nova-prototype

nova-prototype is a command for Claude Code from novasamatech/nova-spektr. It costs 66 tokens per session (8,720 once invoked), scanned A, original, Apache-2.0.

A command that creates interactive Storybook screens from existing project components and fixed sample data.

In plain words
What is it for?
Use it to prototype pages, dialogs, feature demos, and presentation views in a React and TypeScript project.
Why use it?
It lets teams demonstrate or review a screen without implementing its real data connections or business rules.

Command for Claude Code

Install

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.

agentmods
npx agentmods add commands/novasamatech/nova-spektr/nova-prototype
Clone the repo
git clone --depth 1 https://github.com/novasamatech/nova-spektr

Made for: Claude Code.

Wrote 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.

agentmods badge for nova-prototype

README.md
[![agentmods](https://agentmods.dev/badge/commands/novasamatech/nova-spektr/nova-prototype.svg)](https://agentmods.dev/commands/novasamatech/nova-spektr/nova-prototype)
Your own site
<a href="https://agentmods.dev/commands/novasamatech/nova-spektr/nova-prototype"><img src="https://agentmods.dev/badge/commands/novasamatech/nova-spektr/nova-prototype.svg" alt="Measured on agentmods" height="20"></a>
Per session 66 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 8,720 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00066 $0.08720
Opus 5 $0.00033 $0.04360
Sonnet 5 $0.00013 $0.01744
Haiku 4.5 $0.00007 $0.00872

Measured 3d ago against content hash f9f521e12df6, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

nova-prototype 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 3d 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.

.claude/commands/nova-prototype.md · 810 lines

How it starts

The opening of the file, as written. The whole thing — 810 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Nova Spektr Prototype Generator

Generate a .stories.tsx file in src/renderer/stories/prototypes/ that renders a fully interactive UI prototype using real project components with static mock data.

STEP 1: Understand the request

Ask clarifying questions if needed:

  • What feature/screen to prototype?
  • Full page or modal/dialog?
  • What data should be displayed?
  • Any specific interactions (tabs, filters, modals, accordions)?

STEP 2: Study real app patterns

Before building, read source code in src/renderer/pages/, src/renderer/features/, src/renderer/widgets/ that is closest to the requested prototype. Match the real app's:

  • Layout structure (header, content area, sidebar)
  • Spacing and information density
  • Typography hierarchy
  • Component usage patterns

STEP 3: Generate the prototype

Create src/renderer/stories/prototypes/<feature-name>.stories.tsx

STEP 4: Verify against real app

After generating the prototype, compare the output with the actual app components to check visual fidelity. Run through this checklist:

  1. Read the real components — Open the corresponding features/*/ui/ and pages/*/ source files. Focus on the JSX structure, className strings, spacing values, and component hierarchy.
  2. Compare layout patterns — Check:
    • Container backgrounds, padding, border-radius (bg-block-background-default, p-4, rounded-sm)
    • Spacing between elements (gap-x-2, gap-y-4, gap-y-2, gap-y-1.5)
    • Typography components and their text color classes (BodyText vs FootnoteText vs HelpText)
    • Icon sizes, colors, and placement (real app often uses size={14} inline icons, NOT large circle backgrounds)
    • Button variants (variant="fill" pallet="secondary" size="sm" for action buttons, not variant="text")
  3. Check domain components — Verify that the real app uses:
    • WalletIcon with badge overlays (not custom circle icons) for wallet/proxy notifications
    • Small inline Icon components (14px) for status indicators in operation notifications
    • BodyText for titles (not FootnoteText) and BodyText className="text-text-secondary" for descriptions
    • FootnoteText className="text-text-tertiary" for timestamps only
  4. Fix discrepancies — Update the prototype to match. Common mismatches:
    • Using custom colored circle icons instead of real app's inline icons or WalletIcon
    • Wrong typography component hierarchy (e.g., FootnoteText where BodyText should be)
    • Wrong button variant (text link vs filled secondary)
    • Missing inline-flex flex-wrap items-center on description rows
    • Wrong gap/padding values

Read the full file on GitHub · 810 lines

Changes

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.

  1. 3d ago First seen · 810 lines · 66 tokens per session scan A f9f521e12df6

Subscribe to this mod's changes

nova-prototype is a command published in the GitHub repository novasamatech/nova-spektr (56 stars, last pushed today), licensed Apache-2.0. It adds 66 tokens to every session and 8,720 once invoked, about $0.0003 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 2026-09-01.