mda
MDA Open Spec — a Markdown superset for agent-facing documents. One .mda source compiles to drop-in SKILL.md, AGENTS.md, MCP-SERVER.md, and CLAUDE.md. JSON Schema validated,…
Install
git clone https://github.com/sno-ai/mdaInstall command taken from the project's README or registry entry. Always review code before running it.
README excerpt
Read full README on GitHub →📝 MDA Open Spec — Markdown for Agent
A Markdown superset for agent-facing documents. One source, many targets — compile into the
.mdfiles every major agent runtime already loads. Tamper-evident at load — every artifact carries a reproducible content digest, and signed artifacts carry Sigstore-anchored signatures, so neither the agent loading the doc nor the human reviewing it has to trust an unsigned blob.
Read in other languages: English · 中文 · Deutsch · Español · Français · Русский · 한국어 · 日本語 · हिन्दी
What MDA is
Until now, you shipped the same skill four times. Once as SKILL.md for the agentskills.io runtimes. Once as AGENTS.md for the AAIF ecosystem. Once as MCP-SERVER.md with a sidecar JSON. Once as CLAUDE.md. Same content, four frontmatter shapes. Update one, forget the others, and a month in, the four files have quietly drifted into four slightly different instruction files.
You write one .mda. The compiler emits the rest.
┌─────────────────────────┐
│ <name>.mda (source) │ ← MDA superset
└────────────┬────────────┘
│ mda compile
▼
┌─────────────────────────────────────────────────────────┐
│ <name>/SKILL.md (+ scripts/, references/, assets/) │
│ AGENTS.md │
│ <name>/MCP-SERVER.md (+ mcp-server.json sidecar) │
│ CLAUDE.md │
└─────────────────────────────────────────────────────────┘
drop-in compatible
Compatibility
Write your skill once. It drops into every major agent runtime — unchanged.
Five SKILL.md runtimes verified end-to-end with reproducible install kits in compat/. Compiled AGENTS.md artifacts also drop into the AAIF ecosystem (Codex, Copilot, Cursor, Windsurf, Amp, Devin, Gemini CLI, VS Code, Jules, Factory), and at the documentation level into skills.sh and other 2026 SKILL.md consumers.
And those four files can't say who signed them. The agent loading SKILL.md has no way to verify the content matches what you wrote, and the curator reviewing AGENTS.md has no way to know whose hands have been on it between merge and load. The standard frontmatter shapes have nowhere to put a content digest or a signature, so the trust decision quietly falls back to "we trust the repo, somehow."
MDA carries a JCS-canonicalized integrity.digest and DSSE-enveloped, Sigstore-anchored signatures[] in the frontmatter itself. Both sides — the agent at load time and the human at review time — can make a real trust decision against the artifact in hand, not against a feeling about the repo. Tamper-evidence and signer verification ship in the contract, not as a later bolt-on.
.mda adds three things on top of standard Markdown. All of them optional.
Similar plugs
Makes your AI agent think like the laziest senior dev in the room. The best code is the code you never wrote.
Turn any codebase, with its docs, SQL schemas, configs, and PDFs, into a queryable knowledge graph. A /graphify skill for Claude Code, Cursor, Codex, and Gemini CLI: local…
Why use many token when few token do trick. Viral skill + proxy for coding agents that cuts 65% of tokens by talking like a caveman.
Production-grade engineering skills for AI coding agents.
The 1st Collaborative AI Design Agent Workspace. Local-first and open source. Create prototypes, websites, apps, dashboards, presentations, images, and videos with your team…