agentmods.dev

visual-explainer

visual-explainer is a skill for Claude Code from atretyak1985/swarmery. It costs 88 tokens per session (2,098 once invoked), scanned A, original, Apache-2.0.

A tool for turning a document or finished explanation into a self-contained interactive HTML page. It presents plain-language text alongside diagrams, glossary explanations, and extra technical details that readers can open when needed.

In plain words
What is it for?
Use it to explain a specification, plan, investigation, or other document with diagrams, step-by-step views, comparisons, and expandable technical notes.
Why use it?
It helps newcomers understand complex material without removing useful detail for specialists. It also gives long documents a guided structure instead of leaving readers with only dense text.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter.

Runs only inside its plugin — its command needs a path that Claude Code sets for a plugin’s own hooks and for nothing else. Install the plugin, not this.

Part of the architecture-pack plugin — 2 skills, 1 command shipped together

not rated 7repo yesterday A scan 88 tokens original Apache-2.0

Good fit Use it to explain a specification, plan, investigation, or other document with diagrams, step-by-step views, comparisons, and expandable technical notes.

Compare 6 skills from other repositories ↓
View source ↗ atretyak1985/swarmery atretyak1985.github.io
Install

Getting it into your agent

This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.

Claude Code
/plugin marketplace add atretyak1985/swarmery
Claude Code
/plugin install architecture-pack

Made for: Claude Code.

Or install architecture-pack, the plugin that ships this one along with the rest of its 2 skills, 1 command.

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 visual-explainer

README.md
[![agentmods](https://agentmods.dev/badge/skills/atretyak1985/swarmery/visual-explainer/github.svg)](https://agentmods.dev/skills/atretyak1985/swarmery/visual-explainer)
Your own site
<a href="https://agentmods.dev/skills/atretyak1985/swarmery/visual-explainer"><img src="https://agentmods.dev/badge/skills/atretyak1985/swarmery/visual-explainer/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 visual-explainer

Your own site · 80×15
<a href="https://agentmods.dev/skills/atretyak1985/swarmery/visual-explainer"><img src="https://agentmods.dev/badge/skills/atretyak1985/swarmery/visual-explainer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 88 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,098 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.
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 $0.00088 $0.02098
Opus 5.5 $0.00035 $0.00839
Sonnet 5.5 $0.00018 $0.00420
Haiku 4.5 $0.00009 $0.00210

Measured 1mo ago against content hash 0c169451cffa, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

visual-explainer 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 1mo ago.

The scan reads SKILL.md. This mod also ships 6 executable files (scripts/check.mjs, scripts/new-page.mjs, scripts/probe.js, …), 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/architecture-pack/skills/visual-explainer/SKILL.md · 144 lines

How it starts

The opening of the file, as written. The whole thing — 144 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Purpose

Turn a source (a markdown file, several files, or an explanation from the conversation) into one self-contained HTML page that a newcomer can read top to bottom and a specialist can drill into. Two layers, always: plain language and visuals on the page; protocols, file paths, numbers and caveats behind a click (side drawer) or a hover (glossary tooltip).

The page starts from the explainer shell, which already owns navigation, theming, the drawer, tooltips, tabs, a step-through player, scenario switches and filters. You write content and diagrams, not interaction code. scripts/check.mjs and scripts/probe.js then measure the result.

Procedure

  1. Read the whole source. Note the thesis, the mechanisms (what flows where), comparisons, numbers, sequences, decisions, risks and open questions. Every fact on the page must come from the source; keep its "unverified" markers.
  2. Map content to forms before writing markup — read resources/content-mapping.md. Produce a short plan: one row per section with its plain-language claim, the visual that carries it, and what goes to the drawer. A section whose only visual is a table of prose is not done.
  3. Load the companion skills you have (table below). They shape quality; the shell does not replace them.
  4. Start the page from the shell: node "${CLAUDE_PLUGIN_ROOT}/skills/visual-explainer/scripts/new-page.mjs" <out.html>. It copies the project's .claude/templates/explainer-shell.html when the project has one, else this skill's templates/explainer-shell.html, and prints which one it used. Rewrite the token block for this subject, then fill the marked regions: sections, the #glossary island, drawer <template id="d-…"> blocks (markup) or #details entries (plain text). Markup for every component: resources/components.md. Insert content with several Edits of at most ~25 KB each — one huge Write stalls and loses everything when the stream breaks.
  5. Verify — measured, bounded. Read resources/verification.md. Run check.mjs; serve the page with scripts/serve.mjs (127.0.0.1 only, this one file only, stops itself); run the browser matrix (desktop and 400 px, light and dark) with probe.js. Fix everything in one batch, re-run once, stop the server. Do not report success on a pass you did not run after the last edit.
  6. Deliver. The local file is the deliverable. If the page is meant for other people and a publishing tool is available, ask, then convert with scripts/to-artifact.mjs and publish. Tell the user what you checked and what you could not.

Read the full file on GitHub · 144 lines

Files

What ships with it

10 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. 1mo ago First seen · 144 lines · 88 tokens per session scan A 0c169451cffa

Subscribe to this mod's changes

visual-explainer is a skill published in the GitHub repository atretyak1985/swarmery (7 stars, last pushed yesterday), licensed Apache-2.0. It adds 88 tokens to every session and 2,098 once invoked, about $0.0004 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 2026-10-03.

Claude CodeDesign and UXLearning and teachingagentsai-agentsclaude-code-pluginsplugin-marketplace
Related

visual-explainer compared with skills from other repositories

visual-explainer next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
visual-explaineratretyak1985/swarmerySkill7yesterdayApache-2.0A88Claude Code
show-mehumanlayer/humanlayerSkill13k5d agoApache-2.0A25Claude Code
excalidrawfakoli/fakoli-pluginsSkill41mo agoMITA28Claude Code, Codex
recipe-schema-explorefakoli/fakoli-pluginsSkill41mo agoMITA25Claude Code
recipe-create-classroom-coursefakoli/fakoli-pluginsSkill41mo agoMITA15Claude Code
anatomycyborg-garden/hermes-agent-mtSkill14todayMITA15Claude Code, Codex
gws-classroomfakoli/fakoli-pluginsSkill41mo agoMITA17Claude Code