liveBook · Manning

Plugin

Also called extensions, plug-in, plug-ins

A plugin is a software component that extends a host application's capabilities through an extension or integration mechanism.

How 9 Manning books explain it

WordPress Power Toolkit: Harness AI to build next-level websites

A WordPress plugin is an installable software extension that adds or modifies functionality in a WordPress installation.

How it is used
Adds site features such as protection, backups, forms, and sidebar widgets without requiring the site owner to write code.
How deep it goes
Walks through selection, installation, conflict testing, and an AI-generated widget upload; does not develop plugin code in detail.
Examples
Uses Wordfence and UpdraftPlus for protection and backups, plus a GMT date-and-time sidebar widget generated with AI.
What you can do after
Operate/configure WordPress plugins by choosing, installing, activating, and checking them; diagnose/debug conflicts by deactivating and reactivating plugins individually.

Read how WordPress Power Toolkit: Harness AI to build next-level websites explains plugin →

Logs and Telemetry

A plugin is an independently implemented software component that extends an application's capabilities through a defined integration interface.

How it is used
Composes Fluent Bit event pipelines from input, filter, and output building blocks.
How deep it goes
Defines plugin roles and interfaces, then defers extension-language trade-offs to later treatment.
Examples
Uses dummy input help, stdout output selection, CLI pipeline controls, and Go input/output plugin code structure.
What you can do after
Operate/configure plugins through Fluent Bit CLI controls and assess external-extension deployment requirements.

Read how Logs and Telemetry explains plugin →

Build an AI Agent (From Scratch)

An agent skill is a reusable capability that packages knowledge or procedures for carrying out a class of tasks.

How it is used
Manages growing agent tool collections by loading detailed usage instructions only when a task needs them.
How deep it goes
Implements skill discovery, prompt generation, sandbox upload, and an execution flow for a concrete skill.
Examples
Uses a PDF merge skill with pypdf and a token comparison between full tool definitions and skill summaries.
What you can do after
Build it from scratch by discovering skill folders, generating prompt summaries, and uploading instructions to a sandbox.

Read how Build an AI Agent (From Scratch) explains plugin →

AI Agents in Action

A plugin is a registered capability consisting of functions that a Semantic Kernel can expose for use in conversations or interactions.

How it is used
Extends agent and chat interactions with registered functions that perform actions or call services.
How deep it goes
Walks through creating, registering, invoking, and testing plugins, including semantic and native functions.
Examples
Uses movie recommendations and a TMDb chat service, with exercises involving temperature conversion, weather, and news APIs.
What you can do after
Apply it via Semantic Kernel to register functions, invoke them, and expose service capabilities in chat.

Read how AI Agents in Action explains plugin →

LLMs in Production

OpenAI Plugins are extensions that let ChatGPT access third-party tools and external APIs.

How it is used
Connects ChatGPT with third-party tools and external APIs.
How deep it goes
Explains configuration, hosting, registration, review, and operational limitations without detailing API implementation.
Examples
Uses weather lookup, web search, OpenAPI configuration, and ai-plugin.json as concrete integration examples.
What you can do after
Build it from scratch by describing an API, defining plugin metadata, hosting files, and submitting the integration for review.

Read how LLMs in Production explains plugin →

Vibe Engineering

An agentic plugin is a versioned distributable package that bundles AI-agent skills with workflow integrations and configuration.

How it is used
Standardizes and distributes a team's approved agent workflow context as one installable package.
How deep it goes
Defines bundled components, versioning, installation, and governance, but does not specify a detailed plugin manifest schema.
Examples
Uses pull-request conventions, review checklists, deployment scripts, and approved MCP servers as package contents.
What you can do after
Operate/configure a consistent agent workflow by installing a reviewed, versioned plugin through a marketplace or private registry.

Read how Vibe Engineering explains plugin →

AI Governance

A plugin is an add-on software component that extends an application or model-enabled system with additional capabilities or integrations.

How it is used
Frames plugins and tools as extensions that can also create trusted entry points into data and networks.
How deep it goes
Traces installation trust into concrete compromise cases; broader MCP security for agentic systems is treated separately.
Examples
Uses AskTheCode repository access, malicious browser extensions, and compromised MCP services as attack examples.
What you can do after
Evaluate plugin trust by checking installation flows, granted permissions, and risks from inherited access.

Read how AI Governance explains plugin →

Claude at Work

A plugin is a software component that extends a host application's functionality through an established extension interface.

How it is used
Packages skills, connectors, and agents so reusable customizations can be shared and installed.
How deep it goes
Defines the bundle and outlines its repository layout, but does not detail plugin internals.
Examples
Demonstrates a GitHub workflow plugin with skills for creating issues, starting feature work, and creating pull requests.
What you can do after
Operate/configure plugins by adding a marketplace and installing a selected plugin in Claude Desktop or Claude Code.

Read how Claude at Work explains plugin →

Terraform in Depth: Infrastructure as Code with Terraform and OpenTofu

A plugin is a software component that extends a host application's capabilities through a defined extension interface.

How it is used
Extends TFLint with generic, provider-specific, or custom policy rules for Terraform static analysis.
How deep it goes
Configures enablement, presets, versions, sources, exclusions, and inline exceptions, while custom plugin development requires Go.
Examples
Demonstrates Terraform, AWS, Azure, and Google plugins alongside Make targets, diagnostics, disabled rules, and inline ignores.
What you can do after
Operate/configure TFLint plugins to initialize rule sets, customize checks, and handle justified exceptions.

Read how Terraform in Depth: Infrastructure as Code with Terraform and OpenTofu explains plugin →

Also covered in

What to know first

Related concepts

Questions about plugin

What is plugin?

A plugin is a software component that extends a host application's capabilities through an extension or integration mechanism.

Which Manning books explain plugin?

WordPress Power Toolkit: Harness AI to build next-level websites, Logs and Telemetry, Build an AI Agent (From Scratch), AI Agents in Action, LLMs in Production, Vibe Engineering, AI Governance, Claude at Work and 1 more.

What should I know before learning plugin?

Manning books that teach plugin usually introduce server, Python, prompt and contract first.

What kinds of plugin are there?

Kinds of plugin include Easy Google Fonts, logging interceptor, OptinMonster and ActiveMQ JAAS plugin.

What is plugin a kind of?

Plugin is a kind of component. A software component is a modular part of a software system that encapsulates related functionality and interacts with other parts through defined boundaries.

What is plugin also called?

Plugin is also called extensions, plug-in or plug-ins.

These guides are generated from the text of Manning books by Manning's knowledge graph and link to the sections they draw on. The full books are available on liveBook and at manning.com.