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 marcusgoll/Spec-Flow --skill mockup-extractiongit clone --depth 1 https://github.com/marcusgoll/Spec-FlowWrote 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/marcusgoll/spec-flow/mockup-extraction)<a href="https://agentmods.dev/skills/marcusgoll/spec-flow/mockup-extraction"><img src="https://agentmods.dev/badge/skills/marcusgoll/spec-flow/mockup-extraction.svg" alt="Measured on agentmods" 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 | $0.00048 | $0.04314 |
| Opus 5 | $0.00024 | $0.02157 |
| Sonnet 5 | $0.00010 | $0.00863 |
| Haiku 4.5 | $0.00005 | $0.00431 |
Grade A, and why
mockup-extraction 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 4d 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 — 603 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Purpose: Bridge the gap between visual mockups and production code by:
- Identifying repeated UI patterns across mockup screens
- Mapping mockup CSS classes to Tailwind utilities
- Documenting component variants and states
- Creating extraction tasks for systematic implementation
When to invoke: At the start of /implement phase when mockups exist and are approved (UI-first features).
<quick_start> Before extraction, verify:
- Mockups exist in
specs/NNN-slug/mockups/ordesign/prototype/screens/ - Mockup approval gate passed in state.yaml
- Theme files exist (theme.yaml, theme.css)
<basic_workflow>
- Inventory - List all mockup HTML files
- Scan - Parse HTML for component patterns
- Classify - Categorize by component type
- Count - Track occurrence frequency
- Map - Convert CSS to Tailwind utilities
- Document - Populate prototype-patterns.md
- Generate Tasks - Create extraction tasks for tasks.md </basic_workflow>
<extraction_output>
Generate prototype-patterns.md in feature directory:
# Prototype Patterns: {FEATURE_NAME}
## Component Inventory
| Component | Source Screens | Occurrences | Priority |
|-----------|---------------|-------------|----------|
| Button Primary | login, signup, dashboard | 12 | Must extract |
| Card | dashboard, settings | 8 | Must extract |
| Form Input | login, signup, profile | 15 | Must extract |
| Alert | all screens | 6 | Consider extraction |
## Component Details
### Button Primary
- **CSS Classes**: `.btn`, `.btn-primary`
- **Tailwind**: `px-4 py-2 bg-primary text-white rounded-md hover:bg-primary-hover`
- **States**: default, hover, focus, disabled, loading
- **Props**: `variant`, `size`, `icon`, `loading`
### Card
- **CSS Classes**: `.card`, `.card-elevated`
- **Tailwind**: `bg-surface p-4 rounded-lg shadow-md`
- **Variants**: default, elevated, bordered
- **Props**: `padding`, `shadow`, `header`, `footer`
## CSS to Tailwind Mapping
| CSS Variable | Tailwind Utility |
|--------------|------------------|
| var(--color-primary) | bg-primary, text-primary |
| var(--space-4) | p-4, m-4, gap-4 |
| var(--radius-md) | rounded-md |
| var(--shadow-md) | shadow-md |
## Visual Fidelity Checklist
- [ ] Spacing matches 8pt grid
- [ ] Colors use design tokens
- [ ] All states implemented (hover, focus, disabled)
- [ ] Typography uses scale
- [ ] Responsive breakpoints match
</extraction_output> </quick_start>
<detailed_procedures> <component_identification>
Component Identification Rules
Scan mockup HTML for these patterns:
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 4d ago First seen · 603 lines · 48 tokens per session scan A 67753d569368
mockup-extraction is a skill published in the GitHub repository marcusgoll/Spec-Flow (92 stars, last pushed 4mo ago), licensed MIT. It adds 48 tokens to every session and 4,314 once invoked, about $0.0002 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.
Other skills, from other repositories
skill-frontend-ux-guardrails
Apply frontend UX quality gates for SaaS dashboards, product screens, modals, tables, forms, responsive layouts, overflow fixes, accessibility, visual validation, spelling, and reduction of UI rework.
skill-modern-ui-patterns
Use for professional SaaS UI implementation and refinement in React, TypeScript, Tailwind, dashboards, admin panels, tables, forms, settings, billing, onboarding, responsive layouts, component states, and design-system consistency.
skill-impeccable
Orquestra melhorias de frontend inspiradas no Impeccable a partir de pedidos conversacionais de design, UX, acessibilidade, responsividade, tipografia, layout, cor, motion, clareza, hardening e polish.
mobile-only-responsive-navigation
Mobile-only responsive navigation guidance for RTL Persian sites. Use when improving hamburger menus, drawers, touch targets, and mobile theme controls without changing desktop layout.
mobile-ux-responsive-navigation-notes
Curated notes adapted from reviewed public Agent Skill repositories for mobile UX, responsive navigation, accessibility, and anti-slop frontend polish.
ui-styling
Create beautiful, accessible user interfaces with shadcn/ui components (built on Radix UI + Tailwind), Tailwind CSS utility-first styling, and canvas-based visual designs. Use when building user interfaces, implementing design systems, creating responsive layouts, adding accessible components (dialogs, dropdowns…