npm package discovery and stats viewer.

Discover Tips

  • General search

    [free text search, go nuts!]

  • Package details

    pkg:[package-name]

  • User packages

    @[username]

Sponsor

Optimize Toolset

I’ve always been into building performant and accessible sites, but lately I’ve been taking it extremely seriously. So much so that I’ve been building a tool to help me optimize and monitor the sites that I build to make sure that I’m making an attempt to offer the best experience to those who visit them. If you’re into performant, accessible and SEO friendly sites, you might like it too! You can check it out at Optimize Toolset.

About

Hi, 👋, I’m Ryan Hefner  and I built this site for me, and you! The goal of this site was to provide an easy way for me to check the stats on my npm packages, both for prioritizing issues and updates, and to give me a little kick in the pants to keep up on stuff.

As I was building it, I realized that I was actually using the tool to build the tool, and figured I might as well put this out there and hopefully others will find it to be a fast and useful way to search and browse npm packages as I have.

If you’re interested in other things I’m working on, follow me on Twitter or check out the open source projects I’ve been publishing on GitHub.

I am also working on a Twitter bot for this site to tweet the most popular, newest, random packages from npm. Please follow that account now and it will start sending out packages soon–ish.

Open Software & Tools

This site wouldn’t be possible without the immense generosity and tireless efforts from the people who make contributions to the world and share their work via open source initiatives. Thank you 🙏

© 2026 – Pkg Stats / Ryan Hefner

@arnilo/prism-work

v0.12.1

Published

Prism work connectors, Office document capabilities, and bounded document-reader subpaths.

Readme

@arnilo/prism-work

Prism work connectors, Office document capabilities, and bounded document-reader adapters. Import only a subpath; this package has no activating root barrel.

| Subpath | Contents | | --- | --- | | @arnilo/prism-work/connectors | Microsoft 365 and Google Workspace adapters, work tools, drafts, approvals, idempotency, and limits. | | @arnilo/prism-work/connectors/microsoft365 | Microsoft 365 CLI adapter. | | @arnilo/prism-work/connectors/google-workspace | Google Workspace CLI adapter. | | @arnilo/prism-work/connectors/drafts | Draft stores and approval helpers. | | @arnilo/prism-work/documents | Prism Document Model, OOXML generate/parse/patch/preview, and bounded fidelity reporting. | | @arnilo/prism-work/sheets | CSV/XLSX ingest, exact-decimal safety, and bounded schema inference. | | @arnilo/prism-work/diagrams | draw.io embed model, canonical XML, origin validation, and bounded postMessage protocol. | | @arnilo/prism-work/document-extraction | Optional local Markdown conversion (@firecrawl/anydoc). Scanned PDFs fail closed unless the host runs the packaged Docling worker. No hosted OCR. | | @arnilo/prism-work/document-reader | Bounded PDF/DOCX literal-text extraction; optional parser peers fail closed. | | @arnilo/prism-work/sandbox | Host-pinned work sandbox image digest and createWorkComposition. | | @arnilo/prism-work/skills | loadWorkSkills() — vendored Hermes MIT docx/xlsx/powerpoint/pdf. | | @arnilo/prism-work/tools | createOfficeTools filesystem/artifact office tools. |

Install

bun add @arnilo/prism @arnilo/prism-work
import { createWorkTools } from "@arnilo/prism-work/connectors";
import { generateDocument } from "@arnilo/prism-work/documents";

Dependencies and trust boundaries

  • Office APIs are in-memory only: no filesystem, network, or process.env access.
  • mammoth and pdf-parse are optional peers of /document-reader; it refuses creation if selected defaults are unavailable.
  • @firecrawl/[email protected] is an optional peer of /document-extraction. Conversion stays local; the subpath never passes hosted OCR options or reads an API key. Docling OCR is a host-provisioned docling/ocr.py worker, not an npm dependency. createDocumentIngest adapts an extractor to the wiki hook and a RAG parser without importing the memory package.
  • Caps fail closed before output; embedded document content is not fetched or executed.