← The Independent 100: a study

Dan Shipper

#38 in The Sensemakers, the curator’s rank and section @danshipper 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.

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

CEO of Every, an AI newsletter and software company [Verified: every.to]. Posts same-day 'vibe checks' of new models and keeps a public personal writing benchmark [Verified: x.com/danshipper/status/2102439671842435417].

Public work

  • Compound Engineering plugin (Every) repo MIT last activity 2026-09-24 · 25,258 GitHub stars on 2026-09-24

    36 skills for coding agents around a plan-work-review-compound loop; runs on 14 hosts incl. Claude Code, Codex, Cursor, Grok Bot. Maintained by Kieran Klaassen and Trevin Chow, not Dan [Verified: README]

  • Compound Engineering guide blog no license stated

    The method behind the plugin, bylined Kieran Klaassen [Verified]

  • Dan's Editorial Checks other no license stated last activity 2026-09-22

    Personal benchmark: 5 real writing tasks, script checks plus LLM-judge checks (judge is always Claude), per-model scoreboard with outputs and JSON feed [Verified]

  • proof-sdk (Every) repo MIT last activity 2026-08-27 · 1,111 GitHub stars on 2026-09-24

    Collaborative markdown editor with a provenance model and an agent HTTP bridge [Verified: README]

  • Every vibe checks newsletter no license stated last activity 2026-09-22

    Head-to-head model tests on Every's own work [Verified: link in his post]

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, evals, writing, business

Every's MIT plugin is a widely used skills-and-loop system directly comparable to skill libraries, beads and negative-evidence ledgers; his editorial checks are a small, public per-person eval for writing voice. Score reflects Every's work; Dan is CEO, not the plugin maintainer.

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.

What we would study next

  1. Compound Engineering plugin, the 'compound' step (github.com/EveryInc/compound-engineering-plugin). A 25k-star reference for learning capture, comparable to skill libraries, negative-evidence ledgers and ee Effort: medium.
  2. Dan's Editorial Checks (checks.every.to/p/dans-editorial-checks). Template for a personal, script+judge writing benchmark Effort: small.
  3. proof-sdk provenance model (github.com/EveryInc/proof-sdk). Provenance marks and an agent bridge for documents; a reference design for document provenance Effort: medium.

Before reusing anything: compound-engineering-plugin, proof-sdk, hands-on-deck, tend: MIT. compound-knowledge-plugin, claude_commands, compound-writing, Marketing-OS report no license: all rights reserved. Plugins install third-party prompts and possibly hooks; scan before install.

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 38 of people.jsonl.

Limits

Not verified: Plugin skill contents not read beyond README; whether it ships hooks; judge-check rubric details in editorial checks.

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