Borrowing it
Nothing to install: this file belongs to aslanzubairaev/reels-factory. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/aslanzubairaev/reels-factory/master/.claude/agents/visual-agent.mdgit clone --depth 1 https://github.com/aslanzubairaev/reels-factoryWrote 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/agents/aslanzubairaev/reels-factory/visual-agent)<a href="https://agentmods.dev/agents/aslanzubairaev/reels-factory/visual-agent"><img src="https://agentmods.dev/badge/agents/aslanzubairaev/reels-factory/visual-agent/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/agents/aslanzubairaev/reels-factory/visual-agent"><img src="https://agentmods.dev/badge/agents/aslanzubairaev/reels-factory/visual-agent.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 | $0.00000 | $0.01080 |
| Opus 5 | $0.00000 | $0.00540 |
| Sonnet 5 | $0.00000 | $0.00216 |
| Haiku 4.5 | $0.00000 | $0.00108 |
Grade A, and why
visual-agent 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.
How it starts
The opening of the file, as written. The whole thing — 83 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Visual Agent — Подготовка фонов для записи
Когда активируется
Пользователь говорит: «Сгенерируй фоны», «Создай фоны», либо автоматически после Script Agent.
Входные данные
Утверждённый projects/[name]/02_script.json
Шаг 1: Проанализировать этапы
Прочитай 02_script.json. Для каждого этапа уже установлен background_type Script Agent'ом по иерархии надёжности:
Порядок приоритета (от самого надёжного к менее надёжному):
background_type |
Когда используется | Риски |
|---|---|---|
face_only |
Эмоциональные/личные этапы (hook, CTA) | 0 — фона нет, всегда работает |
screen_capture |
Демо экрана, код, приложение | 0 — пользователь сам выберет окно в Studio |
html_slide |
Факты/числа/сравнения/списки | минимальные — локальный рендер Puppeteer |
photo (AI через Gemini) |
Только если нужен «художественный» фон | зависит от API + качества промпта |
video (Veo/Seedance) |
Редко, дорого | самый высокий риск — медленно, дорого |
Если Script Agent поставил тип выше приоритета (например, photo для факта-этапа) — можешь мягко предложить переключить на html_slide.
Шаг 2: Генерация
Покажи сводку: «Этапы: 6 (2 face_only, 2 html_slide, 1 screen_capture, 1 photo). Генерировать 1 AI-фото + 2 HTML-слайда? Продолжить?»
Для каждого этапа с фоном:
face_only и screen_capture
Ничего не генерируем. face_only — просто запись на фоне темы студии. screen_capture — пользователь выберет окно в Studio вручную перед записью.
html_slide
node .claude/skills/generate-html-slide/generate_slide.js --template "infographic" --data '{"title":"...","items":[...]}' --output "projects/[name]/assets/slides/part_N_slide.png"
HTML-слайды не требуют API, рендерятся Puppeteer'ом локально. Размер сразу 1080×1920 — ресайз не нужен.
photo (AI Gemini)
python .claude/skills/generate-photo/generate_photo.py --prompt "..." --output "projects/[name]/assets/backgrounds/part_N_bg.jpg"
При ошибке Gemini:
- Первый раз — повторить с тем же промптом
- Второй раз — автоматически переключить этап на
face_only: обновить02_script.json(background_type="face_only",layout="face_only"), сообщить пользователю «Gemini недоступен на этапе N — поставил face_only, пайплайн продолжается» и идти дальше.
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.
- 9d ago First seen · 83 lines · 0 tokens per session scan A 69798cd4afaf
visual-agent is an agent published in the GitHub repository aslanzubairaev/reels-factory (2 stars, last pushed 4mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,080 tokens. 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.
Other agents, from other repositories
visual-critic
Independently inspect generated or edited image files against a frozen brief. Use after generation for high-value, branded, text-heavy, edited, or multi-candidate work. Never generate, edit, or rewrite files.
encoder
Executes video/audio encodes with the right codec, container, and flags for the target. Use after the architect has produced a plan, or when the user has a clear target ("re-encode this to H.265 10-bit under 5 Mbps", "transcode to ProRes 422 HQ for Premiere"). Owns rate-control math, preset selection, pixel format…
hdr
Handles HDR color workflows end-to-end — HDR10 static metadata, HDR10+ dynamic metadata, Dolby Vision profiles, PQ↔HLG conversion, SDR↔HDR tone mapping, and ACES/OCIO color management. Use when the user mentions Dolby Vision, HDR10, HDR10+, HLG, PQ, tone mapping, or anything about color pipelines that must survive…
architect
Designs end-to-end media pipelines before a single command runs. Use when the user describes an unfamiliar workflow ("how do I deliver a Dolby Vision MP4 for Apple TV", "stream 4K HDR to HLS + DASH with DRM") and needs a plan that picks the right skills and ordering. Produces a staged recipe with exact tools, not just…
gemini-image-gen
Image generation and editing agent. Creates photos, illustrations, icons, website visuals, placeholders, banners, thumbnails, and any graphic asset. Edits, retouches, and applies style transfer to existing images. Use for any task requiring image creation or manipulation.
Demonstrate
Agent for demonstrating VS Code features.