eli5

eli5 is a skill for Claude Code from melodic-software/claude-code-plugins. It costs 155 tokens per session (2,064 once invoked), scanned A, original, MIT.

A visual explainer that teaches one idea at a time with simple diagrams and little text. It first examines the real code or project material before drawing the explanation.

In plain words
What is it for?
It is for explaining modules, system parts, design choices, incidents, and general concepts through a visual HTML page.
Why use it?
It helps beginners understand relationships and processes that are difficult to follow in prose alone.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: mentions Claude Code.

Part of the education plugin — 5 skills shipped together

Good fit It is for explaining modules, system parts, design choices, incidents, and general concepts through a visual HTML page.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/melodic-software/claude-code-plugins/eli5
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent
npx skills add melodic-software/claude-code-plugins --skill eli5
Clone the repo
git clone --depth 1 https://github.com/melodic-software/claude-code-plugins

Made for: Claude Code.

Or install education, the plugin that ships this one along with the rest of its 5 skills.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for eli5

README.md
[![agentmods](https://agentmods.dev/badge/skills/melodic-software/claude-code-plugins/eli5/github.svg)](https://agentmods.dev/skills/melodic-software/claude-code-plugins/eli5)
Your own site
<a href="https://agentmods.dev/skills/melodic-software/claude-code-plugins/eli5"><img src="https://agentmods.dev/badge/skills/melodic-software/claude-code-plugins/eli5/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for eli5

Your own site · 80×15
<a href="https://agentmods.dev/skills/melodic-software/claude-code-plugins/eli5"><img src="https://agentmods.dev/badge/skills/melodic-software/claude-code-plugins/eli5.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 155 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,064 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00155 $0.02064
Opus 5.5 $0.00062 $0.00826
Sonnet 5.5 $0.00031 $0.00413
Haiku 4.5 $0.00015 $0.00206

Measured 17d ago against content hash effbf4f98dae, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

eli5 scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 17d ago.

The scan reads SKILL.md. This mod also ships 2 executable files (scripts/build-explainer.mjs, scripts/build-explainer.test.sh), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

plugins/education/skills/eli5/SKILL.md · 155 lines

How it starts

The opening of the file, as written. The whole thing — 155 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Purpose

Explain one thing as a picture, for a reader assumed to know nothing about it.

The output contract is fixed: a visual HTML explainer that assumes zero prior knowledge: one idea per diagram, minimal text. That contract is what makes this a distinct lane rather than a second prose explainer. education:explain drops altitude and stays in prose; this skill changes the medium, and its floor does not move on request.

The upstream community eli5 plugin writes a page that does not pass through the escape helper, so this skill builds every page itself.

Step 1. Ground the object before drawing it

A diagram of a thing you recalled wrongly is a confident, beautiful, wrong answer. Re-read the actual artifact this turn. What that means depends on the object:

Object Grounding pre-pass
A module, file, or subsystem Read the code. Follow its imports and its callers far enough to know what it actually does, not what its name suggests.
A tradeoff or design decision Read the ADRs, the git history, and the pull-request discussion where it was argued. The reasoning lives in the debate, not the result.
An incident Read the writeup and the logs. Reconstruct the sequence before drawing the causal chain.
A general concept Fetch a primary source. Do not draw from parametric memory.

If the grounding pass cannot be done (no access, no such artifact), say so and ask, rather than drawing a plausible diagram of something you did not read.

Step 2. No delegation

Build the page with this skill, whether or not the upstream eli5 plugin is installed. Step 1 hands this skill repository text or a fetched web page, both untrusted, and the upstream skill writes its own page, which does not pass through the escape helper. Do not invoke it, and do not print an install recipe for it.

Step 3. The inline pass

Build the explainer directly, to the same contract.

  • One idea per diagram. If a diagram needs a paragraph to be read, it is two diagrams.
  • Diagram first, prose second. Each diagram carries a one-line takeaway caption saying what the reader should conclude from it. The caption is the point; the surrounding text is scaffolding.
  • Demote the identifiers. Real function, file, and service names belong in parentheses or monospace, after the plain-words version of what the thing does. A zero-knowledge reader cannot use a name they have never seen as the subject of a sentence.
  • Diagrams are boxes and arrows. Each diagram is a flow (boxes joined by arrows) or a stack (boxes one above the next), listed as steps. Build a system up across several small diagrams, each adding one box, rather than one crowded diagram.
  • Name the styles to leave out. The builder's stylesheet has no italic accent words in headings, numbered "01 / 02 / 03" section labels, or pill-shaped badges. The look is fixed: when the user dislikes it, say so rather than hand-writing a replacement page.

Read the full file on GitHub · 155 lines

Files

What ships with it

3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 17d ago Changed · -14 lines · -10 tokens per session effbf4f98dae
  2. 26d ago Changed · +5 lines ee92a77b2e45
  3. 1mo ago Changed · -1 lines · -14 tokens per session e6c57f2adbb2
  4. 1mo ago First seen · 165 lines · 179 tokens per session scan A db2d7fca2519

Subscribe to this mod's changes

eli5 is a skill published in the GitHub repository melodic-software/claude-code-plugins (26 stars, last pushed today), licensed MIT. It adds 155 tokens to every session and 2,064 once invoked, about $0.0006 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.

Related

Other skills, from other repositories

solve-constraint-puzzle

For constraint satisfaction: Sudoku, scheduling, N-queens, logic puzzles, SAT-like problems, assignment problems. Uses propagate-then-search pattern.

jimmc414/claude-code-plugin-marketplace · 36 tokens

count-combinations

For probability and counting: permutations, combinations, sample spaces, Monte Carlo simulation, brute-force enumeration, card/dice problems.

jimmc414/claude-code-plugin-marketplace · 29 tokens

career-path-planner

Career goal mapping with skill gap analysis, actionable development plans, and milestone tracking. Use when planning career transitions, identifying skill gaps, setting professional development goals, or evaluating career options.

travisjneuman/.claude · 41 tokens

learning-gap-analyzer

Map understanding, identify knowledge gaps, and build targeted learning plans with spaced repetition. Use when assessing knowledge levels, designing study plans, or optimizing learning paths.

travisjneuman/.claude · 36 tokens

parallel-orchestrator

Manage parallel Claude Code workstreams using git worktrees. Use when: splitting large tasks across multiple workers, coordinating parallel development, monitoring worker progress, integrating completed work, analyzing work item documents (code reviews, issue lists). Triggers: parallel, orchestrator, worktrees…

jimmc414/claude-code-plugin-marketplace · 78 tokens

parallel-worker

Execute focused implementation tasks in a parallel workflow. Use when: working on assigned files in a worktree, making checkpoint commits, signaling dependencies or blockers, completing orchestrator-assigned tasks. Triggers: worker, checkpoint, worktree, assigned scope, commit prefix, parallel task.

jimmc414/claude-code-plugin-marketplace · 59 tokens