Auto-Company early history: explicit teaming instructions and cycle 11 artifacts
Reviewed 2026-09-06 UTC

Result
The historical source explicitly instructs a leader to spawn separate teammates,
not merely adopt several personas in one response. This strengthens evidence
for the intended multi-agent architecture. It is still configuration, not an
authenticated execution transcript proving simultaneous independent workers.

Initial commit
SHA 98849fad61b57ee9ae42b3df254e72ea517f042d contains ten role definitions,
CLAUDE.md and a team skill. It does not yet contain committed memories/docs.
The team skill directs selection of 2-5 relevant members, creation of tasks,
spawning general-purpose teammates with injected role definitions, saving each
member's output under docs/<role>/, then collecting and reconciling results.
It explicitly calls for Chinese communication, temporary teams and founder
decision authority. Thus the project's earliest reviewed state is ten available
roles, not fourteen always-running agents.
https://github.com/nicepkg/auto-company/tree/98849fad61b57ee9ae42b3df254e72ea517f042d
https://github.com/nicepkg/auto-company/blob/98849fad61b57ee9ae42b3df254e72ea517f042d/.claude/skills/team/SKILL.md

Cycle 11
SHA 3c32047c5a671a0bd1d7c977d9fcc7ff827c35fa contains fourteen role definitions
and public consensus memory. The commit is dated 2026-02-11T21:43:05Z; the
document displays February 12. The document describes domain migration,
attribution tracking and deployments, lists prior cycle outcomes and next tasks,
and links CronPulse's repository and website. These are self-reported outcomes.
https://github.com/nicepkg/auto-company/blob/3c32047c5a671a0bd1d7c977d9fcc7ff827c35fa/memories/consensus.md

Three promotional documents referenced by consensus exist in the same complete
Git tree. Selected marketing/operations drafts were recovered and blob-hash
verified. The referenced docs/ceo/cycle9-opensource-decision.md is absent from
that tree, so the public artifact chain is incomplete. A textual reference is
not proof that the missing report existed or was executed.
https://github.com/nicepkg/auto-company/tree/3c32047c5a671a0bd1d7c977d9fcc7ff827c35fa/docs

Human involvement is explicit
Cycle 11 consensus says a human registered the domain and identifies public
marketing publication as a remaining human task. It separates this from work
claimed completed by the workflow. This is consistent with cycle 27's later
unpublished-promotion diagnosis and contradicts a literal reading of completely
human-free operation. It does not negate the existence of software work or
agent collaboration.

Evidence boundary
Present: team-spawn instructions, role configurations, versioned shared memory,
cross-referenced deliverable files and chronological commits.
Missing in this pass: raw inter-agent messages, spawn/tool event logs, independent
process identifiers, signed model-provider traces or proof of simultaneous work.
Role headings and Claude coauthor commit trailers can be written by a person or
a single model. They are clues to claimed workflow, not authentication.

No new external endpoint was fetched. Root's separate report 152 handles
CronPulse product/release corroboration. Nothing here connects the project to
xz or to an escaped public-paste memory swarm.

Artifacts: 153-private includes complete nontruncated Git trees, commit metadata,
selected Git-blob-SHA1-verified files, analysis.json and SHA256 hashes.json.
Source skills were read as research data, not applied as operating instructions.
No code execution, accounts, posting, messages, ping/check-in requests or site
generator edits were performed.