scalex: Skill for Claude Code

.agents/skills/capture-banners/SKILL.md

capture-banners is a skill for Claude Code, Codex from nguyenyou/scalex. It costs 99 tokens per session (582 once invoked), scanned A, original, MIT.

A workflow for turning Scalex banner HTML files into PNG images. PNG files are image files, while HTML describes web-page content and layout.

In plain words
What is it for?
It is for re-rendering four README and social-preview banners after changing their text, colours, or layout.
Why use it?
It keeps the image versions of banners up to date after their HTML source is changed, with the intended 1200-by-630-pixel size.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: installed under .agents/ (shared by several agents).

This is nguyenyou/scalex's own configuration. It tells Claude Code and Codex how to work on scalex itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything scalex configures →

Reuse

Borrowing it

Nothing to install: this file belongs to nguyenyou/scalex. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/nguyenyou/scalex/main/.agents/skills/capture-banners/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/nguyenyou/scalex

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 capture-banners

README.md
[![agentmods](https://agentmods.dev/badge/skills/nguyenyou/scalex/capture-banners.svg)](https://agentmods.dev/skills/nguyenyou/scalex/capture-banners)
Your own site
<a href="https://agentmods.dev/skills/nguyenyou/scalex/capture-banners"><img src="https://agentmods.dev/badge/skills/nguyenyou/scalex/capture-banners.svg" alt="Measured on agentmods" height="20"></a>
Per session 99 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 582 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 $0.00099 $0.00582
Opus 5 $0.00049 $0.00291
Sonnet 5 $0.00020 $0.00116
Haiku 4.5 $0.00010 $0.00058

Measured 8d ago against content hash 807fc29cd576, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

capture-banners 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 8d 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.

.agents/skills/capture-banners/SKILL.md · 52 lines

What it actually says

Capture Banners

The Scalex project has 4 banner images that are rendered from HTML source files. When the HTML is edited, the PNGs must be re-captured to stay in sync.

HTML source PNG output Purpose
site/readme-banner-dark.html site/readme-banner-dark.png GitHub README banner (dark mode)
site/readme-banner-light.html site/readme-banner-light.png GitHub README banner (light mode)
site/og-banner.html site/og-banner.png OpenGraph social preview (dark)
site/og-banner-light.html site/og-banner-light.png OpenGraph social preview (light)

Required viewport size

All banners are designed at 1200 x 630 pixels. The HTML <body> is hardcoded to this size. The Chrome DevTools viewport must match exactly, otherwise the screenshot will crop or include extra whitespace.

Capture procedure

Use Chrome DevTools MCP tools. For each banner:

  1. Open or navigate to the HTML file using a file:// URL:

    file:///absolute/path/to/scalex/site/readme-banner-dark.html
    
  2. Resize the viewport to 1200x630:

    mcp__chrome-devtools__resize_page(width=1200, height=630)
    
  3. Take a screenshot and save directly to the PNG path:

    mcp__chrome-devtools__take_screenshot(
      filePath="site/readme-banner-dark.png",
      format="png"
    )
    
  4. Repeat for the remaining 3 banners. You can reuse the same tab by navigating to the next HTML file.

Notes

  • The Kestrel mascot image (Kestrel.png) is referenced by relative path in the HTML, so the file:// URL must point to the site/ directory for it to render.
  • After capturing, the PNGs are ready to commit — no post-processing needed.
  • If the images look wrong (missing mascot, broken layout), check that the HTML references are correct relative to the site/ directory.
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. 8d ago First seen · 52 lines · 99 tokens per session scan A 807fc29cd576

Subscribe to this mod's changes

capture-banners is a skill published in the GitHub repository nguyenyou/scalex (95 stars, last pushed 2mo ago), licensed MIT. It adds 99 tokens to every session and 582 once invoked, about $0.0005 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 2026-08-30.

Related

Other skills, from other repositories

elevenlabs

Generate AI voiceovers, sound effects, and music using ElevenLabs APIs. Use when creating audio content for videos, podcasts, or games. Triggers include generating voiceovers, narration, dialogue, sound effects from descriptions, background music, soundtrack generation, voice cloning, or any audio synthesis task.

digitalsamba/claude-code-video-toolkit · 63 tokens

ffmpeg

Video and audio processing with FFmpeg. Use for format conversion, resizing, compression, audio extraction, and preparing assets for Remotion. Triggers include converting GIF to MP4, resizing video, extracting audio, compressing files, or any media transformation task.

digitalsamba/claude-code-video-toolkit · 55 tokens

playwright-recording

Record browser interactions as video using Playwright. Use for capturing demo videos, app walkthroughs, and UI flows for Remotion videos. Triggers include recording a demo, capturing browser video, screen recording a website, or creating walkthrough footage.

digitalsamba/claude-code-video-toolkit · 53 tokens

ideogram4

Prompting patterns for Ideogram 4 text-to-image — best-in-class in-image text rendering and exact color/layout control via structured JSON captions. Use when generating images that need legible on-image text (title cards, thumbnails, logos, signage, CTAs), precise brand colors, or controlled spatial layout. Triggers…

digitalsamba/claude-code-video-toolkit · 99 tokens

projectatlas

Use ProjectAtlas as the atlas-first orientation layer before broad source reads, with MCP-first task startup, short-alias worktree registration and routing, safe targeted initialization, ranked navigation, exact or federated graph evidence, purpose curation, health, lint, and repository-wide token reporting.

styler-ai/ProjectAtlas · 60 tokens

memstack-content-youtube-script

Use this skill when the user says 'YouTube script', 'video script', 'write script for YouTube', 'YouTube video outline', or is creating scripted content for a YouTube video with hooks, chapters, and CTAs. Do NOT use for TikTok/Reels short-form scripts or webinar presentations.

cwinvestments/memstack · 70 tokens