Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/bestdeejay-design/agent-skillsnpx agentmods add skills/bestdeejay-design/agent-skills/test-graphicsWrote 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/bestdeejay-design/agent-skills/test-graphics)<a href="https://agentmods.dev/skills/bestdeejay-design/agent-skills/test-graphics"><img src="https://agentmods.dev/badge/skills/bestdeejay-design/agent-skills/test-graphics/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/bestdeejay-design/agent-skills/test-graphics"><img src="https://agentmods.dev/badge/skills/bestdeejay-design/agent-skills/test-graphics.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 | $0.00126 | $0.02571 |
| Opus 5 | $0.00063 | $0.01286 |
| Sonnet 5 | $0.00025 | $0.00514 |
| Haiku 4.5 | $0.00013 | $0.00257 |
Grade A, and why
test-graphics 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 7d 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 — 240 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Test Graphics — Генератор тестовых изображений
Загружай этот скилл когда нужно быстро получить тестовые картинки, иконки, фото-заглушки.
Инструмент
scripts/test-graphics.py — Python-скрипт в папке скилла (относительный путь от корня скилла).
Запуск: python3 scripts/test-graphics.py ....
Зависимости: Python 3, Pillow, requests (есть на системе).
Команды
Фото (настоящие, random)
scripts/test-graphics.py photo [width] [height] [output]
Источник: picsum.dev (1-й приоритет), loremflickr.com (fallback), placehold.co (цветной блок), Pillow-генерация (полный fallback).
Примеры:
# Случайное фото 800x600
scripts/test-graphics.py photo
# 200x150
scripts/test-graphics.py photo 200 150
# В конкретный файл
scripts/test-graphics.py photo 1920 1080 ./assets/hero.jpg
Placeholder (цветной блок с текстом)
scripts/test-graphics.py placeholder <width> <height> [color] [text] [output]
Примеры:
# Базовый 800x600 со случайным цветом
scripts/test-graphics.py placeholder
# 200×150 красный
scripts/test-graphics.py placeholder 200 150 "#FF0000" "My Image"
# Синий с текстом
scripts/test-graphics.py placeholder 300 200 "#3498DB" "Hello"
Цвета: #RRGGBB. Если текст содержит пробелы — в кавычки.
Иконка (SVG, встроенные 35 штук)
scripts/test-graphics.py icon <name> [color] [size] [output]
Список всех иконок:
scripts/test-graphics.py list-icons
Примеры:
# Красная звезда 64×64
scripts/test-graphics.py icon star "#E74C3C"
# Синий дом 48×48
scripts/test-graphics.py icon home "#3498DB" 48
# В папку
scripts/test-graphics.py icon user "#2ECC71" 96 ./icons/user.svg
Доступные имена: star, circle, square, triangle, heart, home, user, mail, settings, search, arrow-{right,left,up,down}, check, cross, plus, minus, info, warning, download, upload, folder, file, image, calendar, clock, location, tag, cart, eye, lock, phone, chart, gift.
Аватар (ui-avatars.com)
Генерирует иконку-аватар по имени с настраиваемым фоном/цветом.
What ships with it
3 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.
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.
- 7d ago First seen · 240 lines · 126 tokens per session scan A 6ea87dd314d4
test-graphics is a skill published in the GitHub repository bestdeejay-design/agent-skills (5 stars, last pushed 3d ago), licensed MIT. It adds 126 tokens to every session and 2,571 once invoked, about $0.0006 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 2026-09-03.
Other skills, from other repositories
armada-verification
Mandatory pre-completion verification and evidence checklist before reporting done.
e2e-testing
Prioritize end-to-end test coverage for critical user journeys using BAS workflows. Do not break functionality or regress existing tests; all changes must maintain or improve completeness.
playwright-cli
Automate browser interactions, test web pages and work with Playwright tests.
browser-use
Direct browser control via CDP for web interaction: automation, scraping, testing, screenshots, and site/app work.
android-ui-journey-testing
XML-specified Android UI journey testing, interactive step execution, assertion verification, and JSON outcome reporting.
dogfood
Systematically explore and test a mobile app on iOS/Android with agent-device to find bugs, UX issues, and other problems. Use when asked to dogfood, QA, exploratory test, find issues, bug hunt, or test this app on mobile.