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 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/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/createya-ai/createya-mcp/character-sheet"><img src="https://agentmods.dev/badge/skills/createya-ai/createya-mcp/character-sheet.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 | $0.00140 | $0.02365 |
| Opus 5.5 | $0.00056 | $0.00946 |
| Sonnet 5.5 | $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 1mo 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.
- 1mo 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 5mo ago), licensed MIT. It adds 140 tokens to every session and 2,365 once invoked, about $0.0006 per session on Opus 5.5. 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
ai-hive-simulate-ali-abdaal
A research and content-planning workflow that studies Ali Abdaal’s public work on AI, technology startups, products, business, and teaching. It turns those observations into original material and advisory analysis without impersonating him.
ai-hive-simulate-aravind-srinivas
A research and content-planning workflow that studies Aravind Srinivas’s public work on AI, technology startups, products, business, and teaching. It turns those observations into original material and advisory analysis without impersonating him.
ai-hive-simulate-baoyu-xp
A research and writing workflow that studies Baoyu XP's public methods for explaining AI, technology, products, digital tools, and engineering. It turns those general methods into original content and does not impersonate Baoyu XP.
ai-hive-simulate-berryxia-ai
A research and writing workflow that studies Berryxia AI's public methods for AI tools, agents, AI programming, visual generation, products, and business use. It adapts those methods into original work without imitating the person's identity.
ai-hive-simulate-dario-amodei
A research and content-planning workflow that studies Dario Amodei’s public material about AI, technology companies, products, and management.
ai-hive-simulate-david-holz
A research and content-planning workflow that studies David Holz's public material and turns its general methods into original work using your own facts and experience. It can also organise authorised documents into a source-linked reference library.