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-auditgit 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-audit)<a href="https://agentmods.dev/skills/martinstofko219/agentic-design-toolkit/prototype-audit"><img src="https://agentmods.dev/badge/skills/martinstofko219/agentic-design-toolkit/prototype-audit/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-audit"><img src="https://agentmods.dev/badge/skills/martinstofko219/agentic-design-toolkit/prototype-audit.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 | $0.00180 | $0.02060 |
| Opus 5.5 | $0.00072 | $0.00824 |
| Sonnet 5.5 | $0.00036 | $0.00412 |
| Haiku 4.5 | $0.00018 | $0.00206 |
Grade A, and why
prototype-audit 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 — 99 lines — stays where its author put it; the contents beside it link to each section on GitHub.
prototype-audit
Research tells you what's true about users; a prototype is a bet about how to respond to that truth. This skill checks whether the bet is a good one — reading a research-synthesis doc and a prototype side by side, then writing a prioritized plan that closes whatever gap exists between them. It's a judgment task, not a checklist: the goal is an honest, well-evidenced answer to "does this actually address what we heard," not a mechanical diff.
Inputs
Two things must already exist: a research synthesis (themes, insights, quotes — typically research-synthesis output, though any findings doc will do) and a prototype meant to respond to it. The prototype can be:
- a React/Vite app (
prototype-designoutput) or an Angular build (spec-designoutput) in the workspace - a single-file HTML prototype (
prototype-designoutput) or wireframe (wireframe-designoutput) - Figma frames, provided as a Figma link
If either input doesn't exist yet, point the user at the right skill instead of auditing something that isn't there.
Ask for the synthesis doc's path and the prototype's location or Figma link if they're not obvious — there's no fixed convention for where either lives. If the workspace has more than one candidate for either, confirm rather than assume; an audit built on the wrong prototype version or a stale synthesis doc wastes everyone's time.
Read everything before comparing anything
Read the full synthesis doc first — not just the Insights → Opportunities table; the quotes and "why it matters" notes carry nuance a table row strips out. Then read the prototype in full: every screen, every component, the actual copy, the flows a user can walk through. How depends on what it is:
- React/Vite or Angular codebase — walk the routes or screen components, note what data and copy each screen actually shows, and pay attention to states: is there an empty state, an error state, or does the happy path stand alone?
- HTML — read the screen markup and any data objects directly. A hi-fi prototype carries real copy and data, so content claims are fair game; a wireframe also carries annotations worth reading, and if it was built in placeholder mode (bars instead of real copy) that limits what you can honestly claim about content later.
- Figma frames — use the Figma MCP to pull both the design context (layout structure, component usage, actual text content, and any variants, states, or annotation notes) and a screenshot of each frame, and read them together — the structured context tells you what exists and what things are named, the screenshot confirms what a user actually sees. Walk every frame in the flow, not just the one linked. If the Figma MCP is unavailable, ask for exported screenshots of every frame instead.
What ships with it
1 file 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 · 99 lines · 180 tokens per session scan A e515229e49dc
prototype-audit is a skill published in the GitHub repository martinstofko219/agentic-design-toolkit (1 stars, last pushed 2mo ago), licensed MIT. It adds 180 tokens to every session and 2,060 once invoked, about $0.0007 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.