The vocabulary of AI agent configuration.

Plain definitions for the terms HubBound uses, and for the wider vocabulary teams run into when they try to standardize how their AI agents work.

What are HubBound's core concepts?

HubBound's core concepts are the nouns the product runs on: the AI Artifact and the Kit, the organization and team that own and receive them, distribution, the Marketplace, forks, the Skill audit, and Live Planning with its plan checkpoints.

AI Artifact
An AI Artifact is a versioned, reusable unit of AI agent configuration. It can be a skill, a rule, a hook, a subagent or an MCP server. Every Artifact has an owner, a version history and a visibility scope, and any Artifact can be installed on its own or bundled into a Kit. Artifacts are to AI agents what packages are to code: the smallest thing worth sharing, versioning and depending on.
Kit
A Kit is a named, versioned bundle of AI Artifacts installed with a single command. A Kit is to Artifacts what a package is to modules: the unit a team actually distributes. Instead of asking a new developer to copy nine files out of a wiki, you hand them one Kit and their environment matches the rest of the team in seconds.
Distribution
Distribution is the act of assigning a Kit or an Artifact to a team or to an entire organization. It is the layer public registries do not have: because HubBound knows who belongs to which team, a Kit can reach the frontend group without reaching everyone. Scoped distribution is the main reason an internal registry beats a public one inside a company.
Organization
An organization is the top-level tenant in HubBound. It owns private Artifacts, private Kits and its members, and it is the boundary that visibility rules are enforced against. Anything marked private is visible only to members of the organization that owns it.
Team
A team is a group of people inside an organization: frontend, backend, platform, product. Teams are the target of distribution: Kits and Artifacts are sent to teams. AI usage metrics are reported across the whole organization or for one member, not per team.
Marketplace
The marketplace is where Artifacts and Kits are discovered, forked and distributed. It is read-only: each entry shows its version and the CLI command that installs it. Public entries are visible to everyone; on plans that include a private marketplace, an organization's own entries are visible only to its members. Both live in the same interface, so a team searches one place whether the answer is internal or community-built.
Fork
Forking creates a private, independent copy of an Artifact or Kit, from its current version or a specific one, that a team can modify without affecting the original. It is how a team adopts a community standard and then adapts it: the same operation, and the same reasoning, as forking a repository.
Skill audit
A Skill audit is HubBound's on-demand security analysis of one published Skill version. A deterministic ruleset and a model review read the Skill's exact content and return a verdict (clean, flagged, dangerous or inconclusive), a 0-100 risk score and every finding with its evidence and fix. The verdict is informational: it never blocks a download or an install.
Live Planning
Live Planning is HubBound's collaborative workspace for implementation plans. A coding agent creates the plan through the hubbound-live-planning MCP server; the team shares it, edits it live, comments on selected passages and launches their own coding agents to revise it, then approves it at a review checkpoint before an agent executes it. Plans are Markdown documents and can be downloaded as Markdown at any time.
Plan checkpoint
A plan checkpoint is a saved, immutable version of a Live Planning plan. Reviewers decide on a checkpoint, not on the moving draft, so later edits never change what was approved; the plan's history keeps every checkpoint so it can be compared with the current draft and restored as a new one.
Context Bundle
The Context Bundle is the HubBound add-on that brings Memories, Projects and Ink together, sold per seat as one unit. Memories hold what a team and its coding agents learn, Projects give that knowledge a shared home per project, and Ink answers questions from it with sources. The three ship together because each one is only useful with the other two.
Memory
A memory in HubBound is a decision, convention, architecture note, bugfix, gotcha, procedure, preference, session summary or note that a team or its coding agents capture so the next session does not start blind. Agents save and search memories through the hubbound-memories MCP server; each memory has a scope (Private, Team, Organization or Project), keeps every revision, and links to the memories it supersedes, refines or builds on.
Project
A Project in HubBound is a shared workspace, owned by a team or by the organization, that holds the notes and memories a project's people and agents rely on. Access is granted to people, teams or the whole organization, and every change is recorded in the project's activity.
Ink
Ink is HubBound's AI agent for memories: you ask it a question in plain language and it answers only from the memories you can access, listing the sources it used. It declines requests that try to change how it works or fall outside your organization's memories. Questions past a usage threshold are billed on demand.
Boundy AI
Boundy AI is the AI agent inside HubBound Metrics. It answers questions about an organization's AI usage, adoption and costs in plain language, with KPI cards, charts, tables and leaderboards, and follows the same access rules as the dashboard. Questions past a usage threshold are billed on demand.

