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 martinstofko219/agentic-design-toolkit --skill prototype-designgit clone --depth 1 https://github.com/martinstofko219/agentic-design-toolkitWrote 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/martinstofko219/agentic-design-toolkit/prototype-design)<a href="https://agentmods.dev/skills/martinstofko219/agentic-design-toolkit/prototype-design"><img src="https://agentmods.dev/badge/skills/martinstofko219/agentic-design-toolkit/prototype-design/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/martinstofko219/agentic-design-toolkit/prototype-design"><img src="https://agentmods.dev/badge/skills/martinstofko219/agentic-design-toolkit/prototype-design.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 | $0.00204 | $0.01852 |
| Opus 5.5 | $0.00082 | $0.00741 |
| Sonnet 5.5 | $0.00041 | $0.00370 |
| Haiku 4.5 | $0.00020 | $0.00185 |
Grade A, and why
prototype-design 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 1mo 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 — 71 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Your job is to turn a design idea into a realistic, interactive prototype that feels like a real product. Not production-ready code — but convincing enough to explore, test, and communicate the concept. It should look and behave like a real app.
Session mode: Once invoked, this skill stays active for the rest of the session — apply these guidelines to every subsequent request that builds on or iterates the prototype, without re-invocation. On first load, tell the designer the skill is active and remains so until they say "stop prototype-design" or "exit skill mode."
Discovery First
If the designer says outright they haven't worked the idea out yet, suggest running the design-grill skill before prototyping.
Before writing any code, have a natural conversation with the designer — not a checklist — to understand:
- the problem the interface is solving
- who uses it and in what context
- the industry or domain it lives in
- any workflow or flow the designer has in mind
- references or directions they're drawn to
- whether there's existing research (interviews, usability findings, a synthesis doc) this prototype is meant to answer to
- how much of it has to genuinely work — which interactions are load-bearing for the concept, how many rounds of revision it's likely to face, and where it'll be opened
Follow up where things are unclear and stop when you can make confident decisions — you're understanding the concept, not extracting a spec.
Discovery answers what the concept is; design-grill tests whether it should exist in this form. If the gaps still open once they've answered are decisions nobody has made — no evidence the problem is real, no defined user, unresolved edge cases the design turns on — suggest grilling now, naming the specific gap. Ordinary missing detail you can just ask about is not a grill trigger. Weight it by what's at stake: a build the team will live in for sprints, or one going in front of research participants, is expensive to get wrong; a quick exploration is not. Suggest once: this is a nudge, not a gate — if they'd rather build, build, and state the assumption you're proceeding on.
What ships with it
3 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.
- 1mo ago First seen · 71 lines · 204 tokens per session scan A 3cca984a1eac
prototype-design is a skill published in the GitHub repository martinstofko219/agentic-design-toolkit (1 stars, last pushed 2mo ago), licensed MIT. It adds 204 tokens to every session and 1,852 once invoked, about $0.0008 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.