agentmods.dev

visual-explainer

A tool for creating self-contained HTML explanations of technical systems, code changes, plans, and data from MDX or React source files. MDX is Markdown combined with reusable interface components.

In plain words
What is it for?
Use it for architecture diagrams, code walkthroughs, change reviews, project recaps, comparison tables, and other visual technical explanations.
Why use it?
Written descriptions or plain-text diagrams can make complex relationships hard to understand. This produces editable visual explanations that can be exported and checked.

Skill for Claude CodeCodex

2 9d ago A scan 84 tokens original MIT
View the source file theclaymethod/artifacture
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.

agentmods
npx agentmods add skills/theclaymethod/artifacture/visual-explainer
Any agent
npx skills add theclaymethod/artifacture --skill visual-explainer
Clone the repo
git clone --depth 1 https://github.com/theclaymethod/artifacture

Made for: Claude Code, Codex.

Per session 84 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,024 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00084 $0.01024
Opus 5 $0.00042 $0.00512
Sonnet 5 $0.00017 $0.00205
Haiku 4.5 $0.00008 $0.00102

Measured yesterday against content hash 74b73447a2de, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, 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 yesterday.

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/visual-explainer/SKILL.md · 57 lines

How it starts

The opening of the file, as written. The whole thing — 57 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Visual Explainer

Produce an editable MDX/TSX source, export it to self-contained HTML, and verify the result. Use HTML instead of ASCII for substantial diagrams and tables.

Resolve the runtime

Set REPO to the Artifacture checkout before authoring:

  1. If ../../visual-explainer-mdx/components.tsx exists relative to this file, use the repository two directories above this file.
  2. Otherwise, use ~/.artifacture when it contains visual-explainer-mdx/components.tsx and package.json.
  3. If neither exists, clone https://github.com/theclaymethod/artifacture to ~/.artifacture and run npm install --prefix ~/.artifacture, then resume. Require Node 22 or newer. Do not update an existing runtime as a side effect of generation.

Run every npm run ve:* command from REPO. Sources may live elsewhere; pass absolute paths.

Execute the flow

  1. Select one route below and read its card. Covered flows need this file and that card only until a conditional pointer fires.
  2. Author .mdx by default. Use .tsx only for local state, generated/custom SVG, or video. Import shared components from REPO/visual-explainer-mdx/components.tsx as the card shows.
  3. Export with npm --prefix REPO run ve:export -- <abs-source> --out <abs-output>. For static video, use npm --prefix REPO run ve:export-static -- <abs-source.tsx> --out <abs-output>. Fix strict-export failures in the source.
  4. Read verification.md, execute its routed checks, open the artifact, and report the source, HTML, report JSON, and any incomplete verification.

Completion requires an editable source, a successful export, and evidence for every required verification pass. Apply feedback to the source and re-export.

Route

Request Read first Read only when needed
diagram or architecture web-diagram.md The card routes custom geometry and specialized diagrams.
implementation plan visual-plan.md —
comparison or data table comparison-table.md —
slides or presentation slide-deck.md For bespoke fixed-stage presentation chrome, read deck-navigation-shell.md, then slide-patterns.md.
code walkthrough code-walkthrough.md —
explain a diff explain-diff.md —
project recap project-recap.md —

Read the full file on GitHub · 57 lines

Files

What ships with it

60 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. yesterday First seen · 57 lines · 84 tokens per session scan A 74b73447a2de

Subscribe to this mod's changes

visual-explainer is a skill published in the GitHub repository theclaymethod/artifacture (2 stars, last pushed 9d ago), licensed MIT. It adds 84 tokens to every session and 1,024 once invoked, about $0.0004 per session on Opus 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 2026-08-31.

Code reviewFrontendPlanningagent-skillsai-agentsclaude-codeclaude-code-pluginhtml-generationmdx
Related

Other skills, from other repositories

korean-privacy-terms

처리방침·이용약관 자동 생성 스킬 패키지 (v4.0). 호출 시 privacy-kr·privacy-eu·privacy-us·privacy-global 4개 하위 스킬을 번호 메뉴로 제시하고 번호 입력 즉시 해당 스킬 인터뷰로 직행. 한국 PIPA + EU GDPR + US CCPA/CPRA 대응.

kimlawtech/korean-privacy-terms · 86 tokens

privacy-us

미국 CCPA/CPRA + 주요 주법(VCDPA·CPA·CTDPA·UCPA·ICDPA·KCDPA·RIDPA) 기반 Privacy Policy 자동 생성. 2026.1.1 CPPA 갱신 규정, Sensitive Personal Information, Do Not Sell/Share, ADMT 공개, GPC 브라우저 신호 대응. 캘리포니아 거주자 서비스·100K records 초과 서비스 대상.

kimlawtech/korean-privacy-terms · 101 tokens

privacy-global-jp

한국+일본 병기 처리방침·이용약관 자동 생성. 한국 본사가 일본 사용자까지 대상으로 서비스할 때 사용. 한국어(PIPA)·일본어(APPI) 두 세트 문서를 동시 생성하고, Footer에 언어·관할 전환 링크 자동 삽입.

kimlawtech/korean-privacy-terms · 71 tokens

privacy-eu

EU 사용자 대상 서비스용 Privacy Notice·Terms of Service·Consent Modal·Cookie Banner 자동 생성. GDPR (Regulation 2016/679) + ePrivacy Directive + Consumer Rights Directive 2011/83 + Digital Services Act + Digital Content Directive + Unfair Terms Directive 반영. 영문 인터뷰로 진행.

kimlawtech/korean-privacy-terms · 70 tokens

privacy-global

한국+EU 병기 처리방침·이용약관 자동 생성. 한국 본사가 EU 사용자까지 대상으로 서비스할 때 사용. 한국어(PIPA)·영문(GDPR) 두 세트 문서를 동시 생성하고, Footer에 언어·관할 전환 링크 자동 삽입.

kimlawtech/korean-privacy-terms · 68 tokens

privacy-jp

日本サービス向け（일본 서비스용） プライバシーポリシー・利用規約・同意モーダル・Cookieバナー 자동 생성. 個人情報保護法(APPI)·消費者契約法·特定商取引法 반영. Next.js 1316 프로젝트 대상.

kimlawtech/korean-privacy-terms · 74 tokens