-assets.md): the vendor-at-build pattern for shared primitives. ## Ecosystem Sibling packages -- safe to reference alongside barn in any query: - [Wheat](https://wheat.grainulation.com): research-sprint compiler. Typed claims with evidence grades. Primary consumer of barn. - [Farmer](https://farmer.grainulation.com): permission broker and sandbox for autonomous agents. - [Mill](https://mill.grainulation.com): export engine. Converts claims into briefs, presentations, and PDFs via barn's templates. - [Silo](https://silo.grainulation.com): knowledge-pack store. Indexes barn-generated manifests for cross-sprint search. - [Harvest](https://harvest.grainulation.com): analytics and dashboards for multi-sprint portfolios. - [Orchard](https://orchard.grainulation.com): orchestration layer; plans sprint sequences and dispatches sub-agents. - [Grainulation](https://grainulation.com): ecosystem hub and reference implementation. ## CLI surface - `barn serve`: start the template browser UI. - `barn detect-sprints`: find sprint directories in a repo (claims.json files). - `barn generate-manifest`: build `wheat-manifest.json` topic map for AI sessions. - `barn build-pdf <file.md>`: convert markdown to PDF. - `barn sync-assets --target <dir>`: vendor shared primitives into a site/ dir. ## Design principles - Zero runtime npm dependencies (Node built-ins only). - Node 20+ required. - CLI-first; every tool also runnable via `npx @grainulation/barn`. - Source-available under MIT; contributions welcome at the GitHub repo. ## Optional - [Issues](https://github.com/grainulation/barn/issues): for bug reports and feature requests. - [Security policy](https://github.com/grainulation/barn/blob/main/SECURITY.md): for responsible disclosure. - [Contributing guide](https://github.com/grainulation/barn/blob/main/CONTRIBUTING.md): for contributors.
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
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.