5-assets

5-assets is a command for Claude Code from vercel-labs/design-systems-to-agent-skills. It costs 0 tokens per session (2,491 once invoked), scanned A, original, MIT.

A step in a design-system documentation pipeline that builds a complete catalogue of reusable visual assets. These assets can include icons, logos, and illustrations, along with their names and import paths.

In plain words
What is it for?
Use it to document every available icon, logo, illustration, or similar asset for a design system and show where each one can be imported.
Why use it?
A complete list helps developers and coding agents find existing assets instead of inventing names or duplicating files. It extracts the catalogue from source data or asset folders.

Command for Claude Code ✓ vendor

Written for Claude Code: a Claude Code command (commands/*.md).

Needs its repository: it runs a file that does not travel with it, so clone the repository first. The line is ./scripts/extract-asset-names.sh \.

Good fit Use it to document every available icon, logo, illustration, or similar asset for a design system and show where each one can be imported.

Compare 6 commands from other repositories ↓
About the project

DS Skills Pipeline is a command-line workflow that turns a design system's source code into structured skills for coding agents. It extracts verified tokens, components, icons, assets, usage patterns, and import paths, then generates and verifies reference files that agents can use when working with the design system.

vercel-labs/design-systems-to-agent-skills · 37 stars · on GitHub

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/vercel-labs/design-systems-to-agent-skills
agentmods
npx agentmods add commands/vercel-labs/design-systems-to-agent-skills/5-assets

Made for: Claude Code.

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 5-assets

README.md
[![agentmods](https://agentmods.dev/badge/commands/vercel-labs/design-systems-to-agent-skills/5-assets/github.svg)](https://agentmods.dev/commands/vercel-labs/design-systems-to-agent-skills/5-assets)
Your own site
<a href="https://agentmods.dev/commands/vercel-labs/design-systems-to-agent-skills/5-assets"><img src="https://agentmods.dev/badge/commands/vercel-labs/design-systems-to-agent-skills/5-assets/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 5-assets

Your own site · 80×15
<a href="https://agentmods.dev/commands/vercel-labs/design-systems-to-agent-skills/5-assets"><img src="https://agentmods.dev/badge/commands/vercel-labs/design-systems-to-agent-skills/5-assets.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,491 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 $0.00000 $0.02491
Opus 5 $0.00000 $0.01246
Sonnet 5 $0.00000 $0.00498
Haiku 4.5 $0.00000 $0.00249

Measured 11d ago against content hash e092f76f5b4e, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

5-assets 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 11d 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.

commands/5-assets.md · 272 lines

How it starts

The opening of the file, as written. The whole thing — 272 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Stage 5: Asset Catalog Generation

Required Capabilities

  • File read/write
  • Shell command execution (bash scripts, git)
  • User interaction (confirming asset source locations)

Objective

Run Stage 5 of the design system skill generation pipeline: asset catalog generation.

Produce exhaustive asset catalogs (icons, logos, illustrations, etc.) for every asset system identified in Stage 1. Asset catalogs are lookup tables — every name, every import path — that eliminate name hallucination by giving agents a complete enumeration to search instead of guessing.

This stage combines extraction and generation in one step because:

  • Asset extraction is mechanical (read name arrays or scan directories) — no AI interpretation needed
  • Catalog format is standardized — no PRD needed
  • Output is tables not prose — minimal hallucination risk

The pipeline stages:

  1. Interview — Scope decisions through conversation.
  2. Extract — Extract verified facts from source code.
  3. PRD — Generate a closed PRD with zero open questions.
  4. Generate — Parallel skill file generation.
  5. Assets — YOU ARE HERE. Exhaustive asset catalog generation.
  6. Verify — Programmatic verification (no agent session needed).

Process

Step 1: Load inputs

Read the following files from disk:

  1. context/{ds}/01-decisions.md — Check the Asset Systems section for:

    • Which asset types are in scope (icons, logos, illustrations, pixels, etc.)
    • Source package names and paths for each asset system
    • Whether assets live in the main package or a separate assets package
  2. context/{ds}/02-verified-facts/ — Check if any asset data was already extracted in Stage 2:

    • assets/icons.md, assets/logos.md, etc.
    • If these exist, they contain partial or complete inventories to build on
  3. Existing skill output — Check skills/{ds}/ for:

    • SKILL.md — routing matrix to update
    • references/{ds}/v{N}/ — versioned namespace to place catalogs in

If decisions don't include an Asset Systems section, ask the user:

Read the full file on GitHub · 272 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. 11d ago First seen · 272 lines · 0 tokens per session scan A e092f76f5b4e

Subscribe to this mod's changes

5-assets is a command published in the GitHub repository vercel-labs/design-systems-to-agent-skills (37 stars, last pushed 4mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 2,491 tokens. 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 2026-08-30.