What are the five Artifact types?

HubBound versions exactly five types of AI Artifact: skills, rules, MCP servers, subagents and hooks. Each one configures a different part of how an AI agent works.

Skill
A skill is a packaged procedure an AI agent can invoke to perform repeatable work: run a migration checklist, write a changelog entry, prepare a release. Where a prompt is an instruction, a skill is a capability the agent can call by name.
Rule
A rule is a convention or constraint an AI agent must always follow. Rules are what files like CLAUDE.md, .cursorrules and AGENTS.md contain. As Artifacts they live in one shared, versioned place instead of being copied into every developer's dotfiles and drifting apart.
MCP server
An MCP server is a program that exposes tools and data to an AI agent through the Model Context Protocol. It is how an agent reaches your issue tracker, your database or your internal APIs. Distributing MCP servers as Artifacts means a team connects to the same systems the same way, rather than each developer configuring their own.
Subagent
A subagent is a specialized AI agent that a main agent delegates a focused task to, with its own instructions, tools and model: a code reviewer, a test writer, a migration agent. Subagents keep the main agent's context clean by moving narrow work into a separate one.
Hook
A hook is an automation that fires around an AI agent's lifecycle: before a tool call, after an edit, on session start. Hooks are where a team's policy becomes enforcement rather than a document: the point at which a convention can actually block something.

What do the wider AI agent terms mean?

These terms come from the wider AI ecosystem that engineering teams meet when they standardize their agents: the Model Context Protocol, registries, prompts, context engineering, agentic AI, governance and configuration drift.

Model Context Protocol (MCP)
The Model Context Protocol is an open standard, introduced by Anthropic in 2024, for connecting AI models to external tools and data sources. It defines how an AI client discovers and calls capabilities exposed by an MCP server, which is what makes a tool integration portable across AI applications rather than specific to one.
Registry
A registry is a system of record for versioned, installable artifacts, along with the metadata needed to find and depend on them. npm is a registry for JavaScript packages; Docker Hub is a registry for container images; HubBound is a registry for AI agent capabilities.
Prompt
A prompt is a reusable instruction given to an AI model or agent. It is one of the most common units of AI configuration teams try to standardize, though HubBound versions it as part of a skill or a rule rather than as its own Artifact type.
Prompt management
Prompt management is the practice of storing, versioning, reviewing and distributing prompts as shared assets rather than as text pasted into individual editors. It becomes necessary the moment more than one person depends on a prompt working the same way.
Prompt version control
Prompt version control is applying versioning to prompts and other AI configuration: every change produces a new version, previous versions remain retrievable, and consumers choose when to move. It answers the question teams hit first: which version of this prompt is the one that actually worked.
Context engineering
Context engineering is the practice of deciding what information an AI agent has available at the moment it acts: instructions, rules, tools, retrieved documents and conversation history. It is the discipline that grew out of prompt engineering once agents gained tools and memory, and the prompt stopped being the only lever.
Agentic AI
Agentic AI describes systems where a model plans and executes multi-step work using tools, rather than only producing text in response to a single request. AI coding agents such as Claude Code, Cursor and Codex are the form most engineering teams meet first.
AI governance
AI governance, in an engineering context, is the set of controls that determine which AI capabilities are available to whom, how they are configured, and what evidence exists about how they were used. It is a distribution and measurement problem before it is a policy document.
Configuration drift
Configuration drift is the gradual divergence of setups that were meant to be identical. In AI tooling it appears when every developer configures rules, hooks and MCP servers on their own machine: what works for one person does not exist for the next, and onboarding starts from zero every time.

Where are these standards documented?

The Model Context Protocol, Claude Code, Cursor, OpenAI Codex and the HubBound CLI are each documented by the people who build them. These are the primary sources behind the definitions on this page.

See how it all connects.

Each piece of HubBound builds on the others. Pick where you want to go next.