Glossary
This page and the Terminology section of the specification are generated from one file, glossary/terms.json. Terms taken from another specification name their source and keep its wording.
Archive
A ZIP archive in the canonical encoding of section 10.2. Its digest identifies one version of one plugin or skill.
- Source: this spec
- Since: 0.1.0-draft
- Do not call it: “zip file”, “package file”
- See also: Plugin archive, Skill archive, Digest
Base namespace
The configurable path, by default /.agent-marketplace/, that holds every published file other than the entry points. Written <base> in paths; it starts and ends with a slash.
- Source: this spec
- Since: 0.1.0-draft
- Do not call it: “base path”, “base directory”, “output folder”
- See also: Entry point
Canonical JSON
The single JSON serialization every generated JSON file uses: sorted keys, two-space indentation and a final newline (section 7.1).
- Source: this spec
- Since: 0.1.0-draft
- Do not call it: “pretty JSON”, “normalized JSON”
Catalog
The document <base>catalog.json, from which every other published file is derived (section 7.2).
- Source: this spec
- Since: 0.1.0-draft
- Do not call it: “registry”, “manifest file”, “master index”
- See also: Entry document
Client
Software that reads the published files of a site to list, download or install packages, such as a host or a skills command-line tool. A conforming client meets section 16.1.
Component
One of skills, agents, commands, hooks or Model Context Protocol (MCP) servers inside a plugin.
- Source: Claude Code plugin reference
- Since: 0.1.0-draft
- See also: Plugin
Conformance case
A directory of the conformance suite holding case.json, input/, expected/ and SHA256SUMS (section 16.2).
- Source: this spec
- Since: 0.1.0-draft
- Do not call it: “test fixture”, “golden test”
- See also: Generator
Digest
The lowercase hexadecimal SHA-256 of an archive’s bytes, written sha256:<hex> where an upstream format requires that form.
- Source: Agent Skills discovery 0.2.0
- Since: 0.1.0-draft
- Do not call it: “hash value”, “fingerprint”
- See also: Archive
Entry document
The file <base>entries/<p>.json or <base>entries/skills/<s>.json: one catalog item with $schema, kind and specVersion added (section 7.6).
- Source: this spec
- Since: 0.1.0-draft
- Do not call it: “entry file”, “item file”
- See also: Catalog
Entry point
A published file that a client finds by a fixed path rather than by a link (section 5).
- Source: this spec
- Since: 0.1.0-draft
- Do not call it: “discovery file”, “root file”
- See also: Base namespace, Well-known URI
External entry
An input B marketplace entry whose source is remote. It is listed in the catalog but never fetched or packaged (section 7.7).
- Source: this spec
- Since: 0.1.0-draft
- Do not call it: “remote plugin”, “third-party plugin”
- See also: Catalog
Generator
Software that reads an input tree and parameters and writes the published files. A conforming generator meets section 16.1.
- Source: this spec
- Since: 0.1.0-draft
- Do not call it: “projector”, “exporter”, “site builder”
- See also: Conformance case
Host
An application that installs plugins or skills. This profile covers Claude Code, Codex, Grok Build, Antigravity and Gemini CLI, plus clients of Agent Skills discovery.
- Source: this spec
- Since: 0.1.0-draft
- Do not call it: “client app”, “agent platform”
- See also: Support level, Host package
Host package
An archive or tree in a host-specific layout, produced only when requested (Annex A).
- Source: this spec
- Since: 0.1.0-draft
- Do not call it: “host bundle”, “platform package”
- See also: Host
Install prompt
Generated text a user can paste into their own agent to install one plugin or skill with the host’s own commands (section 12).
- Source: this spec
- Since: 0.1.0-draft
- Do not call it: “install instructions”, “agent prompt”, “setup prompt”
- See also: Host
Lock
The record, kept in the source repository and never published, of every archive published under a versioned path and its digest (section 11.2).
- Source: this spec
- Since: 0.1.0-draft
- Do not call it: “lockfile”, “lock file”, “release ledger”
- See also: Yank, Digest
Plugin
A directory in the Claude Code plugin layout: an optional .claude-plugin/plugin.json plus component folders such as skills/, agents/, commands/ and hooks/.
- Source: Claude Code plugin reference
- Since: 0.1.0-draft
- Do not call it: “add-on”, “addon”
- See also: Component, Plugin archive
Plugin archive
The archive of a whole plugin, with the plugin root at the top, used as a Claude Code archive source (section 10.1).
- Source: this spec
- Since: 0.1.0-draft
- See also: Archive
Site
The static website the files are published on. Its origin is the scheme, host and port of siteUrl.
- Source: this spec
- Since: 0.1.0-draft
- Do not call it: “web site”
- See also: Entry point
Skill
A directory holding a SKILL.md file and any supporting files.
- Source: Agent Skills
- Since: 0.1.0-draft
- See also: Skill archive
Skill archive
The archive of one skill with SKILL.md at the top, as Agent Skills discovery 0.2.0 requires (section 10.1).
- Source: Agent Skills discovery 0.2.0
- Since: 0.1.0-draft
- See also: Archive
Support level
One of native, partial or none, saying how much of a plugin works on a host (section 7.5).
- Source: this spec
- Since: 0.1.0-draft
- Do not call it: “compatibility level”, “compatibility score”
- See also: Host
Well-known URI
A URI whose path starts with /.well-known/, reserved for names registered with IANA.
- Source: RFC 8615
- Since: 0.1.0-draft
- Do not call it: “well-known path”
- See also: Entry point
Yank
To withdraw one published version: it leaves every published document and its archives stop being served, and the lock keeps the reason (section 11.4).
- Source: this spec
- Since: 0.1.0-draft
- Do not call it: “unpublish”, “revoke”
- See also: Lock