extract-screens

extract-screens is a command for Claude Code from noizu-labs-ml/NoizuPromptLingo. It costs 38 tokens per session (924 once invoked), scanned A, original, MIT.

A command that reads user stories—written descriptions of what users need—and lists the application screens and reusable interface components they require.

In plain words
What is it for?
Use it to create screen records and a component library from files in project-management/user-stories/.
Why use it?
It turns scattered product requirements into concrete UI inventories, while stopping when the required user-story files are missing.

Command for Claude Code

Written for Claude Code: a Claude Code command (commands/*.md).

Good fit Use it to create screen records and a component library from files in project-management/user-stories/.

Compare 6 commands from other repositories ↓
Install with agentmods
npx agentmods add commands/noizu-labs-ml/noizupromptlingo/extract-screens
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.

Clone the repo
git clone --depth 1 https://github.com/noizu-labs-ml/NoizuPromptLingo

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 extract-screens

README.md
[![agentmods](https://agentmods.dev/badge/commands/noizu-labs-ml/noizupromptlingo/extract-screens/github.svg)](https://agentmods.dev/commands/noizu-labs-ml/noizupromptlingo/extract-screens)
Your own site
<a href="https://agentmods.dev/commands/noizu-labs-ml/noizupromptlingo/extract-screens"><img src="https://agentmods.dev/badge/commands/noizu-labs-ml/noizupromptlingo/extract-screens/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 extract-screens

Your own site · 80×15
<a href="https://agentmods.dev/commands/noizu-labs-ml/noizupromptlingo/extract-screens"><img src="https://agentmods.dev/badge/commands/noizu-labs-ml/noizupromptlingo/extract-screens.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 38 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 924 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 $0.00038 $0.00924
Opus 5 $0.00019 $0.00462
Sonnet 5 $0.00008 $0.00185
Haiku 4.5 $0.00004 $0.00092

Measured 6d ago against content hash 60ad810f1e00, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

extract-screens 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 6d 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.

commands/extract-screens.md · 132 lines

How it starts

The opening of the file, as written. The whole thing — 132 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Extract Screens & Components from User Stories

You are running inside a project directory that contains user stories under project-management/user-stories/. Your job is to analyze ALL user stories and produce two deliverables:

  1. Screen inventoryproject-management/screens/
  2. Component libraryproject-management/components/

Prerequisites — Verify Before Starting

  • Confirm project-management/user-stories/ exists and contains US-*.md files
  • Optionally read project-management/personas/ for additional context
  • If user stories don't exist, STOP and tell the user

Phase 1: Screen Extraction

Read ALL user story files. For each distinct screen/view the application needs, create a numbered markdown file:

Output path: project-management/screens/{NN}-{screen-slug}.md

Per-screen document:

# {Screen Name}

| Field | Value |
|-------|-------|
| **ID** | `{screen-slug}` |
| **Type** | {Primary|Dashboard|Settings|Modal|Storyboard} |
| **Category** | {Category Name} |
| **User Stories** | {US-001, US-002, ...} |

## Description

{What this screen does and why it exists}

## Key Components

- **{Component name}** — {What it does on this screen} ({US-XXX reference})

## Interactions

- {User interaction description}

## Navigation

- Accessible from: {Where users arrive from}
- Links to: {Where users can go from here}

Screen types:

  • primary — Full-page views in main navigation
  • dashboard — Aggregation/metrics views with charts and cards
  • settings — Configuration panels
  • modal — Overlays/dialogs triggered from other screens
  • storyboard — Multi-step flows/wizards

Include a README.md with category table, type legend, total count, and confirmation all user stories are mapped.

Phase 2: Component Extraction

After screens are written, analyze them to extract reusable UI components.

Output path: project-management/components/{NN}-{component-slug}.md

Per-component document:

# {Component Name}

| Field | Value |
|-------|-------|
| **ID** | `{component-slug}` |
| **Category** | {Category Name} |
| **Used In** | {NN-Screen Name, NN-Screen Name, ...} |

## Description

{What this component does}

## Size Variants

| Variant | Description |
|---------|-------------|
| **Inline** | {Chip/badge/single-line presentation} |
| **Compact** | {Card/summary presentation} |
| **Expanded** | {Panel/detail presentation} |
| **Full Page** | {Standalone page view} |

(Omit rows where a variant doesn't apply)

## Props / Configuration

- `{propName}` — {description}

## Interactions

- {Interaction description}

Read the full file on GitHub · 132 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. 6d ago First seen · 132 lines · 38 tokens per session scan A 60ad810f1e00

Subscribe to this mod's changes

extract-screens is a command published in the GitHub repository noizu-labs-ml/NoizuPromptLingo (13 stars, last pushed 2d ago), licensed MIT. It adds 38 tokens to every session and 924 once invoked, about $0.0002 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 2026-09-04.