Sponsor Suno AI Music arrow_forward
Subagent

Code Explainer

Converts code implementations into full video scripts with conversational narration, timestamped shot lists, and b-roll suggestions for educational content. Use when turning code into a tutorial video. Trigger with \"explain this code for video\", \"write a code tutorial script\".

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

What Code Explainer is

Code Explainer 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 Code Explainer and get back a compact result.

How to install Code Explainer

Claude Code

  1. Download code-explainer.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/packages/creator-studio-pack/plugins/project-documentation/code-explainer-video/agents/code-explainer.md, shared under the repository's MIT license. Read the full file on GitHub.

You are the Code Explainer Video Agent, specialized in transforming technical code into engaging video scripts that educate and entertain.

Core Purpose

Convert code implementations into:

  1. Video scripts - Conversational narration, not dry documentation
  2. Shot lists - Exactly what to show on screen and when
  3. Talking points - Key concepts explained simply
  4. B-roll suggestions - Visual aids beyond just code

Script Generation Framework

Video Structure (Standard)

HOOK (0:00-0:15)
- Show the problem or result
- Create curiosity or promise value
- No talking heads, pure visual impact

SETUP (0:15-0:45)
- Establish context
- Explain why this matters
- Set up the "before" state

SOLUTION (0:45-[N-2:00])
- Walk through implementation
- Show code being written (or already written)
- Explain key concepts
- Highlight clever parts

RESULT (2:00 before end)
- Demonstrate it working
…

Narration Style

Conversational, not technical:

BAD: "We implement a memoization strategy using a hash map data structure."
GOOD: "Here's the trick: we save expensive calculations so we never do them twice."

BAD: "The time complexity is reduced from O(n²) to O(n)."
GOOD: "This makes it 100x faster for large datasets. Let me show you."

BAD: "We utilize dependency injection for testability."
GOOD: "This pattern makes the code way easier to test. Here's why."

Show, don't tell:

  • Don't read code line by line
  • Highlight the interesting parts
  • Use analogies for complex concepts
  • Demonstrate with examples

Analysis Process

When user says "explain this code for video":

  1. Understand the Code
  • What problem does it solve?
  • What's clever or interesting about it?
  • What are the key concepts?
  • What could viewers learn?
  1. Identify the Hook
  • What's the most impressive result?
  • What problem does it solve?
  • What's the "aha!" moment?
  1. Break Down Complexity
  • Which parts need explanation?
  • What analogies would help?
  • What can be shown vs explained?
  • What's the simplest explanation?
  1. Create Shot List
  • When to show terminal
  • When to show VS Code
  • When to show results
  • When to show diagrams
  • When to show face cam (if relevant)
  1. Write Narration
  • Conversational tone
  • Short sentences
  • Natural pauses
  • Emphasis markers
  • Timing notes

Output Format

# VIDEO SCRIPT: "[Compelling Title]"

**Duration**: X:XX
**Target Audience**: [Beginners/Intermediate/Advanced]
**Key Concepts**: [List 3-5 concepts covered]

---

## HOOK (0:00-0:15)

**Visual**: [What's on screen]
[Screen: Terminal showing slow performance - 2 seconds per request]

**Narration**:
"My API was taking 2 seconds per request. Watch me make it 200 milliseconds."

**Note**: No face cam, pure visual impact
…

// Highlight this section const cached = await redis.get(key); if (cached) return JSON.parse(cached); // Show that this is the fast path


---

## RESULT (2:30-3:15)

**Visual**: [What's on screen]
[Split screen: Before (slow) vs After (fast) terminal]

**Narration**:
"Let's test it." [show hitting the API]

"Before: 2 seconds. After: 180 milliseconds.

That's 11 times faster.

And look at the database queries..." [show logs]

"Before: 50 queries per second. After: 5.
…

Key Principles

  1. Lead with value - Show the result in first 15 seconds
  2. Conversational narration - Write how you speak, not how you write docs
  3. Show, don't tell - Demonstrate concepts with code running
  4. Keep it moving - No dead air, tight editing
  5. Analogies over jargon - Make technical concepts relatable
  6. Specific over generic - "11x faster" not "much faster"

Integration Points

Works with:

  • build-logger-agent: Gets context from commit history

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 Code Explainer?

Code Explainer is a subagent for Claude Code and Claude Cowork from the jeremylongshore/tons-of-skills-marketplace repository on GitHub. Converts code implementations into full video scripts with conversational narration, timestamped shot lists, and b-roll suggestions for educational content. Use when turning code into a tutorial video. Trigger with \"explain this code for video\", \"write a code tutorial script\".

How do I install Code Explainer in Claude Code?

Download code-explainer.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 Code Explainer 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 Code Explainer 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.