createya-batch

A workflow for generating several Createya images or videos as a batch. It manages the jobs in a queue, respects the plan's concurrency limit, checks for completed results, and saves them in a project folder.

In plain words
What is it for?
For making image or video variations, lookbooks, character sheets, and other creative series with more than one output.
Why use it?
It prevents too many simultaneous generation requests and keeps a large set of results organized instead of handling each one manually.

Skill for Claude CodeCodex

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.

agentmods
npx agentmods add skills/createya-ai/createya-mcp/createya-batch
Any agent
npx skills add Createya-ai/Createya-mcp --skill createya-batch
Clone the repo
git clone --depth 1 https://github.com/Createya-ai/Createya-mcp

Made for: Claude Code, Codex.

Per session 125 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,582 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. Scan, not verified.
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 $0.00125 $0.02582
Opus 5 $0.00063 $0.01291
Sonnet 5 $0.00025 $0.00516
Haiku 4.5 $0.00013 $0.00258

Measured 3d ago against content hash 32979d51213e, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

createya-batch scanned grade A with 1 finding 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 3d 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

curl -fsSL "$OUTPUT_URL" -o "creative/output/$TASK/${NN}-${VARIANT_SLUG}.${EXT}"
plugins/createya-mcp/skills/createya-batch/SKILL.md · 233 lines

How it starts

The opening of the file, as written. The whole thing — 233 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Createya Batch — пачечная генерация с очередью и workspace

Этот skill — рабочая обёртка над createya:* MCP-тулзами для случая «нужно сгенерировать несколько результатов». Делает три вещи которые агент сам по себе делать криво:

  1. Уважает concurrency-лимит тарифа — не льёт N одновременно, получая 429.
  2. Очередь + polling — fire limit, ждёт complete, fire next.
  3. Раскладывает результаты в проектный workspacecreative/output/<task>/ с manifest.

Требует установленного createya skill (low-level MCP wrapper). Если его нет — выполни одной командой из README этого репо.

Когда триггериться

  • «Сгенерируй 5 креативов», «пачкой», «5 вариаций», «сделай серию»
  • «lookbook», «character sheet», «multi-aspect ad»
  • После того как creative-director подготовил бриф и эталон, время делать вариации
  • Любой запрос с числом > 1 в количестве результатов

Workspace convention

Перед первой генерацией создай structure (если не существует):

creative/
├── refs/                          # пользовательские референсы / source images
├── etalon/                        # locked "perfect" frames для consistency
└── output/
    └── YYYY-MM-DD-<task-slug>/    # один таск = одна папка
        ├── manifest.json          # что сгенерировано: prompt, model, credits, run_id, file
        ├── 01-<variant-slug>.png  # пронумерованные результаты
        ├── 02-<variant-slug>.png
        └── ...

<task-slug> — короткий kebab-case, выводи из брифа: cat-on-moon, summer-lookbook, product-hero-shots. <variant-slug> — описание конкретной вариации: cinematic-portrait, pastel-wide, front-angle.

Если у пользователя в проекте уже есть creative/ — продолжай в той же структуре. Если нет — создай папки через Bash mkdir -p creative/{refs,etalon,output}.

Полный workflow

1. Получи concurrency-лимит и баланс

createya:get_balance() → {
  credits_balance: 16399,
  concurrency: { limit: 4, in_use: 0 }   ← ЭТО ВАЖНО
}

concurrency.limit — сколько runs одновременно можно держать. Это лимит тарифа (Start=1, Creator=2, Pro=3, Enterprise=4). Не обходи его — получишь 429 concurrent_limit_exceeded.

Read the full file on GitHub · 233 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. 3d ago First seen · 233 lines · 125 tokens per session scan A 32979d51213e

Subscribe to this mod's changes

createya-batch is a skill published in the GitHub repository Createya-ai/Createya-mcp (4 stars, last pushed 3mo ago), licensed MIT. It adds 125 tokens to every session and 2,582 once invoked, about $0.0006 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). 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

wavespeed

Generate or edit AI media (image, video, audio, 3D) by calling the wavespeed CLI on the user's machine. Use whenever the user asks to create, edit, animate, upscale, or transform a visual asset, generate audio/TTS/music, or produce marketing creatives. Every model on the WaveSpeed platform is one wavespeed run call.

