cfg.md  ·  the full concept

Your AI configuration should be portable, versioned, and yours.

A system of record for the instructions, context, skills, and rules that decide how your agents behave — broken into atomic assets, versioned independently, and rendered into whatever format each tool expects.

Concept v0.1 · working draft · ← back to overview
The premise

Files are renderings. Assets are the source of truth.

A CLAUDE.md is not the unit of value — it's an output. The real substance is smaller: one preference, one constraint, one heuristic, one fact about how you work. Once those are atomic they can be versioned, encrypted, recombined, shared selectively, and compiled to any target.


The problem, concretely

Today

The same preference lives in a Claude Code project, a ChatGPT custom instruction, a Cursor rules file, and an Obsidian note — four syntaxes, quietly drifting apart. Personal facts sit beside reusable structure, so sharing means hand-sanitizing first. Nothing answers the basic question: what is my current setup?

How it composes
ASSETS preference constraint skill identity fact secret ENVIRONMENT composed + versioned RENDERED TARGETS CLAUDE.md AGENTS.md .cursor/rules skill manifests MCP / tool config
One source of truth, many renderings. Secret values never leave the client in plaintext.

The loop the first version has to prove
  1. Import an existing config — a file, a folder, a repo — without losing the original form.
  2. Review the proposed asset boundaries. The split is AI-assisted; the decision stays yours.
  3. Classify each asset public, private, or secret.
  4. Compose the assets you want into a named environment.
  5. Publish a reusable module, or keep the whole thing private.
  6. Fork someone else's public module — its structure, none of their personal data.
  7. Personalize the values it asks you for.
  8. Render the result to at least two agent-specific formats.
Principles
What this is not

Not an agent runtime. Not a replacement for Git. Not a prompt observability platform. Not an optimizer that quietly tunes you without asking. The first job is the configuration lifecycle — import, version, classify, compose, render. Marketplace, teams, and governance are all downstream of that working first.