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
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.
git clone --depth 1 https://github.com/vercel-labs/design-systems-to-agent-skillsWrote 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/3-prd)<a href="https://agentmods.dev/commands/vercel-labs/design-systems-to-agent-skills/3-prd"><img src="https://agentmods.dev/badge/commands/vercel-labs/design-systems-to-agent-skills/3-prd/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/3-prd"><img src="https://agentmods.dev/badge/commands/vercel-labs/design-systems-to-agent-skills/3-prd.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 | $0.03301 |
| Opus 5 | $0.00000 | $0.01650 |
| Sonnet 5 | $0.00000 | $0.00660 |
| Haiku 4.5 | $0.00000 | $0.00330 |
Grade A, and why
3-prd 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 — 330 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Stage 3: Closed PRD Generation
Required Capabilities
- File read/write
- User interaction (resolving ambiguities)
- Shell command execution (git)
Objective
Run Stage 3 of the design system skill generation pipeline: closed PRD generation.
Synthesize decisions from Stage 1 and verified facts from Stage 2 into a PRD that specifies every file to generate, its exact content structure, the wave/batch plan, and the sub-agent prompt template. The PRD must have ZERO open questions.
The PRD is the load-bearing checkpoint of the pipeline. Every file generated in Stage 4 is only as good as this document. Errors or ambiguities here multiply across ALL component files — if 68 components are in scope, one bad decision in the PRD produces 68 bad files.
The PRD also serves as the specification for Stage 4 sub-agents. A well-specified PRD means every sub-agent gets identical, unambiguous instructions — preventing prompt drift across batches.
Process
Step 1: Load inputs
Read summary files only — do NOT read individual component fact files. The summaries contain everything needed for the PRD. Reading 50+ component files wastes context budget.
context/{ds}/01-decisions.md— scope, categories, guides, conventionscontext/{ds}/02-verified-facts/imports.md— all validated import pathscontext/{ds}/02-verified-facts/compound-components.md— compound structurescontext/{ds}/02-verified-facts/tokens.md— token catalog- Scan
context/{ds}/02-verified-facts/components/— count extracted components (list filenames, don't read contents) - If
context/{ds}/02b-usage-patterns/exists: readcontext/{ds}/02b-usage-patterns/summary.md— usage-level behavioral patterns from a consuming codebase. This is optional — the directory only exists if Stage 2b was run.
If any input is missing, tell the user which previous stage needs to complete first.
Verify: the number of extracted component files matches the in-scope component list from decisions. Report any discrepancies.
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 · 330 lines · 0 tokens per session scan A 010da54d36bf
3-prd 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 3,301 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.