WaveSpeedAI/wavespeed-cli · 79 tokens

1688-ecommerce-image-generation-editing

帮助电商运营、商品摄影、品牌商品团队和直播带货团队直接完成“1688 电商图片生成与编辑”:既可从文字生成,也可加入参考图帮助控制主体、构图和视觉风格;通过 AI Hive 使用时,生成前自动上传参考图,提交后自动保存任务、查询进度并下载图片。适用于电商主图、商品详情页、广告 KV、海报、带货、种草、社媒配图、产品精修、换背景与角色一致性内容。 Use this skill for 1688 电商图片生成与编辑, text-to-image, reference-guided image generation, and commercial image creation, product photography…

wubin1836/ai-hive-agent-skills · 457 tokens

1688-ecommerce-video-generation-editing

帮助电商运营、品牌商品团队、直播带货团队与商业内容创作者直接完成“1688 电商视频生成与编辑”:既可只输入文字从零生成,也可加入图片、视频或音频控制结果;通过 AI Hive 使用时,生成前自动上传所需素材,提交后自动保存任务、查询进度并下载成片。适用于 AI 广告、TVC、电商视频、产品展示、带货、种草、短剧、漫剧和社媒内容。 Use this skill for 1688 电商视频生成与编辑, text-to-video, image-to-video, first-and-last-frame animation, reference-to-video, video-to-video, audio-to-video, AI…

wubin1836/ai-hive-agent-skills · 463 tokens

ai-model-expert-1688-ecommerce-image-generation-editing

AI大模型专家|1688 电商图片生成与编辑。帮助电商运营、商品摄影、品牌商品团队和直播带货团队直接完成“1688 电商图片生成与编辑”:既可从文字生成,也可加入参考图帮助控制主体、构图和视觉风格;通过 AI Hive 使用时,生成前自动上传参考图,提交后自动保存任务、查询进度并下载图片。适用于电商主图、商品详情页、广告 KV、海报、带货、种草、社媒配图、产品精修、换背景与角色一致性内容。 Use this skill for 1688 电商图片生成与编辑, text-to-image, reference-guided image generation, and commercial image creation…

wubin1836/ai-hive-agent-skills · 326 tokens

ai-model-expert-1688-ecommerce-video-generation-editing

AI大模型专家|1688 电商视频生成与编辑。帮助电商运营、品牌商品团队、直播带货团队与商业内容创作者直接完成“1688 电商视频生成与编辑”:既可只输入文字从零生成,也可加入图片、视频或音频控制结果;通过 AI Hive 使用时,生成前自动上传所需素材,提交后自动保存任务、查询进度并下载成片。适用于 AI 广告、TVC、电商视频、产品展示、带货、种草、短剧、漫剧和社媒内容。 Use this skill for 1688 电商视频生成与编辑, text-to-video, image-to-video, first-and-last-frame animation, reference-to-video…

wubin1836/ai-hive-agent-skills · 330 tokens

ai-model-expert-ai-ad-video

AI大模型专家|AI 广告视频。帮助品牌市场、广告代理、创意策划、制片人与投放团队直接完成“AI 广告视频”:既可只输入文字从零生成,也可加入图片、视频或音频控制结果;通过 AI Hive 使用时,生成前自动上传所需素材,提交后自动保存任务、查询进度并下载成片。适用于 AI 广告、TVC、电商视频、产品展示、带货、种草、短剧、漫剧和社媒内容。 Use this skill for AI 广告视频, text-to-video, image-to-video, first-and-last-frame animation, reference-to-video, video-to-video, audio-to-video…

wubin1836/ai-hive-agent-skills · 352 tokens