]> FAF Foundation

United States of America team@faf.one https://foundation.faf.one

Independent Submission This document specifies the FAF Agent Format (.fafa): a declarative, YAML-based format for an agent's identity, the capabilities it exposes, and the endpoints through which it is reached. A .fafa document describes an agent; it never instructs one. .fafa (application/vnd.fafa+yaml, IANA-registered June 2026 in the vendor tree) is the agent member of the FAF family, alongside .faf (project context) and .fafm (agent memory). It functions as a portable passport that answers four questions: who the agent is, what it may do, where it is reached, and what it must never do. Protocol-native cards (for example A2A Agent Cards and MCP Server Cards) remain useful wire formats; repository instruction files such as AGENTS.md remain the ops briefing; .fafa complements them as a house-neutral source of truth that can be projected into those formats; it does not replace them. This document documents the existing IANA vendor-tree registration. No standards-tree registration is requested. A companion white paper, "Why Agents Need a Passport," provides the production rationale and lifecycle framing.

Introduction

Problem Statement Agent-interaction work consistently defines an object model for agent identity, capability, and endpoint, and then defers the serialization to "some JSON" or an unspecified schema. The object model is specified repeatedly; the on-the-wire, in-the-registry, in-the-repository format — the document an agent publishes about itself — is left unspecified. In production that identity is usually inferred from system prompts, product settings, and protocol-native cards that do not travel cleanly across hosts. The result is seam rewrites when an agent moves between environments, repeated inference cost, and trust surfaces that cannot be diffed or reviewed as data.

Solution Overview .fafa specifies the missing document: a vendor-neutral, YAML-native declaration of what an agent is, what it can do, and how it is reached. It functions as a portable passport that answers four questions:

• who the agent is,
• what it may do,
• where it is reached, and
• what it must never do.

A .fafa document describes an agent; it never instructs, authorizes, or executes one. It defines the document that protocols and hosts carry, reference, or resolve; it does not define discovery, transport, authorization, or orchestration. .fafa is complementary by design. It composes with existing and future agent-interaction protocols and repository instruction conventions and competes with none of them. Protocol-native cards (A2A Agent Cards, MCP Server Cards, and similar) remain useful wire formats; files such as AGENTS.md remain the repository ops briefing. A .fafa document is the house-neutral source of truth that can be projected into those formats (see ). A companion paper provides extended motivation, worked examples, and further detail on the projection model summarized in .

Design Goals

1. Declarative, never executable — a .fafa document describes an agent; it never instructs, authorizes, or executes one.
2. Vendor-neutral — no dependency on any single agent-interaction protocol.
3. Composable — sits at the format layer beneath protocols, not in competition with them.
4. Forward-compatible — unknown fields are preserved as extensions; documents remain valid across minor revisions.
5. Family-coherent — extends .faf ; shares YAML 1.2 as base syntax and MIT-licensed distribution.
6. Portable source of truth — intended to be authored once and projected into the protocol- or host-specific cards that different environments require.

Terminology The key words "MUST", "MUST NOT", "REQUIRED", "SHALL", "SHALL NOT", "SHOULD", "SHOULD NOT", "RECOMMENDED", "NOT RECOMMENDED", "MAY", and "OPTIONAL" in this document are to be interpreted as described in BCP 14 when, and only when, they appear in all capitals, as shown here. The following terms are used throughout this document:

• Agent — An autonomous or semi-autonomous software entity that exposes capabilities and accepts invocation.
• Capability — A named, addressable function the agent can perform.
• Endpoint — A reachable address plus protocol binding for invoking the agent.
• Attachment — Optional infrastructure context within which the agent operates (gateway, domain, policy scope).
• Provenance — Optional context substrate the agent reads from, most commonly a .faf reference.
• Passport (informal) — A .fafa document when emphasizing its role as a portable, projectable identity declaration.
• Projection (informal) — The process of deriving a protocol- or host-specific card or instruction fragment from a .fafa source document.

The Agent Format (.fafa)

Format Overview A .fafa file MUST be a valid YAML 1.2 document . It is declarative: it carries identity, capability declarations, and endpoint references, and MUST NOT contain executable content, code, or instructions to a model.

