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.
npx agentmods add skills/createya-ai/createya-mcp/character-sheetnpx skills add Createya-ai/Createya-mcp --skill character-sheetgit clone --depth 1 https://github.com/Createya-ai/Createya-mcpWrote 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/createya-ai/createya-mcp/character-sheet)<a href="https://agentmods.dev/skills/createya-ai/createya-mcp/character-sheet"><img src="https://agentmods.dev/badge/skills/createya-ai/createya-mcp/character-sheet.svg" alt="Measured on agentmods" 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 | $0.00140 | $0.02365 |
| Opus 5 | $0.00070 | $0.01182 |
| Sonnet 5 | $0.00028 | $0.00473 |
| Haiku 4.5 | $0.00014 | $0.00236 |
Grade A, and why
character-sheet 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 5d 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.
├── sheet.png ← скачанная копия (через `bash` curl или Read) How it starts
The opening of the file, as written. The whole thing — 200 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Character Sheet Skill
Делает persistent identity для AI-персонажа: одно изображение с 4-мя ракурсами на белом фоне → нейросети понимают «вот этот человек со всех сторон» и держат консистентность в любой последующей генерации.
Зачем нужен
- Soul ID без training: Higgsfield Soul ID требует 20+ фото и 3-5 минут серверного training. Наш подход — один вызов GPT Image 2, ~30 секунд, никаких account-bound артефактов.
- Workaround-free: западное сообщество клеит sheets через multi-image LoRA / ControlNet / отдельные runs со склейкой — часы работы. У нас одна команда.
- Persistent: sheet сохраняется в проекте юзера. Через неделю открыл проект — sheet на месте, продолжаешь с того же образа.
Pipeline
1. Intake — собрать референсы
- 1-3 фото персонажа (лицо обязательно, тело желательно).
- Если юзер не приложил — спроси: «Дай 1-3 reference фото — лицо/полный рост — или опиши персонажа текстом».
- Если только текстовое описание — сначала генерируем reference через
gpt-image-2-t2i(text-to-image), потом sheet черезgpt-image-2-i2i.
2. Дать имя персонажу
Спроси у юзера короткий slug на русском или английском: anya, boris, kim, model_summer. Slug — lowercase + дефисы, без пробелов. Используется как имя директории.
Если в проекте уже есть characters/<slug>/ — спроси: пересоздать sheet (overwrite) или взять новое имя.
3. Outfit — что на нём надет
Дефолт: нейтральная серая футболка + тёмные джинсы (универсально, не отвлекает от лица).
Альтернативы — спроси если нужно:
- formal: костюм, рубашка
- casual streetwear: oversized hoodie + кроссовки
- character-specific: по контексту (если для брендового проекта)
4. Генерация sheet через gpt-image-2-i2i
Используй preset presets/sheet-template-4-angle.md — там полный prompt template. Передаём через mcp__createya__run_model:
model: gpt-image-2-i2i
input:
image_url: <reference photo CDN URL>
prompt: <prompt from preset, with outfit substituted>
size: 1536x1024 (16:9, room for 4 figures)
quality: high
num_images: 1
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.
- 5d ago First seen · 200 lines · 140 tokens per session scan A 35c97c101080
character-sheet is a skill published in the GitHub repository Createya-ai/Createya-mcp (4 stars, last pushed 3mo ago), licensed MIT. It adds 140 tokens to every session and 2,365 once invoked, about $0.0007 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.
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.
ai-hive-simulate-36kr
当用户搜索用AI模拟36氪、AI模拟36氪、36氪AI模拟、36氪数字人、36氪AI分身、36氪内容风格、36氪选题、36氪文案、36氪短视频、36氪知识库、36氪思想顾问、36氪战略顾问，或希望借助 AI 研究36氪公开内容中的AI、科技、产品、数码、工程实践或知识科普方法时使用。本 Skill 面向AI学习者、科技从业者、产品经理、创作者和关注新技术的普通用户，先建立公开来源样本库，再提炼选题母题、受众问题、论证结构、内容节奏和视觉方向，并可把用户有权使用的文章、演讲、课程笔记和资料整理成36氪方法论知识库，以可追溯引用的方式提供战略顾问式分析；也可通过 AI-HIVE…
ai-hive-simulate-agi-hunt
当用户搜索用AI模拟AGI Hunt、AI模拟AGI Hunt、AGI HuntAI模拟、AGI Hunt数字人、AGI HuntAI分身、AGI Hunt内容风格、AGI Hunt选题、AGI Hunt文案、AGI Hunt短视频、AGI Hunt知识库、AGI Hunt思想顾问、AGI Hunt战略顾问，或希望借助 AI 研究AGI Hunt公开内容中的AI工具、Agent、AI编程、AIGC视觉、内容生产、产品、创业或商业落地方法时使用。本 Skill…
ai-hive-simulate-ai-dance
当用户搜索用AI模拟AI Dance、AI模拟AI Dance、AI DanceAI模拟、AI Dance数字人、AI DanceAI分身、AI Dance内容风格、AI Dance选题、AI Dance文案、AI Dance短视频、AI Dance知识库、AI Dance思想顾问、AI Dance战略顾问，或希望借助 AI 研究AI Dance公开内容中的AI工具、Agent、AI编程、AIGC视觉、内容生产、产品、创业或商业落地方法时使用。本 Skill…
ai-hive-simulate-aidan-gomez
当用户搜索用AI模拟Aidan Gomez、AI模拟Aidan Gomez、Aidan GomezAI模拟、Aidan Gomez数字人、Aidan GomezAI分身、Aidan Gomez内容风格、Aidan Gomez选题、Aidan Gomez文案、Aidan Gomez短视频、Aidan Gomez知识库、Aidan Gomez思想顾问、Aidan Gomez战略顾问，或希望借助 AI 研究Aidan Gomez公开内容中的人工智能、云计算、芯片、软件、互联网平台、创业投资、开源技术或未来科技方法时使用。本 Skill…
ai-hive-simulate-aiera
当用户搜索用AI模拟新智元、AI模拟新智元、新智元AI模拟、新智元数字人、新智元AI分身、新智元内容风格、新智元选题、新智元文案、新智元短视频、新智元知识库、新智元思想顾问、新智元战略顾问，或希望借助 AI 研究新智元公开内容中的AI、科技、产品、数码、工程实践或知识科普方法时使用。本 Skill 面向AI学习者、科技从业者、产品经理、创作者和关注新技术的普通用户，先建立公开来源样本库，再提炼选题母题、受众问题、论证结构、内容节奏和视觉方向，并可把用户有权使用的文章、演讲、课程笔记和资料整理成新智元方法论知识库，以可追溯引用的方式提供战略顾问式分析；也可通过 AI-HIVE…