archify

archify is a skill for Claude Code, Codex from HK-hub/AgentSkills. It costs 187 tokens per session (15,996 once invoked), scanned A, original, MIT.

A diagram-making workflow for turning plain-language requirements into standalone HTML diagrams. It supports architecture, process, sequence, data-flow, and lifecycle or state diagrams with interactive navigation and image or SVG export.

In plain words
What is it for?
Use it to create technical diagrams, trace relationships between components, inspect nodes, navigate diagram chapters, present a story through the diagram, and export images or SVG files.
Why use it?
It helps explain complex systems and workflows in a form people can explore, search, present, and share without installing extra software.

Skill for Claude CodeCodex

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/hk-hub/agentskills/archify
Any agent
npx skills add HK-hub/AgentSkills --skill archify
Clone the repo
git clone --depth 1 https://github.com/HK-hub/AgentSkills

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/hk-hub/agentskills/archify.svg)](https://agentmods.dev/skills/hk-hub/agentskills/archify)
Your own site
<a href="https://agentmods.dev/skills/hk-hub/agentskills/archify"><img src="https://agentmods.dev/badge/skills/hk-hub/agentskills/archify.svg" alt="Measured on agentmods" height="20"></a>
Per session 187 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 15,996 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 $0.00187 $0.15996
Opus 5 $0.00093 $0.07998
Sonnet 5 $0.00037 $0.03199
Haiku 4.5 $0.00019 $0.01600

Measured 4d ago against content hash d98b8cff4e88, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, 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.

The scan reads SKILL.md. This mod also ships 27 executable files (bin/archify.mjs, bin/open-artifact.mjs, bin/preview.mjs, …), 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.

archify/SKILL.md · 417 lines

How it starts

The opening of the file, as written. The whole thing — 417 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 (create, copy, or download a 1200×630 Share Card; copy full-diagram 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.

Offer the optional 1200×630 Share Card PNG when the user asks for a README, release, social, or launch preview. It uses the current theme and visual preset, contains the entire canonical diagram without cropping, and never claims validation; the checked HTML remains the source of any delivery receipt. When the browser supports image clipboard writes, Copy Share Card must reuse that same one-pass canonical PNG; unsupported readers retain the download action.

Route Share Card is a reader-invoked optional export, never a default generation or delivery mode. When the user wants to share an incident path, request chain, dependency route, or PR explanation, offer the choice to resolve a Route Probe and use Export → Route Share Card; otherwise keep ordinary Share Card and canonical exports unchanged. The contextual Export item appears only after a real directed route resolves, reuses that exact ordered node and stable-edge snapshot without re-running pathfinding, preserves the full diagram as dimmed context, and downloads one 1200×630 PNG named <diagram-base>-route-share-card.png. It remains the shared Share Card seam (Archify.exportMenu.shareCard({ variant: "route" })) with format=share-card and variant=route; clear, unreachable, stale, or conflicting routes must fail closed. The isolated clone may use only static data-share-route-* decoration and must not include Journey position, animation overlays, camera, Focus, Lens, or Story state. Do not claim the route variant is canonical. This slice is download-only: do not promise Copy Route Share Card, a new format, schema, layout, dependency, URL, or storage surface.

Reach Share Card is the corresponding reader-invoked export for an active authored reachability query. When the user wants to explain what authored relationships lead into a component or continue from it, focus that node, choose Upstream or Downstream, then offer Export → Reach Share Card. The item must remain hidden unless a non-empty reach result is active. It consumes the already resolved node IDs, stable edge keys, minimum depths, origin, direction, and maximum hops without running BFS again; stale, duplicate, conflicting, empty, or tampered DOM state fails closed. The shared 1200×630 seam is Archify.exportMenu.shareCard({ variant: "reach" }), with format=share-card, variant=reach, canonical=false, and an independent reach-state-clean receipt. The clone may use only static data-share-reach-* decoration, keeps the complete diagram as dimmed context, labels the header Authored upstream/downstream, and downloads <diagram-base>-<direction>-reach-share-card.png. Never call the asset impact, blast radius, breakage, or runtime causality. This is download-only and adds no copy action, format, schema, parser, layout, dependency, URL, storage, hosted service, or mobile product surface.

Read the full file on GitHub · 417 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. 4d ago First seen · 417 lines · 187 tokens per session scan A d98b8cff4e88

Subscribe to this mod's changes

archify is a skill published in the GitHub repository HK-hub/AgentSkills (6 stars, last pushed 17d ago), licensed MIT. It adds 187 tokens to every session and 15,996 once invoked, about $0.0009 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.

Related

Other skills, from other repositories

mermaid

Create, validate, and repair Mermaid.js diagrams. Use when generating flowcharts, sequence, class, ER, state, or Gantt diagrams, or any visualization.

rp1-run/rp1 · 36 tokens

diagram-generation

Generate self-contained HTML architecture diagrams. Use when creating visual diagrams for PRs, task plans, or architectural explanations.

comet-ml/opik · 26 tokens

plannotator-annotate

Open Plannotator's annotation UI for a file, folder, or URL, then address the returned annotations.

backnotprop/plannotator · 29 tokens

devx-ux

Activate when designing or modifying CLI command surfaces, command help text, install/init/run flows, error wording, or first-run experience in the APM CLI -- even when the user does not say "UX" explicitly.

microsoft/apm · 48 tokens

visual-qa

MUST USE after building/changing any UI or when asked whether a page, component, or TUI looks right. Rigorous visual QA across web/page, terminal, and paginated-document surfaces. Prefer browser:control-in-app-browser for unauthenticated browser/page QA in Codex, then Playwright/agent-browser/dev-browser. Captures…

code-yeongyu/oh-my-openagent · 161 tokens

frontend

MUST USE for frontend/web UI/UX/visual work: building, styling, redesigning pages/components, React setup, performance audits, visual QA, taste, and polish. Routes four rulesets: design taste router and brand references; perfection for Playwright/Chromium Lighthouse/Core Web Vitals; ui-ux-db palettes/fonts/guidelines…

code-yeongyu/oh-my-openagent · 183 tokens