← The Independent 100: a study

Jeffrey Emanuel

#55 in The Basement Labs, the curator’s rank and section @doodlestein Relevance to our work: 5 of 5

Bracketed tags are evidence labels: [Verified] means we read the page, file or API response ourselves, [Reported] means a source says so and we did not check the underlying thing, and [Inference] is our own reasoning. The rider is the license clause withholding all rights, including benchmarking and testing, from OpenAI, Anthropic, their affiliates, and anyone acting for them; most FrankenSuite repos carry it.

Credit

The Independent 100 list was curated by dan (@irl_danB) and published on 2026-09-24 at independent.prose.md (announcement). The ranks and section names are his, and number 100 is his open wild-card slot. This study is ours and is not endorsed by him or by anyone on the list.

What they publicly do

[Verified] Former long/short equity analyst who publishes a very large body of agent-coding tools and Rust reimplementations as Dicklesworthstone on GitHub, collected at agent-flywheel.com (github.com/Dicklesworthstone). His FrankenSuite repositories are assessed in depth by Franken Research, the project this study belongs to (fr.zeststream.ai); this entry adds only what is new.

Public work

  • franken-research (our assessment of his work) other no license stated last activity 2026-09-24

    Evidence-tiered assessment of 44 FrankenSuite repositories plus 21 parts of the wider stack. Refer here; not redone in this survey.

  • skillranker repo license file present, not recognised by GitHub last activity 2026-09-25 · 119 GitHub stars on 2026-09-24

    NEW (created 2026-09-17). Rust CLI that ranks agent skills for the next step from live session context. Uses Jev from TypeSafe.ai; ships Claude Code hooks, JSON output, abstention and local feedback. Requires a TypeSafe API key.

  • beads_bend / toon_bend repo license file present, not recognised by GitHub last activity 2026-09-25 · 5 GitHub stars on 2026-09-24

    NEW (created 2026-09-20). A law-proved Bend port of br (beads_rust), and a byte-for-byte Bend port of the toon CLI.

  • franken_code_browser repo license file present, not recognised by GitHub last activity 2026-09-25 · 6 GitHub stars on 2026-09-24

    Created 2026-09-12. Spatial Rust source browser, a native Metal Mac app; demoed on X on 2026-09-23.

  • annus-mirabilis.com other NOASSERTION last activity 2026-09-25 · 3 GitHub stars on 2026-09-24

    Created 2026-09-14. Interactive critical edition of Einstein's four 1905 papers; first public glimpse posted 2026-09-24.

  • Interior walkthrough-to-3D skill (announced, not located) other no license stated last activity 2026-09-24

    Posted 2026-09-24: a companion to his drone-footage-to-exterior-3D skill, taking phone, glasses or GoPro walkthrough footage to an interior scene.

Licenses of GitHub repositories are from the authenticated GitHub license API on 2026-09-25, one row per repository in evidence/licenses.jsonl (“no license file” means the API found none; “license file present, not recognised by GitHub” means GitHub could not classify it). Other licenses are as the source states. Check the license file before reusing anything.

Relevance to our work

5 of 5 lenses: agents, orchestration, rust, memory, verification, research-method

[Verified] franken-research exists to assess his tools (NTM, beads, Agent Mail, dcg, cass, ee, RCH). New and relevant: skillranker addresses skill routing for agents that carry many skills. The interior-scan skill pairs with his own drone-footage-to-3D skill. [Verified] On 2026-09-24 he posted that he spends 90%+ of his human time on planning, then turns plans into granular beads and lets agents choose within those constraints (x.com/doodlestein/status/2102770777502441664, x.com/doodlestein/status/2103244068218449971).

Where it already touches our work: Franken Research exists to assess his FrankenSuite repositories and parts of his wider stack (NTM, beads, Agent Mail, dcg, cass, ee).

Scored 0 to 5 against the study’s relevance rubric: 5 means public, openly licensed work squarely in our lanes that we could study or adopt now, and 1 means little connection to our work. The score is one reviewer’s judgement of how much this public work bears on our own work. It is not a ranking of people and says nothing about the person or the quality of their work.

Franken Research on Jeffrey’s work

Franken Research, the project this study belongs to, is an independent, evidence-labelled assessment of Jeffrey’s FrankenSuite repositories. Start with the map of assessed repositories, then the method, the techniques, the failure modes, the lessons and the starter kit. Each repository has its own brief, reachable from the map.

What we would study next

  1. Assess skillranker for franken-research (github.com/Dicklesworthstone/skillranker). It targets skill selection for agents that carry many skills. It depends on a paid external API (TypeSafe Jev) and carries the rider, so assess it before any trial. Effort: small.
  2. Interior walkthrough-to-3D skill, once published (x.com/doodlestein/status/2103233645985099952). A companion to his drone-footage-to-exterior-3D skill. Effort: small.

Before reusing anything: skillranker's LICENSE reads 'MIT License (with OpenAI/Anthropic Rider)'. It grants no rights to OpenAI, Anthropic, their affiliates or anyone acting for them, so it is non-OSI (read verbatim). franken-research README:21 records the same rider on 38 of 44 assessed repos. skillranker also sends session context to TypeSafe.ai, which is a privacy review item. The rider was not checked on beads_bend or the other new repos (GitHub API returns NOASSERTION).

Sources

Overall confidence in this record: High. Sources were read on 2026-09-24 and every link was checked on 2026-09-25. The full record is line 55 of people.jsonl.

Limits

Not verified: Where the interior-scan skill and his 'mtdt' music-theory tool (X, 2026-09-23) are published. His own claims of 2T tokens and ~300k GitHub commits in 12 months (x.com/doodlestein/status/2103169939310018902, x.com/doodlestein/status/2102961628098752805). Whether skillranker is already in franken-research: no assessment of it was found.

This record comes from a first-pass survey of public material by an AI agent session on 2026-09-24, edited for publication on 2026-09-25. Nothing was installed or run for it. Roles, stars and licenses change; see the study’s limits.

Request a correction

Is something about this record wrong or out of date, or would you rather not be covered? Open a correction (a GitHub issue form with this page’s address filled in). A request to remove a record is honoured without argument; accepted corrections are recorded in the changelog with the date.

Help fix it

Each opens a GitHub issue form with this page’s address filled in. You need a GitHub account.

Made by Joshua Nowak (ZestStream) with AI coding agents. Not affiliated with or funded by Jeffrey Emanuel; Joshua uses his public tools and is a paying subscriber to jeffreys-skills.md.

Source on GitHub MIT licensed