Media Type The agent format is identified by application/vnd.fafa+yaml, registered in the IANA vendor tree on 2026-06-26 . This document documents that vendor-tree registration. No standards-tree registration is requested. The canonical specification is . The file extension is .fafa.

Document Structure A .fafa document is a single YAML mapping. Required top-level fields: version; agent (with at least name and id); capabilities (array, MAY be empty); endpoints (array, MUST be non-empty). Optional top-level fields: attachment, provenance, signature, metadata (free-form vendor extensions). Primary example: Minimal valid example:

Agent Section Declares identity.

• Required: name (string, unique within the issuing vendor namespace); id (globally unique identifier — DID, URI, or vendor-scoped UUID).
• Optional: vendor; version (semantic version of the agent, NOT of this specification); description; homepage; license (SPDX identifier).

Capabilities Section Each capability is a structured object.

• Required: name (unique within the document); type (tool, resource, prompt, event, or other).
• Optional: description, input_schema, output_schema, tags, apophatic (boolean; if true, the capability refuses out-of-scope invocation rather than attempting best effort), cites_spec (the format or specification the capability operates against).

The capabilities array MAY be empty. Declaration is not authorization (see ).

Endpoints Section Each endpoint declares a protocol binding.

• Required: protocol (mcp, a2a, grpc, http, or other); transport (stdio, http, websocket, quic); location (reachable address — URI, package name, or transport-specific locator).
• Optional: version, auth, region, health.

Multiple endpoints MAY declare the same protocol with different transports.

Attachment Section (Optional) Describes the infrastructure context within which the agent operates, without requiring any particular gateway protocol. Optional fields: gateway, domain, policy, attachment_point.

Provenance Section (Optional) Cites the context substrate the agent operates from — the FAF-family integration point. A .fafa agent SHOULD declare which .faf it reads. Optional fields: faf (reference to a .faf document), fafm (reference to a .fafm document), spec (media type of the substrate), version.

Parser Requirements

• Consumers MUST use YAML safe-load (no custom type construction).
• Consumers MUST treat unknown top-level fields, and unknown subfields within agent, capabilities, and endpoints, as forward-compatible extensions.
• Consumers SHOULD use UTF-8 encoding and SHOULD keep documents within common registry storage budgets (RECOMMENDED: < 64 KB).

File Conventions

• Standard filename: agent.fafa (alongside project.faf at the project layer), or served via the /.well-known/faf discovery anchor defined in .
• File extension: .fafa. Encoding: UTF-8.
• Multiple .fafa documents per scope are permitted, distinguished by agent.id.

Versioning The top-level version field declares the version of this specification to which the document conforms. Versioning is semantic: 1.x revisions are backward-compatible; a new major version is reserved for breaking changes made only with strong cause. Consumers MUST accept documents whose version shares their supported major version, and MUST apply forward-compatible extension handling for unknown fields. This separates the agent's version (agent.version) from the format's version (top-level version), so an agent may revise independently of the specification.

Relationship to Protocol-Native Cards and the FAF Family

Projection, Not Replacement .fafa is not a replacement for protocol-native identity and capability documents; it is a source of truth those documents MAY be projected from. Existing wire formats remain useful and unaffected:

Protocol-native document	Relationship to .fafa
Agent-to-Agent (A2A) Agent Card	MAY be projected from .fafa
Model Context Protocol server-card / tool list	MAY be projected from .fafa
Framework-native agent configuration	MAY be projected from .fafa
Repository instruction files (AGENTS.md and siblings)	Orthogonal (ops briefing)

The preferred pattern is one .fafa passport with many projections, rather than multiple hand-maintained, independently drifting cards describing the same agent. A publisher MAY maintain .fafa as the authoring source and generate protocol-native documents from it; this document does not require or standardize that generation process.

A2A Agent Cards The Agent-to-Agent (A2A) protocol defines an Agent Card as a JSON metadata document, conventionally published at /.well-known/agent-card.json. An A2A Agent Card describes identity, skills, supported interfaces, security schemes, and related metadata, and MAY be signed. A .fafa document can be projected into an A2A Agent Card. Typical mappings include agent.name / agent.id → identity fields, capabilities[] → skills, endpoints[] → supportedInterfaces, and agent.description → card description. The .fafa document remains the upstream source; the Agent Card is the protocol-specific advertisement derived from it.

