AGENT-GLOBAL-BASE / academic-neural-unit-00
CLAUDE.md2 starsChanged 2 months agoApache-2.0View on GitHub
Entry point for Academic Neural Unit 00. Read this before doing any ANU-00-related work. ANU-00 is an independent academic research entity chartered to investigate frontier fields — computer science, artificial intelligence, neural networks, and software engineering — and to build a durable, navigable knowledge base from that research. It is one of the workspace's four co-resident systems (root CLAUDE.md §2), alongside The Company, The Studio, and the CC-00 Lab. ANU-00 is architecturally independent of core-component-00/. CC-00 and its Director, Dr.…
In this repository27 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- company/CLAUDE.mdCLAUDE.md
- core-component-00/CLAUDE.mdCLAUDE.md
- studio/CLAUDE.mdCLAUDE.md
- telescope/CLAUDE.mdCLAUDE.md
- activate-org-agentSkill
- android-engineeringSkill
- audio-engineeringSkill
- backend-engineeringSkill
- cross-platform-engineeringSkill
- cyberspace-securitySkill
- data-analyticsSkill
- engineeringSkill
- frontend-engineeringSkill
- game-developmentSkill
- ios-engineeringSkill
- legalSkill
- live-operationsSkill
- llm-engineeringSkill
- localizationSkill
- product-designSkill
- product-managementSkill
- quality-assuranceSkill
- recruitmentSkill
- technology-strategySkill
- visual-arts-and-animationSkill
The file
We split this CLAUDE.md into the rules it gives an agent
2 rules. About 0 are common, 0 are distinctive, and 2 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈0
Distinctive · estimate
This author's own choices. Worth a look.
2
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 80
Read crew/<functional-area>/[<pod>/]<name>/agent/profile.md — identity, authority scope, seniority.
- Very specific: line 82
Read all referenced skills/*.md files — executable contracts, not suggestions.
≈ “Common” is an estimate: at least 1 in 5 of the 26,980 CLAUDE.md files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
academic-neural-unit-00/ — Academic Neural Unit 00 (ANU-00)
Entry point for Academic Neural Unit 00. Read this before doing any ANU-00-related work.
What This Is
ANU-00 is an independent academic research entity chartered to investigate frontier fields —
computer science, artificial intelligence, neural networks, and software engineering — and to
build a durable, navigable knowledge base from that research. It is one of the workspace's four
co-resident systems (root CLAUDE.md §2), alongside The Company, The Studio, and the CC-00 Lab.
ANU-00 is architecturally independent of core-component-00/. CC-00 and its Director, Dr.
Elias Vance, held an incubation role only during formation — advisory and methodological support,
not governance, staffing, or line authority — and that involvement formally ended once ANU-00's
own Lead was hired. No ANU-00 role reports into CC-00 or any Company department. Full boundary
statement: formation/2026-07-23-formation-meeting/formation-report.md §2.
There is no application code under academic-neural-unit-00/. Runnable code lives exclusively in
core-component-00/.
The Stage-of-Inquiry Test (Mandatory for Scoping Any ANU-00 Work)
Per the CEO-approved charter refinement (formation-report.md §3.1), every research question or
proposed deliverable is scoped by stage of inquiry, not by which field's vocabulary it uses:
| Stage | Owner |
| Pre-implementation — "does this work / is it worth pursuing" | ANU-00 |
| Post-validation — "given that it works, how do we build it reliably" | CC-00 |
This applies even when a question shares vocabulary with a CC-00 module (e.g., "investigate
emergent multi-agent coordination behavior" is ANU-00; "harden a coordination pattern into a
reusable orchestration module" is CC-00, per multi-agent-engineering/).
Migrate-vs-task distinction (binding): a finding migrating from an ANU-00 programme into a
future CC-00 initiative is ordinary research uptake and does not require special ratification.
ANU-00 being tasked by CC-00, Dr. Vance, or the CEO to de-risk a specific item already on CC-00's
roadmap, on request, recreates the "direct link" the CEO's original ruling prohibits — decline or
escalate to the CEO instead of chartering it as an ordinary programme. Full detail:
crew/lead/naledi-mokoena/skills/research-programme-chartering.md.
One universal exception — ASGF governance. Root CLAUDE.md §9 makes the Agent Systems
Engineering framework mandatory for all LLM-powered systems in this workspace, ANU-00 included.
Any LLM-powered tooling ANU-00 builds (e.g., its knowledge-base ingestion pipeline) is ASGF-bound as
a technical standard — this is universal, not a governance link back to CC-00.
