preview-generator

preview-generator is a skill for Claude Code, Codex from srinidhis05/agentura. It costs 2 tokens per session (721 once invoked), scanned A, original, Apache-2.0.

A generator for a self-contained HTML preview that shows a proposed mobile feature inside a phone frame. It uses screen descriptions and app-building details to create a visual mockup without requiring the Android app to be built.

In plain words
What is it for?
Use it to preview an incubated mobile feature, map app screens into an HTML mockup, and give product managers a visual version of the planned Android experience.
Why use it?
It lets product managers inspect the intended screens and navigation before implementation is complete. The preview can show the feature using the supplied sample screen and backend information.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: model in frontmatter; positional $N argument.

Good fit Use it to preview an incubated mobile feature, map app screens into an HTML mockup, and give product managers a visual version of the planned Android experience.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/srinidhis05/agentura/preview-generator
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.

Any agent
npx skills add srinidhis05/agentura --skill preview-generator
Clone the repo
git clone --depth 1 https://github.com/srinidhis05/agentura

Made for: Claude Code, Codex.

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 preview-generator

README.md
[![agentmods](https://agentmods.dev/badge/skills/srinidhis05/agentura/preview-generator/github.svg)](https://agentmods.dev/skills/srinidhis05/agentura/preview-generator)
Your own site
<a href="https://agentmods.dev/skills/srinidhis05/agentura/preview-generator"><img src="https://agentmods.dev/badge/skills/srinidhis05/agentura/preview-generator/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.

agentmods 80×15 button for preview-generator

Your own site · 80×15
<a href="https://agentmods.dev/skills/srinidhis05/agentura/preview-generator"><img src="https://agentmods.dev/badge/skills/srinidhis05/agentura/preview-generator.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 2 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 721 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00002 $0.00721
Opus 5 $0.00001 $0.00360
Sonnet 5 $0.00000 $0.00144
Haiku 4.5 $0.00000 $0.00072

Measured 9d ago against content hash 67c94f1f6d54, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

preview-generator 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 9d 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.

skills/incubator/preview-generator/SKILL.md · 99 lines

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.

Preview Generator Agent

Task

You generate a self-contained HTML file that renders a phone-frame mockup of the incubated feature. This gives PMs a visual preview without needing to build the Android app. The mockup uses the spec's screen definitions and the mobile-builder's actual Compose screen descriptions to produce a realistic-looking preview.

Input Format

{
  "feature_name": "expense-tracker",
  "pit_name_hyphenated": "expense-tracker",
  "mobile_spec": {
    "feature_package": "expense_tracker",
    "screens": [
      {
        "name": "ExpenseListScreen",
        "description": "List of expenses with total, filter by category/date"
      },
      {
        "name": "AddExpenseScreen",
        "description": "Form to add a new expense with amount, category, description"
      }
    ],
    "navigation": {
      "start_destination": "expense_list",
      "routes": [...]
    }
  },
  "backend_spec": {
    "base_path": "/api/v1/expense-tracker",
    "endpoints": [...]
  }
}

Execution Protocol

Phase 1: Plan the Mockup

Map each screen from mobile_spec.screens to an HTML panel:

  • Use screen description to determine layout and content
  • Generate realistic sample data for lists, forms, charts
  • Plan navigation between panels (tab/swipe simulation)

Gate: All screens mapped to mockup panels.

Phase 2: Build the HTML Preview

Create a single self-contained preview.html file with:

  • Phone frame — centered div with phone dimensions (375x812), rounded corners, status bar
  • Screen panels — one per screen, switchable via tabs/buttons
  • Material Design styling — colors and typography matching Material 3
  • Incubation banner — yellow/amber banner at top of each screen saying "Incubating: <feature_name>"
  • Sample data — realistic mock data (not "Lorem ipsum")
  • Navigation — clickable tabs or buttons to switch between screens

Requirements:

  • Self-contained — all CSS/JS inline, no external dependencies
  • Responsive — works in any browser
  • Print-friendly — PM can screenshot for stakeholder presentations

Read the full file on GitHub · 99 lines

Files

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.

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. 9d ago First seen · 99 lines · 2 tokens per session scan A 67c94f1f6d54

Subscribe to this mod's changes

preview-generator is a skill published in the GitHub repository srinidhis05/agentura (9 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 2 tokens to every session and 721 once invoked, about $0.0000 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 2026-08-31.

Related

Other skills, from other repositories

axiom-media

Use when working with camera, photos, audio, haptics, ShazamKit, the user's Apple Music library, or Now Playing. Covers AVCaptureSession, PHPicker, PhotosPicker, AVFoundation, Core Haptics, audio recognition, MediaPlayer, CarPlay, MusicKit playback and library enumeration.

CharlesWiltgen/Axiom · 67 tokens

app-preview-video

When the user wants to plan, script, produce, or optimize App Store Preview videos or Google Play promo videos — the autoplay videos that show in App Store/Play Store search and product pages. Use when the user mentions "App Preview", "preview video", "app store video", "promo video", "Play Store video", "video poster…

Eronred/aso-skills · 143 tokens

argent-screen-recording

Record a video of an iOS simulator or Android emulator/device screen using argent MCP tools. Use when the user asks to record the screen, capture a video of a flow, interaction, or animation, produce a screen recording, or document app behavior as a video clip.

software-mansion/argent · 59 tokens

phone-ui-demos

A tool for making cinematic web demonstrations that present information inside a realistic smartphone interface, such as notifications, chats, settings, or an app screen.

Unclecheng-li/AI_Animation · 194 tokens

generate-images-with-firebase-ai

Use when generating or editing images from Flutter/Dart with Firebase AI Logic and a Gemini image model (Nano Banana), making the first call work, choosing Gemini Developer API vs Vertex AI, hitting quota, billing or App Check failures, getting empty or image-only responses, sending a user photo as input, controlling…

evanca/flutter-ai-rules · 84 tokens

ios-marketing-capture

Use when the user wants to automate capture of marketing screenshots for a SwiftUI iOS app across multiple locales, devices, or appearances. Covers full-screen shots, isolated element renders (carousel cards, widgets), and reproducible output naming. Triggers on marketing screenshots, locale screenshots, widget…

ParthJadhav/ios-marketing-capture · 78 tokens