Sponsor Suno AI Music arrow_forward
Subagent

Vibe Explorer

Delivers single-concept micro-explanations using everyday analogies when learning mode is active. Use when a learner wants to understand one technical concept at a time in plain language. Trigger with "explain this", "what is that".

Type
Subagent
GitHub stars
2.8k
License
MIT
Repo last updated
Sep 27, 2026
Model
sonnet
Version
1.0.0
Author
Intent Solutions <[email protected]>

What Vibe Explorer is

Vibe Explorer is a subagent published in the jeremylongshore/tons-of-skills-marketplace repository on GitHub, which has about 2.8k stars. The repository describes itself as: “Model-agnostic agent-skills platform with a harness-free canonical layer, verified adapters, and the ccpi package manager. Explore at tonsofskills.com.”

A subagent is a specialist assistant that Claude can hand part of a task to. It is a markdown file whose frontmatter sets a name, a description that tells Claude when to delegate, and optionally the tools and model it may use; the body becomes the subagent's own system prompt.

Because a subagent works in its own context, it keeps the main conversation focused: Claude can send a narrow job, such as a review or a specialised analysis, to Vibe Explorer and get back a compact result.

How to install Vibe Explorer

Claude Code

  1. Download explorer.md from the repository.
  2. Save it to ~/.claude/agents/ to use it in every project, or to .claude/agents/ inside one project to share it through version control.
  3. Claude Code watches these folders, so the subagent is usually available right away. Ask Claude to use it by name, or @-mention it to make sure it runs.

Claude Cowork

  1. Cowork loads subagents through plugins. If the repository is packaged as a plugin marketplace, add it under Customize → Plugins → Add marketplace and install the plugin that contains this subagent.
  2. Otherwise, bundle the file into your own plugin's agents/ folder and upload it from Customize → Plugins.

New to extending Cowork? Our plugins guide and Customize guide explain how skills, plugins, and connectors fit together.

Inside the source file

An excerpt from plugins/productivity/vibe-guide/agents/explorer.md, shared under the repository's MIT license. Read the full file on GitHub.

You provide tiny educational nuggets when learning mode is enabled. You explain one concept at a time using simple analogies that connect coding to everyday life.

Your Capabilities

  • Single-concept focus: Explain only one thing per activation
  • Analogy mastery: Connect technical concepts to everyday objects
  • Jargon-free: Immediately explain any technical term used
  • Brevity: Keep explanations to 2-4 sentences

When to Activate

Activate when:

  • session.json has learning_mode: true
  • User runs /vibe-guide:learn on
  • A step has completed and the user wants to learn

Do NOT activate when learning mode is off.

Output Format

2-4 sentences explaining ONE concept. Use an analogy. No jargon.

Examples

Components are like LEGO blocks for websites. Each one does one thing, and you snap them together to build pages. We just made a header block that will sit at the top of every page.
When we "import" something, we're telling the code "go get that thing from over there." It's like saying "grab the hammer from the toolbox." We just told our main file to grab the new header.
A "route" is an address for different pages. When someone types /about, the route says "show them the About page." We just added a new address for the stats page.

Key Principles

  1. One concept - Never explain multiple things
  2. Simple analogy - Connect to everyday objects
  3. No jargon - If you use a tech term, immediately explain it
  4. 2-4 sentences max - Keep it brief
  5. Relevant - Explain something from the current step only

What to Explain

Pick from what just happened:

  • A file type (.tsx, .json, .css)
  • An action (import, export, create, edit)
  • A pattern (component, route, state)
  • A tool (npm, git, test runner)

Choose the concept most useful for a non-technical person to understand.

Success Criteria

A successful explanation:

  • Covers exactly one concept
  • Uses a relatable everyday analogy
  • Contains no unexplained technical terms
  • Is 2-4 sentences (no more)
  • Relates directly to what just happened in the session

Before you install

  • Read the whole file first. Skills, commands, and subagents are instructions Claude will follow, so make sure they match what you want.
  • Check which tools, scripts, or MCP servers it uses. Local servers and scripts run with your permissions.
  • Try it in a test project or a copy of your files before pointing it at real work.
  • Pin the version you tested, and review changes before updating.
  • Watch for instructions that fetch web content or run shell commands; those are where prompt injection risks start. See our prompt injection guide.

FAQ

What is Vibe Explorer?

Vibe Explorer is a subagent for Claude Code and Claude Cowork from the jeremylongshore/tons-of-skills-marketplace repository on GitHub. Delivers single-concept micro-explanations using everyday analogies when learning mode is active. Use when a learner wants to understand one technical concept at a time in plain language. Trigger with "explain this", "what is that".

How do I install Vibe Explorer in Claude Code?

Download explorer.md from the repository. Save it to ~/.claude/agents/ to use it in every project, or to .claude/agents/ inside one project to share it through version control. Claude Code watches these folders, so the subagent is usually available right away. Ask Claude to use it by name, or @-mention it to make sure it runs.

Can I use Vibe Explorer in Claude Cowork?

Cowork loads subagents through plugins. If the repository is packaged as a plugin marketplace, add it under Customize → Plugins → Add marketplace and install the plugin that contains this subagent. Otherwise, bundle the file into your own plugin's agents/ folder and upload it from Customize → Plugins.

Is Vibe Explorer safe to install?

It is a third-party community resource, not reviewed by Anthropic or this site. Read the source file first, check which tools and connectors it uses, and install only from sources you trust.

Similar resources

Browse all skills, subagents, and plugins →

Listing data comes from the public GitHub repository and was last checked in September 2026. Excerpts are © their authors and shared under MIT. This directory is independent and not affiliated with Anthropic or the resource's authors.