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.
npx agentmods add skills/hk-hub/agentskills/archifynpx skills add HK-hub/AgentSkills --skill archifygit clone --depth 1 https://github.com/HK-hub/AgentSkillsWrote 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.
[](https://agentmods.dev/skills/hk-hub/agentskills/archify)<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>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.
| Model | Per session | Once 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 |
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.
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.
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.
- assets/template.html 586 KB
- bin/archify.mjs 48 KB runs code
- bin/open-artifact.mjs 2.2 KB runs code
- bin/preview.mjs 24 KB runs code
- delta/architecture-delta.mjs 69 KB runs code
- examples/agent-run.lifecycle.json 4.3 KB
- examples/agent-tool-call.workflow.json 6.3 KB
- examples/async-job-roundtrip.sequence.json 4.4 KB
- examples/cache-miss-request.sequence.json 4.3 KB
- examples/checkout-platform.base.architecture.json 2.3 KB
- examples/checkout-platform.head.architecture.json 2.4 KB
- examples/dataflow-product-analytics.html 603 KB
- examples/deployment-release.lifecycle.json 4.3 KB
- examples/event-stream.dataflow.json 5.4 KB
- examples/incident-response.workflow.json 5.3 KB
- examples/lifecycle-agent-run.html 596 KB
- examples/product-analytics.dataflow.json 5.6 KB
- examples/production-deployment.architecture.json 5.4 KB
- examples/release-delivery.workflow.json 5.1 KB
- examples/sequence-cache-miss-request.html 599 KB
- examples/web-app-rendered.html 597 KB
- examples/web-app.architecture.json 3.8 KB
- examples/workflow-agent-tool-call-rendered.html 605 KB
- LICENSE 1.1 KB
- package-lock.json 2.5 KB
- package.json 1016 B
- recipes/scenarios.mjs 27 KB runs code
- renderers/architecture/grid.mjs 2.0 KB runs code
- renderers/architecture/render-architecture.mjs 21 KB runs code
- renderers/dataflow/README.md 3.6 KB
- renderers/dataflow/render-dataflow.mjs 17 KB runs code
- renderers/lifecycle/README.md 4.5 KB
- renderers/lifecycle/render-lifecycle.mjs 21 KB runs code
- renderers/sequence/README.md 3.8 KB
- renderers/sequence/render-sequence.mjs 17 KB runs code
- renderers/shared/cli.mjs 9.4 KB runs code
- renderers/shared/diagnostics.mjs 4.0 KB runs code
- renderers/shared/engineering-profiles.mjs 6.8 KB runs code
- renderers/shared/generated-validators.mjs 278 KB runs code
- renderers/shared/geometry.mjs 44 KB runs code
- renderers/shared/layout-report.mjs 1015 B runs code
- renderers/shared/repository-evidence.mjs 11 KB runs code
- renderers/shared/utils.mjs 8.1 KB runs code
- renderers/shared/validator.mjs 3.4 KB runs code
- renderers/workflow/README.md 4.9 KB
- renderers/workflow/render-workflow.mjs 25 KB runs code
- schemas/architecture.schema.json 5.5 KB
- schemas/common.schema.json 1.7 KB
- schemas/dataflow.schema.json 5.1 KB
- schemas/lifecycle.schema.json 5.5 KB
- schemas/README.md 6.6 KB
- schemas/sequence.schema.json 4.3 KB
- schemas/workflow.schema.json 7.4 KB
- scripts/check-render-output.mjs 29 KB runs code
- scripts/generate-validators.mjs 2.3 KB runs code
- scripts/render-examples.mjs 1.2 KB runs code
- test/animation.test.mjs 8.2 KB runs code
- test/architecture-delta.test.mjs 22 KB runs code
- test/authored-reachability.test.mjs 4.4 KB runs code
- test/automatic-port-spread.test.mjs 8.7 KB runs code
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.
- 4d ago First seen · 417 lines · 187 tokens per session scan A d98b8cff4e88
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.
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.
diagram-generation
Generate self-contained HTML architecture diagrams. Use when creating visual diagrams for PRs, task plans, or architectural explanations.
plannotator-annotate
Open Plannotator's annotation UI for a file, folder, or URL, then address the returned annotations.
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.
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…
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…