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 skills add leefanv/omit-design --skill distill-patterns-from-prdgit clone --depth 1 https://github.com/leefanv/omit-designWrote 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/leefanv/omit-design/distill-patterns-from-prd)<a href="https://agentmods.dev/skills/leefanv/omit-design/distill-patterns-from-prd"><img src="https://agentmods.dev/badge/skills/leefanv/omit-design/distill-patterns-from-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/skills/leefanv/omit-design/distill-patterns-from-prd"><img src="https://agentmods.dev/badge/skills/leefanv/omit-design/distill-patterns-from-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 | $0.00087 | $0.01335 |
| Opus 5 | $0.00044 | $0.00668 |
| Sonnet 5 | $0.00017 | $0.00267 |
| Haiku 4.5 | $0.00009 | $0.00134 |
Grade A, and why
distill-patterns-from-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 9d 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 — 104 lines — stays where its author put it; the contents beside it link to each section on GitHub.
distill-patterns-from-prd — extract reusable patterns from a PRD
When to trigger
- The user copied the "Distill patterns from this PRD" prompt from the PRDs tab in the workspace.
- The user explicitly asks "从这份 PRD 里抽 pattern" / "see what patterns this PRD needs" / "distill patterns".
- Invoked upstream by
new-designwhenpatterns/is empty and a PRD exists.
Do not trigger this skill for:
- Generating actual design pages — that's
new-design's job. Stop after patterns land. - Editing an existing pattern — use the workspace Patterns tab or
add-pattern. - Anything not anchored to a concrete PRD body (use
add-patternconversational mode instead).
Output contract
For each new pattern, write three files to <project>/patterns/<id>/:
patterns/<id>/
├── pattern.json { "name": "<id>", "whitelist": ["OmFoo", "OmBar"], "description": "..." }
├── template.tmpl.tsx first line `// @pattern: <id>`; minimal skeleton; TODO placeholders for copy
└── README.md "When to use" / "Skeleton" / "When NOT to use"
Whitelist entries must come from GET /preset/components (the Om* names exported by @omit-design/preset-mobile). Unknown names break ESLint's require-pattern-components rule.
Execution flow
Step 1 — Parse the PRD
Read the body (frontmatter already trimmed by the workspace's clipboard handler). Identify:
- Page count — how many distinct screens does this PRD cover?
- Archetype per screen — list / detail / form / dialog / dashboard / sheet / welcome?
- Data shape per screen — single record / homogeneous list / tree / kanban / table?
- User actions — read / select / fill / submit / compare / dismiss?
Step 2 — Scan existing patterns
ls <project>/patterns/*/pattern.json
cat <project>/patterns/<id>/README.md for each
For each PRD screen, judge: does an existing pattern cover this archetype well enough? Match on the README's "When to use" / "When NOT to use" sections, not just on the name.
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.
- 9d ago First seen · 104 lines · 87 tokens per session scan A 11000cad05bc
distill-patterns-from-prd is a skill published in the GitHub repository leefanv/omit-design (54 stars, last pushed 3mo ago), licensed MIT. It adds 87 tokens to every session and 1,335 once invoked, about $0.0004 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 2026-08-30.
Other skills, from other repositories
moai-design-tools
Design tool integration specialist covering Figma MCP, Pencil renderer, and Pencil-to-code export. Use when fetching design context from Figma, rendering Pencil designs, or exporting to React/Tailwind code.
moai-domain-uiux
UI/UX design systems specialist covering accessibility, icons, theming, design tokens, and user experience patterns. Use when working on design systems, WCAG compliance, ARIA patterns, or dark mode theming.
ux-design
Create comprehensive UX design with user flows, wireframes, and design systems.
premium-experience
Premium app generation that creates WOW-factor experiences. Multi-page apps with smooth animations, zero TypeScript errors, and production-ready quality. Lovable-style experience: one prompt, complete app, instant delight. MUST be used alongside vibe-orchestrator for new projects.
ui-first-builder
Creates production-ready UI immediately from any description. Generates complete pages, components, and realistic mock data in FIRST response. Uses Next.js 16 + Tailwind + shadcn/ui. Never asks questions - infers everything from context. Triggers: UI creation, page building, component generation, build interface…
agentic
Conversational AI-first interface with minimal controls, clear outcomes, and delegated task flows for agentic workflows.