design-acquire

design-acquire is a skill for Claude Code from atretyak1985/swarmery. It costs 69 tokens per session (1,866 once invoked), scanned A, original, Apache-2.0.

A guide for converting different kinds of design handoff into a measurable input, such as exported HTML, a ZIP file, a handoff prompt, design-system tokens, or screenshots.

In plain words
What is it for?
It helps locate and unpack design exports, read handoff references, obtain design tokens, and record limitations when only screenshots are available.
Why use it?
It clarifies what each input can reliably show, since screenshots and instructions do not provide the same layout information as rendered HTML.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: mentions Claude Code.

Part of the design-pack plugin — 3 skills, 1 command, 1 agent shipped together

Good fit It helps locate and unpack design exports, read handoff references, obtain design tokens, and record limitations when only screenshots are available.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/atretyak1985/swarmery/design-acquire
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.

Any agent
npx skills add atretyak1985/swarmery --skill design-acquire
Clone the repo
git clone --depth 1 https://github.com/atretyak1985/swarmery

Made for: Claude Code.

Or install design-pack, the plugin that ships this one along with the rest of its 3 skills, 1 command, 1 agent.

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 design-acquire

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/atretyak1985/swarmery/design-acquire"><img src="https://agentmods.dev/badge/skills/atretyak1985/swarmery/design-acquire.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 69 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,866 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 $0.00069 $0.01866
Opus 5 $0.00034 $0.00933
Sonnet 5 $0.00014 $0.00373
Haiku 4.5 $0.00007 $0.00187

Measured 7d ago against content hash 1c146da1e95f, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

design-acquire 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 7d 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.

plugins/design-pack/skills/design-acquire/SKILL.md · 157 lines

How it starts

The opening of the file, as written. The whole thing — 157 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Purpose

Phase 1 of design-implement. Four input shapes arrive in practice, and they do not promise the same thing: only a self-contained HTML export is ground truth for geometry. This skill turns whatever arrived into a path plus an honest statement of what that path can support, and hands both back. It does not extract tokens (Phase 2) and it does not measure anything (design-verify).

The export route in Claude Design

This is the part operators do not find on their own — reproduce it for them exactly:

In Claude Design (claude.ai/design) open the project → the Share menu in the top right corner → the Export section → then either Claude Code — "Implement this design in code" → Send (sends the handoff prompt into the Claude Code session), or Project HTML → Download (downloads a .zip with self-contained HTML/CSS). Pixel work needs Project HTML specifically: the handoff prompt describes intent, while the .zip contains what actually renders.

Input shape 1 — a handoff prompt

The operator pasted a design tool's handoff prompt (or it arrived through Send).

  1. Parse it. Look for a reference to a file or a URL carrying the actual markup.
  2. If the prompt leads to HTML — fetch it and continue with shape 2. The prompt's prose is context, not a substitute.
  3. If it does not — ask for Project HTML and show the route above. A handoff prompt on its own describes intent: it states what the screen means, not the computed values it renders at, so nothing downstream can be measured against it.

Promises: intent and structure. Not geometry, not exact values.

Input shape 2 — a .zip or .html export

  1. Unpack into the working directory: .design-verify/source/<slug>/.
  2. Find the entry document (the top-level index.html, or the single .html at the root of the archive; if several are plausible, list them and let the operator pick — do not guess which screen is meant).
  3. Check self-containment: scan for external network resources (remote stylesheets, webfonts, images, script tags pointing off-host). Record every one of them. They change what renders, so they change the measurement — a font fetched from the network that fails to load in the headless run silently reshapes every text block.
  4. Pass the entry document's path forward.

Read the full file on GitHub · 157 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. 7d ago First seen · 157 lines · 69 tokens per session scan A 1c146da1e95f

Subscribe to this mod's changes

design-acquire is a skill published in the GitHub repository atretyak1985/swarmery (5 stars, last pushed yesterday), licensed Apache-2.0. It adds 69 tokens to every session and 1,866 once invoked, about $0.0003 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 2026-09-03.

Related

Other skills, from other repositories

excalidraw

Create or extend editable Excalidraw diagrams from descriptions or repository evidence using a local skeleton-to-scene converter.

fakoli/fakoli-plugins · 28 tokens

multi-surface-render

Multi-surface rendering with json-render — one JSON spec produces React web, Next.js, React Native, Ink terminal UIs, PDFs, emails, Remotion videos, OG images, and 3D scenes. Covers renderer target selection, registry mapping, and platform APIs (renderToBuffer, renderToStream, renderToFile). Use when generating output…

yonatangross/orchestkit · 98 tokens

web-artifacts-builder-v2

Suite of tools for creating elaborate, multi-component claude.ai HTML artefacts using modern frontend web technologies (React 19, Tailwind CSS v4, shadcn/ui). Use for complex artefacts requiring state management, routing, or shadcn/ui components - not for simple single-file HTML/JSX artefacts.

sammcj/agentic-coding · 73 tokens

design-workflow

A workflow for bringing design handoff files, design tokens, and project design briefs into a code project. It validates the tokens and loads research, system, and specification notes before interface implementation.

modu-ai/moai-cowork · 159 tokens

cosmic

Futuristic sci-fi aesthetic with dark themes, vibrant neon accents, and immersive spatial elements.

bergside/awesome-design-skills · 22 tokens

modern

Contemporary editorial style with serif typography, minimal palettes, and clean layouts for polished digital products.

bergside/awesome-design-skills · 21 tokens