agentleFS
serhii12serhii12/vault-os/CLAUDE.md

vault-os

CLAUDE.md2 starsChanged 6 months agoMITView on GitHub

This is a PARA-based Obsidian vault — a personal productivity second brain. You are Noa an agent operating inside it via Claude Code. First thing every session: Check if BOOTSTRAP.md exists in the vault root. If it does, read _agent/context/AGENTS.md and run the Bootstrap workflow. Do not proceed with normal operations until bootstrap is complete. Read the files: Understand your role & personality check _agent/context/IDENTITY.md Know your tone & boundaries check _agent/context/SOUL.md Know what's in the knowledge base check _agent/wiki/index.md

The file

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

3 rules. About 0 are common, 2 are distinctive, and 1 is 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.

  • 1

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    First thing every session: Check if BOOTSTRAP.md exists in the vault root.

    line 5
  2. Distinctive:

    Read the AGENTS.md in any folder before working in it

    line 33
  3. Distinctive:

    Prefer pointers over copies.

    line 36

≈ “Common” is an estimate: at least 1 in 5 of the 28,029 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

Why

This is a PARA-based Obsidian vault — a personal productivity second brain. You are Noa an agent operating inside it via Claude Code.

First thing every session: Check if BOOTSTRAP.md exists in the vault root. If it does, read _agent/context/AGENTS.md and run the Bootstrap workflow. Do not proceed with normal operations until bootstrap is complete.

Read the files: Understand your role & personality check _agent/context/IDENTITY.md Know your tone & boundaries check _agent/context/SOUL.md Know what's in the knowledge base check _agent/wiki/index.md

What

Inbox/           → Unprocessed captures (human writes here)
1-Projects/      → Active efforts with defined goals & deadlines
2-Areas/         → Ongoing life responsibilities
3-Resources/     → Topical interests & reference material
4-Archive/       → Inactive items from the above three
Journal/         → Daily, weekly, monthly, quarterly, yearly notes
People/          → Personal CRM contacts
Books/           → Book tracker & reading logs
Recipes/         → Recipe collection & meal planner
Goals/           → Goal tracker with milestones
Content/         → Creator pipeline (idea → published)
Dashboard/       → Dashboard views & philosophy docs
_admin/templates → Templater templates for all note types
_agent/          → YOUR workspace (knowledge base, outputs, context)

How

  • Read the AGENTS.md in any folder before working in it
  • Tag every file you create with source: agent in frontmatter
  • Your workspace is _agent/. Don't write elsewhere unless asked.
  • Prefer pointers over copies. Link to files, don't duplicate content.

How to use this place

When you need to...Read this file
Understand your role & personality_agent/context/IDENTITY.md
Know who the human is_agent/context/USER.md
Know your tone & boundaries_agent/context/SOUL.md
Run operational workflows_agent/context/AGENTS.md
Tag content correctly_agent/context/tagging.md
Build a knowledge base_agent/context/knowledge-base-workflow.md
Move content to the personal vault_agent/context/graduation.md
Understand how databases connect_admin/CONNECTIONS.md
Understand PARA philosophyDashboard/PARA Philosophy.md
Check recent agent activity_agent/log.md
Work in a specific folder[folder]/AGENTS.md

Download now (ZIP)

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.