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

@dungle-scrubs/deep-research

v0.1.0

Published

dr - deterministic deep-research pipeline CLI (caller-supplied intelligence, CLI-held validation)

Vulnerabilities

Powered byPowered by Snyk
  • 0High
  • 0Medium
  • 0Low

Links

Git

Maintainers

dungle-scrubs-orgdungle-scrubs-org

Keywords

Readme

deep-research

dr is a deterministic deep-research pipeline CLI: it turns one research question into a verified, citation-traced report. Hosted deep-research tools search well and validate poorly - citations nobody checked against the pages they name. dr inverts that: the caller (a human or an agent session) supplies the intelligence - searching, judging, writing - with whatever model it chooses per step, and the CLI holds state, fetches every cited URL itself, derives claim statuses by fixed rules, and refuses to advance on anything it cannot check. Every claim in the final report carries a status traceable to fetched evidence on disk.

Spec: docs/rfc/01_deep-research-cli-deterministic-pipeline-with-caller-supplied-intelligence.rfc.md. Tracker: GitHub issues on dungle-scrubs/deep-research.

Inspiration

The pipeline design borrows from Tom's Yudame research process (workflow, methodology): two-pass retrieval with gap analysis between, a cross-validation matrix, gates between stages, and methodology baked into prompts. dr makes that machinery deterministic and fixes its known weakness - matrix entries compared tool outputs instead of underlying sources - by fetching every cited URL and deriving claim statuses from caller verdicts against the fetched text.

Install (dev)

Node via mise. No npm publish in v1.

pnpm install
pnpm build
node dist/dr.mjs --help

Skill for agent sessions

One line, no Homebrew:

ln -s "$(pwd)/skills/deep-research" ~/.agents/skills/deep-research

The skill teaches an agent session to drive the CLI: the loop, the per-step choose-model queries, and the untrusted-content warning for fetched pages.

Use

node dist/dr.mjs new "burnout in early childhood educators"
node dist/dr.mjs next
node dist/dr.mjs fulfill brief ./brief.md
node dist/dr.mjs status
node dist/dr.mjs help gaps

Runs live in YYYY-MM-DD-slug/ under the cwd, --root <dir>, or DR_ROOT. Every command takes --json (envelope {ok, run, step, errors[]}). Exits: 0 ok, 1 usage, 2 gate/validation, 3 nothing takeable, 4 internal.

Smoke

pnpm smoke

Builds, then drives a fixture run end to end (loopback citation, SSRF refusal, unreachable derivation, report gate) to done. Exits green.

Status

Tickets #11-#14 are implemented and closed: prose pipeline, claims schema and fetcher, verdicts and derivation, briefing/synthesis/finalize. This ticket (#15) adds the skill, README, and smoke recipe.

License

MIT - see LICENSE.