MCP Server Cards and Tool Surfaces The Model Context Protocol (MCP) is evolving discovery mechanisms, including Server Cards that describe a server's identity, transports, and protocol versions prior to connection. Tool, resource, and prompt surfaces remain runtime concerns (for example via tools/list). A .fafa document can serve as the upstream source that is projected into an MCP Server Card or used to seed the tool surface an MCP host advertises; .fafa does not replace MCP Server Cards or the runtime tool list.

Repository Instruction Files Files such as AGENTS.md, CLAUDE.md, GEMINI.md, and .cursorrules provide project-level operational guidance. They are instruction surfaces, not structured identity or capability declarations. .fafa and these files address orthogonal questions: .fafa answers who the agent is and what it may do; AGENTS.md answers how to work in this repository. The two coexist cleanly.

Relationship within the FAF Family .fafa is the agent member of the FAF family : Context Layer (project IS -- static, read once) .fafm -> Memory Layer (agent REMEMBERS -- mutating) .fafa -> Agent Format (agent IS -- declarative identity) ]]> The .fafa schema extends application/vnd.faf+yaml additively. A consumer that understands only .faf parses a .fafa file as valid YAML and extracts top-level identity; a .fafa-aware consumer gains the full agent declaration.

Security Considerations This section addresses the IANA media-type security-considerations checklist for application/vnd.fafa+yaml.

Active or Executable Content None. A .fafa document is YAML data with no scripts, code, or active markup. Implementations MUST treat .fafa content as data, never as instructions or commands. Declaration is not authorization: an implementation MUST NOT invoke or auto-execute a capability solely because it is declared. Projection of a .fafa document into a signed protocol card does not transfer authorization; the receiving system must still apply its own policy and least-privilege controls.

YAML-Specific Vulnerabilities .fafa is built on YAML 1.2; the YAML security considerations of apply. Parsers MUST disable custom type construction (e.g., !!python/object, !ruby/object), MUST enforce alias-expansion limits to mitigate entity-expansion ("billion laughs") attacks, and MUST enforce nesting-depth limits to prevent stack overflow.

Untrusted Input and Prompt Injection .fafa documents originate from agents and third parties and MUST be treated as untrusted input. Consumers MUST NOT elevate .fafa content to "system" or "developer" tiers within prompt hierarchies; it occupies the user-data tier. Capability declarations are a documented vector for over-trust and prompt injection.

Identity, Endpoints, and Least Privilege Identity claims, capability declarations, and endpoints are self-asserted. Consumers MUST treat endpoints as untrusted until verified (against signature where present), MUST scope capability consumption to the declaring agent's verified identity, and MUST apply least privilege when acting on declared capabilities.

Prohibited Content .fafa documents MUST NOT contain secrets, API keys, or credentials; MUST NOT contain user-personal data (use .fafm for memory of that kind); and MUST NOT contain executable code.

IANA Considerations

Media Type (Documentation Only) The agent format is already registered in the IANA "Media Types" registry, vendor tree:

• application/vnd.fafa+yaml — registered 2026-06-26 . File extension .fafa. Published specification: .

This document documents that registration. No new media-type registration is requested.

Relationship to the Existing Vendor-Tree Registration The vendor-tree registration remains valid. This document does not request promotion to the standards tree.

References Normative References In many standards track documents several words are used to signify the requirements in the specification. These words are often capitalized. This document defines these words as they should be interpreted in IETF documents. This document specifies an Internet Best Current Practices for the Internet Community, and requests discussion and suggestions for improvements. RFC 2119 specifies common key words that may be used in protocol specifications. This document aims to reduce the ambiguity by clarifying that only UPPERCASE usage of the key words have the defined special meanings. This document registers the application/yaml media type and the +yaml structured syntax suffix with IANA. Both identify document components that are serialized according to the YAML specification. IANA Informative References Zenodo

Additional Example

Document History

-00

29 June 2026 -- Initial version.

-01

16 August 2026 -- Clarified positioning as portable passport; expanded problem statement with production motivation; added relationship to A2A Agent Cards, MCP Server Cards, and AGENTS.md; synchronized examples with AGENT-FORMAT.md (including apophatic and cites_spec); added companion white paper reference; minor security clarification regarding projection.