Agent

What an AI agent is, what an agent plugin is, a comparison of three mainstream coding agents, and how to build a plugin.

Agent

What is an agent

An AI agent is an LLM wrapped in a loop that can act, not just answer. The model decides which tool to call, observes the result, and repeats until the goal is met. The essential ingredients are:

  • A model โ€” the reasoning engine.
  • Tools โ€” functions it can call (run a command, read a file, search the web).
  • A loop โ€” plan โ†’ act โ†’ observe โ†’ re-plan, until done.
  • Context / memory โ€” the task, prior steps, and relevant project knowledge.

A plain chatbot returns text. An agent edits files, runs tests, fixes the failures, and reports back โ€” it closes the loop on real work.

What is an agent plugin

A plugin packages reusable capability so you don’t re-teach the agent every time. Across today’s tools a plugin typically bundles some of:

  • Slash commands โ€” custom prompts/workflows you invoke by name.
  • Subagents โ€” specialized helpers the main agent can delegate to.
  • Skills โ€” domain knowledge loaded on demand.
  • Hooks โ€” scripts that fire on events (e.g. before a commit).
  • MCP servers โ€” connections to external systems (see MCP).

Plugins make an agent extensible and shareable: install one and the agent gains new commands and integrations instantly.

Three mainstream agents

AgentFormStrengthTrade-off
Claude CodeCLI / IDEDeep autonomy, rich plugin + MCP + skills ecosystemTerminal-first; needs a Claude subscription/API
CursorFull IDE (VS Code fork)Best inline editing UX, multi-model, great for explorationYou switch editors; agent autonomy is shallower
GitHub CopilotIDE extension + coding agentNative GitHub/PR integration, huge install baseLess open/customizable, ecosystem-locked

The differences in short:

  • Claude Code is the most agentic and the most open to extend โ€” plugins, skills, hooks and MCP make it programmable. Best when you want the agent to drive multi-step work autonomously.
  • Cursor wins on editing experience. It’s an IDE, so completions, diffs and context-picking feel native. Best for hands-on, in-editor coding.
  • Copilot wins on integration and ubiquity. It lives where your code already is (GitHub, VS Code, JetBrains) and its coding agent can take an issue to a PR. Best for teams already standardized on GitHub.

There is no single winner โ€” pick by how much autonomy vs. inline control you want, and how much you care about extensibility vs. zero-setup integration.

Developing a plugin

Using Claude Code’s plugin system as the concrete example, a plugin is just a directory with a manifest plus the components it adds:

my-plugin/
โ”œโ”€โ”€ .claude-plugin/plugin.json   # name, version, description
โ”œโ”€โ”€ commands/                    # slash commands (markdown prompts)
โ”œโ”€โ”€ agents/                      # subagent definitions
โ”œโ”€โ”€ skills/                      # on-demand knowledge
โ”œโ”€โ”€ hooks/                       # event scripts
โ””โ”€โ”€ .mcp.json                    # MCP servers to wire in

The workflow is roughly:

  1. Scaffold the directory and plugin.json manifest.
  2. Add a command โ€” a markdown file whose body is the prompt the agent runs.
  3. Optionally add subagents, skills, hooks, or MCP servers.
  4. Install it locally to test, then publish via a marketplace/repo so others can install it.

You’re not writing model code โ€” you’re writing prompts, configuration, and small scripts that compose into reusable behavior.


Resources

https://docs.claude.com/en/docs/claude-code

https://cursor.com/

https://github.com/features/copilot

Designed by Canux