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 tomzx/agents --skill create-mockupsgit clone --depth 1 https://github.com/tomzx/agentsWrote 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/tomzx/agents/create-mockups)<a href="https://agentmods.dev/skills/tomzx/agents/create-mockups"><img src="https://agentmods.dev/badge/skills/tomzx/agents/create-mockups/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/tomzx/agents/create-mockups"><img src="https://agentmods.dev/badge/skills/tomzx/agents/create-mockups.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 | $0.00034 | $0.02379 |
| Opus 5.5 | $0.00014 | $0.00952 |
| Sonnet 5.5 | $0.00007 | $0.00476 |
| Haiku 4.5 | $0.00003 | $0.00238 |
Grade A, and why
create-mockups scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 22d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 202 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Create Mockups
Produces UI mockups for a feature from its requirements and specification, settling the visual layout, component breakdown, interaction states, and flows before a line of UI code is written.
Each screen is delivered as a self-contained HTML document under .sdlc/features/N-<slug>/mockups/, with a companion mockups.md that carries the narrative: regions, components, states, flow, responsiveness, accessibility, and copy.
Without this step, UI work starts with no shared picture of what to build, so layout, states, and accessibility are improvised during implementation and reworked in review.
For features with no user interface (a pure API, a background job, a CLI), skip this phase and state the skip explicitly.
Prerequisites
- Apply the shared SDLC conventions in
skills/sdlc/references/shared.md. - If no argument is provided, locate the feature directory under
.sdlc/features/whose frontmatterissuefield references$ISSUE_NUMBER. .sdlc/features/N-<slug>/requirements.md(must have passed review with findings verdictapproved), or a requirements document provided in context or as a file path ($1).sdlc/features/N-<slug>/specification.md(must have passed review with findings verdictapproved, if produced): reuse the data models, API contracts, and flows it defines so the mockups stay faithful to what the system can actually deliver.sdlc/features/N-<slug>/lifecycle.md(optional, if a lifecycle document was produced): reflect resource states and transitions in the UI states (e.g., show different views or disabled actions based on the resource's current state).sdlc/features/N-<slug>/codebase-analysis.md(optional, if existing code was analyzed): reuse existing UI components and patterns it inventoried, and honor any "must not change" constraints on shared components
Steps
- Read the requirements, the specification if present, and the codebase analysis if present.
- Decide whether the feature has a UI surface.
If it does not, emit
verdict: skipped(do not writemockups.mdand do not create themockups/directory). Theskippedverdict routes the pipeline straight to the next phase, bypassing/review-mockups. - Inventory every screen, view, or dialog the feature needs, cross-referenced against the requirements and the spec's flows.
- For each screen, author a self-contained HTML mockup at
.sdlc/features/N-<slug>/mockups/<screen-slug>.html. The document shows the layout, labels each region, highlights the primary action, and renders every interaction state as its own labelled section. It uses inline CSS only (no external stylesheets, scripts, fonts, or images, and no build step) so it opens directly in a browser fromfile://. Media queries cover the target viewports so resizing the window demonstrates the responsive behavior. - Break the UI down into components, marking which already exist in the codebase (reuse), which must be extended, and which are new.
- For each key component and screen, enumerate its interaction states: empty, loading, populated, error, and disabled or read-only where relevant. Each state also appears as a labelled section in the screen's HTML mockup.
- Map the navigation between screens as a flow, including entry points, exits, and the back path, rendered as a Mermaid flowchart in
mockups.md. - Specify responsive behavior across the viewports the feature targets (mobile, tablet, desktop), noting what collapses, reorders, or hides.
- Call out accessibility requirements: keyboard reachability, focus order and visible focus, screen-reader labels, color-contrast targets, and minimum touch-target sizes.
- Note copy and content as placeholders so writers can fill them without changing layout.
- Flag where a static HTML mockup is insufficient (motion, drag-and-drop, canvas, real data density, interactive prototype behavior) and a Figma file or clickable prototype is warranted, with a pointer or request.
- Write the narrative to
.sdlc/features/N-<slug>/mockups.md, linking each screen to its HTML mockup.
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.
- 22d ago Changed · +45 lines a93c449aabbb
- 23d ago Changed · -4 lines d19519ecc886
- 2mo ago First seen · 161 lines · 34 tokens per session scan A e12a8d2da57c
create-mockups is a skill published in the GitHub repository tomzx/agents (13 stars, last pushed yesterday), licensed MIT. It adds 34 tokens to every session and 2,379 once invoked, about $0.0001 per session on Opus 5.5. 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 2026-08-31.
Other skills, from other repositories
webgl-holographic-foil
A self-contained WebGL2 hero: thin-film interference over a crushed-foil surface whose palette shifts with the viewing angle; move the cursor to tilt the film.
html-ppt-hermes-cyber-terminal
OpenDesign + BYOK: choosing and wiring your own model, hands-on — cost, quality, and the routing decision. Built as a decision-grade AI literacy deck for engineers, IT, applied-AI teams.
html-ppt-taste-brutalist
16:9 HTML deck in tactical-telemetry / CRT-terminal taste. Deactivated-CRT charcoal slides, white-phosphor monospace, hazard-red accent, scanline overlay, ASCII syntax, density over decoration. Distilled from Leonxlnx/taste-skill brutalist-skill (Tactical Telemetry mode).
visual-ralph
Visual Ralph orchestration for frontend UI from generated references, static references, or live URL targets, using $ultragoal with built-in visual verdict and pixel-diff evidence until the implementation matches and leaves a reproducible design system.
glance-canonical-layouts
Use this skill to create home screen widgets using Jetpack Glance Canonical Layouts from the Android Platform Samples project, or when asked to implement standard widget layout patterns (including Check List, Image Grid, Snap Scrolling, and Standard Toolbar).
accessibility
Consolidated accessibility skill entrypoint for WCAG 2.2, ARIA Authoring Practices, cognitive accessibility, Section 508, EN 301 549, design intent verification, and the Accessibility Planner workflow.