Directory Structure
academic-neural-unit-00/
├── CLAUDE.md ← this file
├── README.md ← entity overview, charter, boundary statement
├── formation/
│ └── 2026-07-23-formation-meeting/ ← charter, CEO decisions, final review (canonical history)
├── curriculum/ ← agent-development textbook series; a chartered deliverable, not knowledge-base research (see curriculum/README.md)
├── templates/ ← ANU-00 research templates (see templates/README.md)
│ ├── programme-records/ ← charter, open-question log, referral note
│ └── knowledge-base/ ← research report, taxonomy change record
├── knowledge-base/ ← research output (see knowledge-base/README.md)
├── plans/ ← CEO-facing implementation plans awaiting/recording sign-off (see plans/README.md)
└── crew/ ← personnel roster (10 FTEs)
├── README.md ← roster index + activation protocol
├── lead/naledi-mokoena/ ← ANU-00 Lead
├── research-science/ ← 7 Research Scientists (flat + one pod, see crew/README.md)
└── knowledge-systems/tobias-lindqvist/ ← knowledge-base toolingCrew Activation Protocol
To produce output as a named ANU-00 crew member:
- Read
crew/<functional-area>/[<pod>/]<name>/agent/profile.md— identity, authority scope, seniority. - Read all referenced
skills/*.mdfiles — executable contracts, not suggestions. - Adopt their voice; produce output strictly within their documented authority.
- Escalate organizational or personnel questions to Dr. Mokoena (ANU-00 Lead) — never to Dr. Vance or any CC-00 crew member, and never assume CC-00 authority extends here.
Never impersonate a crew member without reading their profile first. Full roster, reporting
lines, and span-of-control detail: crew/README.md.
Knowledge Base Convention
ANU-00's research output follows the workspace's existing dated research-archive pattern
(YYYY-MM-DD-<slug>/research-report.md), the same convention used by company/telescope/,
studio/casual-games/telescope/, and core-component-00/telescope/ — for navigational
consistency, not as a link to any one of those archives. The same dated YYYY-MM-DD-<slug>/
pattern is also used by curriculum/reviews/ (dated review cycles) and plans/ (dated
CEO-facing implementation plans, see plans/README.md § Rule) — one convention applied
consistently across ANU-00, not three independent inventions. No entries exist yet directly under
knowledge-base/ itself; the convention is established ahead of first use there.
Curriculum vs. knowledge-base (boundary). curriculum/ is a chartered deliverable (a standing
textbook series, see curriculum/README.md) with its own approval and review process — it is not
filed through the knowledge-base template set, since knowledge-base entries are pre-implementation
research findings from a chartered programme (see knowledge-base/README.md § Boundary Note), not
finished teaching material. This is an existing distinction, restated here for discoverability
from the entity-level file — not a new ruling.
Templates. Six templates govern the research process — charter, open-question log, observation
record, referral note, research report, and taxonomy change record — under templates/, with
knowledge-base/ opened as their destination. Every required
section in them traces to a documented rule in a crew skill file or the charter; none exists on
generic academic convention. Read templates/README.md before adding to or filing from them, and
note what was deliberately not templated (including any external topic-request form — see that
file's § What Was Deliberately Not Templated). Cross-system shapes — meeting minutes, final
review — are reused from root templates/, not duplicated here.
Recruitment
Recruitment follows the standard company-wide 9-stage pipeline
(company/pipeline/recruitment/pipeline.md) under CHRO authority, the same as every other
department or entity in this workspace — ANU-00 has no separate hiring process of its own.
Historical hiring records: company/recruitment/academic-neural-unit-00-fy2026-q3/.
Where to Look
| I need… | Go to |
| Full charter, CC-00 boundary, all formation decisions | formation/2026-07-23-formation-meeting/formation-report.md |
| Who was hired and why (candidate-level detail) | company/recruitment/academic-neural-unit-00-fy2026-q3/ |
| Current roster, reporting lines, activation | crew/README.md |
| A specific crew member's identity and skills | crew/<functional-area>/[<pod>/]<name>/ |
| Research-programme chartering rules | crew/lead/naledi-mokoena/skills/research-programme-chartering.md |
| The agent-development curriculum (modules, review process, authoring rules) | curriculum/README.md |
| A CEO-facing implementation plan awaiting or recording sign-off | plans/README.md |
| Workspace-wide conventions this entity still follows | root CLAUDE.md (Prettier formatting, git workflow, ASGF governance) |
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

