nexuschainsnexuschains/operator-os/CLAUDE.md

operator-os

CLAUDE.md0 starsChanged 5 months agoMITView on GitHub

Route first. Retrieve, don't pre-load. Full explanation: docs/ai-os-framework.md.

Reads credentials

We split this CLAUDE.md into the rules it gives an agent

6 rules. About 0 are common, 2 are distinctive, and 4 are very specific to this project.

≈0
Common · estimate
Many files like this have a rule of this kind.
≈2
Distinctive · estimate
This author's own choices. Worth a look.
4
Very specific
Tied to their project's names, files or tools. Probably skip.

Common
Distinctive
Very specific
could be automatic: a setting could enforce it

Very specific:
If this is your first session: run /onboard — it will guide you through imprinting the OS with your identity, domains, connections, and …
line 22
Very specific:
If you have an existing imprint: check operators/<your-slug>/IMPRINT.md for any open handoffs or pending cadence items.
line 23
Very specific:
If something feels stale: run /audit to grade the workspace against its own standards, then /level-up to surface the improvement queue.
line 24
Very specific:
Never commit credentials. Use .env.local (gitignored).
line 43
Distinctive:
Never leave a mid-phase swarm build without a handoff document.
line 44
Distinctive:
Read before editing any file.
line 46

≈ “Common” is an estimate: at least 1 in 5 of the 25,680 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.

Keep what fits and drop the rest. Your version, ready for your agents.

Files

CLAUDE.md

operator-os — Root Router

Route first. Retrieve, don't pre-load.

Need	Go here
What this OS is and how it works	`docs/ai-os-framework.md`
How persistent knowledge works	`docs/protocols/persistent-knowledge.md`
How multi-agent swarms are structured	`docs/protocols/multi-agent-coordination.md`
How to extend the OS with new skills/agents	`docs/protocols/capability-extension.md`
Skill naming, model pins, conventions	`docs/conventions/`
Wiki routing (what's in the knowledge base)	`wiki/ROUTER.md`
Swarm protocol (role taxonomy, handoff, HITL)	`swarms/PROTOCOL.md`
Run the three rituals	`/onboard` · `/audit` · `/level-up`
See a working end-to-end example	`swarms/example-research-swarm/CLAUDE.md`
Your operator imprint	`operators/<your-slug>/IMPRINT.md`

Session start checklist

If this is your first session: run /onboard — it will guide you through imprinting the OS with your identity, domains, connections, and first swarm.
If you have an existing imprint: check operators/<your-slug>/IMPRINT.md for any open handoffs or pending cadence items.
If something feels stale: run /audit to grade the workspace against its own standards, then /level-up to surface the improvement queue.

The Four Cs (tl;dr)

Layer	Question answered	Lives in
Context	What does the OS know?	`wiki/`
Connections	What can it reach?	`.mcp.json` · `.env.example`
Capabilities	What can it do?	`.claude/skills/` · `.claude/commands/` · `swarms/`
Cadence	What runs on rhythm?	`.claude/settings.json` hooks · `/loop` · `/schedule`

Full explanation: docs/ai-os-framework.md.

Rules

Never commit credentials. Use .env.local (gitignored). Only ${VAR} references enter .mcp.json.
Never leave a mid-phase swarm build without a handoff document.
Plan before 3+ step tasks. Spec before build.
Read before editing any file.
Agents work inside the workspace; the workspace governs the agents.

Download now (ZIP)

In this repository11 other files it gives its agents.
- wiki/CLAUDE.mdCLAUDE.md
- cross-linkerSkill
- find-skillsSkill
- skill-creatorSkill
- summarize-sourceSkill
- swarm-conformSkill
- swarm-scaffolderSkill
- tag-taxonomySkill
- wiki-ingestSkill
- wiki-lintSkill
- wiki-statusSkill

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

What did you use it for? e.g. Reviewing pull requests in a Rails app

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.

Check your setup, free