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.
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.
git clone --depth 1 https://github.com/vercel-labs/design-systems-to-agent-skillsnpx agentmods add commands/vercel-labs/design-systems-to-agent-skills/5-assetsWrote 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/commands/vercel-labs/design-systems-to-agent-skills/5-assets)<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.
<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>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 5.1 | $0.00000 | $0.02491 |
| Opus 5 | $0.00000 | $0.01246 |
| Sonnet 5 | $0.00000 | $0.00498 |
| Haiku 4.5 | $0.00000 | $0.00249 |
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.
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:
- Interview — Scope decisions through conversation.
- Extract — Extract verified facts from source code.
- PRD — Generate a closed PRD with zero open questions.
- Generate — Parallel skill file generation.
- Assets — YOU ARE HERE. Exhaustive asset catalog generation.
- Verify — Programmatic verification (no agent session needed).
Process
Step 1: Load inputs
Read the following files from disk:
-
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
-
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
-
Existing skill output — Check
skills/{ds}/for:SKILL.md— routing matrix to updatereferences/{ds}/v{N}/— versioned namespace to place catalogs in
If decisions don't include an Asset Systems section, ask the user:
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.
- 11d ago First seen · 272 lines · 0 tokens per session scan A e092f76f5b4e
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.
Other commands, from other repositories
profile
Save, load, inspect, update, reset, or delete diagram-design client profiles.
ui-flow-review
Review menus, HUD, navigation, and player flow from a UX perspective.
responsive-design-specialist
Use when a layout breaks between sizes. Arbitrary breakpoints, type that does not scale, images that blow out the grid, or a desktop design retrofitted onto mobile.
ppt-image2-editable-rebuild
Rebuild image2 or imagegen reference slides as editable PowerPoint decks.
p3-ux-wireframes
Creates wireframes (ASCII art) for the most important screens with interaction descriptions.
team-ui
Orchestrate UI/UX design team.