Whitepaper

A Skill Provenance and Royalty Marketplace for AI Agents

AI agent runtimes increasingly generate reusable skills, but those skills are trapped inside the runtime that produced them — no portable record of authorship, no way to verify what a consumer is about to run, and no mechanism to compensate authors when their work is reused. This paper specifies the manifest format, the on-chain settlement contract and its conservation invariants, the royalty model, the threat model, and the off-chain architecture, and argues that a tokenless, per-invocation design is the right primitive for an emerging skill economy.

Download PDFOpen in new tab16 pages · PDF · v0.1
What’s inside
01Introduction

The skill-economy thesis and why the value stays trapped today.

02Prior work

Hermes, OpenClaude, MCP, and existing registries — what they do and don't provide.

03Protocol

Skill manifests, DID identity, content addressing, and canonical signing.

04Contract

AtriumRegistry design, conservation invariants, and the pull-payment pattern.

05Economics

Per-invocation pricing, the royalty cascade, and the tokenless thesis.

06Security

Threat model, mitigations, and open issues.

07Deployment

Base rationale, indexer + interface architecture, and governance.

08Comparison

Atrium vs npm, PyPI, Hugging Face Hub, the GPT Store, and agentskills.io.

09Future work

Encrypted bodies, ZK benchmark proofs, and cross-chain reputation.

The whitepaper source (Markdown + diagrams) lives in the repository; the PDF is built reproducibly in CI.