archify

archify is a skill for Claude Code, Codex from wangdong233/media-gen-mcp. It costs 307 tokens per session (12,891 once invoked), scanned A, original, MIT.

A tool for creating interactive technical diagrams as standalone HTML files, with SVG graphics and controls for exploring relationships and reading depth.

In plain words
What is it for?
It is for making explorable architecture, sequence, lifecycle, and dependency diagrams with search, navigation, themes, and image export.
Why use it?
It helps readers inspect complex architecture, workflows, data flows, and state changes without relying on static images.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Needs its repository: it runs a file that does not travel with it, so clone the repository first. The line is node bin/archify.mjs inspect architecture my.architecture.json.

Good fit It is for making explorable architecture, sequence, lifecycle, and dependency diagrams with search, navigation, themes, and image export.

Compare 6 skills from other repositories ↓
Install

Getting it into your agent

It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.

Clone the repo
git clone --depth 1 https://github.com/wangdong233/media-gen-mcp
agentmods
npx agentmods add skills/wangdong233/media-gen-mcp/archify

Made for: Claude Code, Codex.

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 archify

README.md
[![agentmods](https://agentmods.dev/badge/skills/wangdong233/media-gen-mcp/archify/github.svg)](https://agentmods.dev/skills/wangdong233/media-gen-mcp/archify)
Your own site
<a href="https://agentmods.dev/skills/wangdong233/media-gen-mcp/archify"><img src="https://agentmods.dev/badge/skills/wangdong233/media-gen-mcp/archify/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 archify

Your own site · 80×15
<a href="https://agentmods.dev/skills/wangdong233/media-gen-mcp/archify"><img src="https://agentmods.dev/badge/skills/wangdong233/media-gen-mcp/archify.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 307 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 12,891 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 $0.00307 $0.12891
Opus 5 $0.00153 $0.06445
Sonnet 5 $0.00061 $0.02578
Haiku 4.5 $0.00031 $0.01289

Measured 4d ago against content hash ead3157bfdf2, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

archify 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 4d ago.

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.

.doc-archive-snapshot/doc_v11/archify-investigation/archify_SKILL.md · 348 lines

How it starts

The opening of the file, as written. The whole thing — 348 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Archify Skill

Create professional technical diagrams as self-contained HTML files with inline SVG, a theme toggle, and a built-in image/SVG export menu.

Every renderer-backed diagram ships with a factual Diagram Guide for discovering its current actions and shortcuts, deterministic semantic node hooks, a counted two-kind Semantic Lens with selective inline legend entrances, a fine-pointer/keyboard Intent Trace before committed focus, a two-endpoint Route Probe over authored directed relationships, a searchable Node Finder, keyboard-accessible one-hop focus with a renderer-owned Semantic Passport and copyable deep link, a live Semantic Radar overview, an optional Named Chapter Rail with static Chapter Delta Preview, a native Story Beat Navigator with Story Follow Camera, Story Director Strip, and Story Horizon, and stable Shareable Story Moment links, a reader-controlled Live/Still Motion Governor for trace artifacts, a viewer-only Share Chapter Cue for one-shot embeds, Presentation Stage, dependency-free pan/zoom, a dark/light theme toggle (persists in localStorage, respects prefers-color-scheme), an export menu (copy PNG to clipboard; download PNG/JPEG/WebP rasterized natively at up to 4× resolution; download a dual-theme SVG; record a trace-enabled diagram to WebM), and a CSS-variable color system that keeps both themes consistent. Temporary Diagram Guide, Semantic Lens, legend preview, Intent Trace, Route Probe, finder, focus, radar, Chapter Delta Preview, Story Trail overlays, Story Director Strip, Story Horizon, beat state, guided-view, playback, presentation, motion-owner, and viewport state never changes the canonical full-diagram export.

Reading Depth progressively reveals renderer-owned context and fine detail as the reader zooms, while semantic interactions reveal the exact local facts they need at any scale.

Direct Relationship Pin makes every unique compiled relationship directly operable without changing the authored line. Give important connections, edges, messages, flows, and transitions an optional author-controlled id using the normal identifier pattern; IDs must be unique within their relationship collection. The renderer keeps its numeric data-edge-key for runtime de-duplication and emits the author identity separately as data-edge-id. At runtime, reject conflicting source/target/label/ID metadata and clone only path/line/polyline geometry into one viewer-owned overlay below nodes. Use a transparent 24px non-scaling stroke for hit testing plus a separate dashed focus rail; keep exactly one relationship button at tabindex="0" and move roving focus with all Arrow keys, Home, and End. Fine-pointer hover and keyboard focus reuse exact Relationship Preview transiently. Click, tap, Enter, or Space opens the source Semantic Passport and pins the exact existing Lens row. When the relationship has an authored ID, the pin writes #relation=<id>, changes the action to Copy relation, and restores the same source, target, label, path, and bounded camera after reordering; stale IDs fail closed. An ID-less legacy relationship remains an in-page pin, keeps Copy node, and never exposes its numeric key. The same relationship, a true background activation, Clear, or Escape clears it. aria-pressed conveys the pin while the source/target/label name stays stable. Touch never waits for hover, nodes win near endpoints, panning never activates a relation, and stronger Focus, Story, Route, Semantic Lens, Chapter, and embed states take priority. Do not add another panel, toolbar action, dependency, storage, or authored geometry. Remove all hit, pin, preview, and pulse state from embed, print, and canonical export; preserve the authored data-edge-id as semantic SVG identity.

Read the full file on GitHub · 348 lines

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. 4d ago First seen · 348 lines · 307 tokens per session scan A ead3157bfdf2

Subscribe to this mod's changes

archify is a skill published in the GitHub repository wangdong233/media-gen-mcp (0 stars, last pushed 5d ago), licensed MIT. It adds 307 tokens to every session and 12,891 once invoked, about $0.0015 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 2026-09-04.

Related

Other skills, from other repositories

fin-arch-diagram

A tool for creating architecture diagrams, process flowcharts, and hierarchy trees. These show how system parts, business steps, decisions, or organizational levels relate to one another.

csmar432/finai-research · 72 tokens

kami

A design and typesetting guide for creating professional documents and product landing pages, such as resumes, white papers, portfolios, and slide decks.

tw93/Kami · 157 tokens

read

Reads URLs and PDFs by fetching source content, defaulting to concise summaries for plain read requests and clean Markdown when asked to convert, save, quote, cite, or feed downstream work. Use when users ask in any language to read, fetch, check, summarize, quote, cite, convert, or save a URL or PDF. Not for local…

tw93/Waza · 78 tokens

mermaid-tools

Extracts Mermaid diagrams from markdown files and generates high-quality PNG images using bundled scripts. Activates when working with Mermaid diagrams, converting diagrams to PNG, extracting diagrams from markdown, or processing markdown files with embedded Mermaid code.

daymade/claude-code-skills · 48 tokens

excel-mcp

Excel MCP Server skill for Windows workbook automation. Use when an assistant needs rich MCP tools to create, inspect, modify, format, or analyze Excel files. Supports Power Query (M), Data Model/DAX, PivotTables, Tables, Ranges, Charts, Slicers, formatting, screenshots, VBA macros, connections, and calculation mode.…

sbroenne/mcp-server-excel · 106 tokens

industrial-kaizen

A visual design guide built around warm neutral colours, strict tables, aligned numbers, thin dividing lines, and restrained typography. It is intended for reports and business pages where information density matters.

arcsin1/oh-my-ppt · 0 tokens