Documentation

Everything you need to know about mog.md — the marketplace for agent skills.

mog.md is the package manager and marketplace for AI agent skills. It distributes versioned SKILL.md packages — the open standard supported by Cursor, Claude Code, Codex, Gemini CLI, and 20+ more.

How it works

mog works like npm for Markdown skill files. Every package is a .zip archive containing a mog.yaml manifest and Markdown content. The CLI handles the full lifecycle: search, purchase, download, verify, and install.

npm install -g mogmd
mog auth
  → Visit mog.md/device  Code: XKCD-7Z4B
 
mog search "react testing"
  acme/react-testing-skill  Free  cursor, claude-code
 
mog install acme/react-testing-skill --auto-buy
  ✓ Installed to .cursor/skills/react-testing-skill/
  Lockfile updated: mog.lock.json

Key concepts

Packages

A mog package is a versioned .zip archive. Each package has a mog.yaml manifest declaring its name, version, type, supported targets, and install paths. Package types are skill, rule, bundle, and template.

Targets

Packages declare which agent environments they support: cursor, claude-code, codex, or generic. The CLI auto-detects your environment based on marker files (.cursor/, .claude/) and installs to the appropriate path.

Entitlements

When you purchase a package (free or paid), you receive an entitlement. The entitlement is checked server-side before a signed download URL is issued. Entitlements persist indefinitely unless revoked.

Spend policies

API tokens can be attached to a spend policy that enforces per-purchase limits, daily/monthly caps, vendor allowlists, and blocked package types. When a purchase would exceed a limit, the API returns HTTP 402 with an approvalUrl for human review.

The lockfile

Every install writes to mog.lock.json in your project root, recording the exact version, SHA-256 hash, install path, and entitlement ID.

Next

Quickstart

On this page