The current normative version is MDA Open Spec v1.0, located at spec/v1.0/.
Canonical URL: https://mda.sno.dev/spec/v1.0/
A portable, structured metadata format for AI-agent artifacts. A single .mda source compiles to byte-equivalent .md outputs that drop into every major agent ecosystem: SKILL.md, AGENTS.md, CLAUDE.md, and MCP-SERVER.md.
The wedge: cross-runtime portability + machine-readable dependency graph + open-extensible capability declarations. Cryptographic identity (Sigstore-anchored signatures) is an enabler that makes enterprise adoption viable, not the wedge itself.
Every MDA design decision follows P0 > P1 > P2:
- P0 — AI-agent authorability. An LLM with only this Open Spec in context MUST be able to produce conforming output.
- P1 — Human authorability. A human with a text editor and standard hashing and DSSE-capable signing tools MUST be able to produce conforming output.
- P2 — Tooling convenience. Reference implementations are convenience, not requirement.
See spec/v1.0/00-overview.md §0.5 for the normative statement.
MDA artifacts MAY be produced in any of three equivalent ways:
- Agent mode — an AI agent writes the
.mddirectly (primary use case in 2026) - Human mode — a human writes the
.mddirectly with standard tooling - Compiled mode — an author writes a
.mdasource; the MDA compiler emits one or more.mdoutputs
See spec/v1.0/00-overview.md §0.6 and docs/create-sign-verify-mda.md for the human and agent-author paths.
- §00 — Overview, terms, priority, modes, governance, versioning
- §01 — Source (
.mda) and Output (.md); compile direction - §02 — Frontmatter
- §03 — Relationships (footnote +
depends-on+ version/digest pinning) - §04 — Platform namespaces → registry:
REGISTRY.md - §05 — Progressive disclosure
- §06 — Target schemas
SKILL.md— Tier 1, agentskills.io v1AGENTS.md— Tier 1, AAIF-alignedMCP-SERVER.md— Tier 2, AAIF-aligned, with sidecarmcp-server.jsonCLAUDE.md— Tier 2, stub
- §07 — Conformance
- §08 — Integrity (
integrityfield, combined hash) - §09 — Signatures (
signatures[], Sigstore OIDC default) - §10 — Capabilities (
metadata.mda.requires) - §11 — Implementer's Guide (informative)
- §12 — Sigstore tooling integration (informative)
- §13 — Trusted Runtime Profile
MDA is an independent project. It actively serves AAIF (Linux Foundation Agentic AI Foundation) governed targets — AGENTS.md and MCP-SERVER.md — as first-class compile destinations. MDA does not seek to join AAIF in v1.0. See spec/v1.0/00-overview.md §0.8.
- JSON Schemas:
schemas/—frontmatter-source,frontmatter-skill-md,frontmatter-agents-md,frontmatter-mcp-server-md,relationship-footnote,mda-trust-policy, plus_defs/forintegrity,signature,requires,depends-on,version-range - Conformance suite:
conformance/— fixtures +manifest.yaml - Examples:
examples/—source-only/,skill-md/(additional target examples land alongside reference-implementation maturity) - Vendor namespace registry:
REGISTRY.md— also lists standardrequireskeys, reserved Sigstore OIDC issuers, reserved transparency log providers, and reserved DSSEpayload-typevalues - Create-sign-verify recipes:
docs/create-sign-verify-mda.md— hand-author and sign without the MDA CLI - Reference implementation:
apps/cli/— TypeScript, npm:@markdown-ai/cli. Architecture spec:apps/cli/IMPL-SPEC.md
MDA v1.0 is the only major+minor planned. Future development:
- Patch releases (
v1.0.1,v1.0.2, …) deliver editorial fixes and reference-implementation maturity. They do not change the conformance contract. - Pre-release cycle: the current release candidate is
v1.0.0-rc.3. The finalv1.0.0lands when the reference implementation passes 100% conformance. - Minor releases (
v1.1.0) are not pre-planned. They emerge from observed adoption. - Major releases (
v2.0.0) ship breaking changes in a new directory; previous versions remain immutable at their canonical URLs.
See spec/v1.0/00-overview.md §0.9.
This document set is licensed under CC-BY-4.0. Schemas and tooling under Apache-2.0.