A set of rules for using Createya, a remote service that generates images, videos, audio, and user-generated content through MCP. MCP is a way for an AI agent to call external tools.

Use it when planning photoshoots or creating image, video, audio, or UGC content with Createya.

It gives the agent a defined process for preparing prompts, checking results, estimating costly requests, and getting approval before making variations.

cursor — Cursor rule by Createya-ai

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 rules/createya-ai/createya-mcp/cursor

Clone the repo

git clone --depth 1 https://github.com/Createya-ai/Createya-mcp

Per session 0 Nothing until a file matches its globs; then the whole rule loads.

When invoked 529 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.

Model	Per session	Once invoked
Fable 5	$0.00000	$0.00529
Opus 5	$0.00000	$0.00264
Sonnet 5	$0.00000	$0.00106
Haiku 4.5	$0.00000	$0.00053

Measured yesterday against content hash a2e252628c52, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

cursor 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 yesterday.

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 -H "Authorization: Bearer $CREATEYA_API_KEY" https://api.createya.ai/v1/models

configs/cursor.mdc · 52 lines

What it actually says

Createya Creative Director

When the user asks to generate images, videos, audio, plan a photoshoot, or create UGC content:

Workflow

Brief — if incomplete, ask: subject, style, platform, target format
Guide — call get_model_guide(slug) before every run_model — this is the primary source for prompt structure and anti-patterns
Etalon — generate one reference frame with locked composition (250+ word English prompt)
Approval gate — show result, wait for "ок" / "да" / "good" / any approval signal
Variations — image-to-image from the approved etalon

Key Rules

Credit estimate before any model costing >50 credits
UGC content: add imperfection block (grain, off-center framing, handheld aesthetic) + skin realism (visible pores, NO acne)
Two-step video: approved still → animate with video model
After each generation: visual QA (sharp, correct subject/composition/lighting), max 2 retries with refined prompt

Available MCP Tools

list_models — available models with prompt style hints
get_model_guide — full prompt guide: skeleton, anti-patterns, examples
run_model — generate image or video (sync or async)
get_run_status — poll async generation every 30s
request_upload_url — presigned PUT URL for reference upload (24h CDN, 50MB max)

REST Fallback (if MCP unavailable)

# List models
curl -H "Authorization: Bearer $CREATEYA_API_KEY" https://api.createya.ai/v1/models

# Get prompt guide
curl -H "Authorization: Bearer $CREATEYA_API_KEY" \
  https://api.createya.ai/v1/models/nano-banana-pro/prompting-guide

# Generate
curl -X POST -H "Authorization: Bearer $CREATEYA_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model":"nano-banana-pro","prompt":"...","parameters":{}}' \
  https://api.createya.ai/v1/generate

Full skill reference: https://github.com/Createya-ai/createya-mcp/blob/main/skills/creative-director/SKILL.md

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.

yesterday First seen · 52 lines · 0 tokens per session scan A a2e252628c52

Subscribe to this mod's changes

cursor is a cursor rule published in the GitHub repository Createya-ai/Createya-mcp (4 stars, last pushed 3mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 529 tokens. 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.

Creative and media Planning Writing and docs ai-image-generation ai-video-generation claude claude-code cline codex

cursor

Getting it into your agent

What it costs to keep this loaded

Grade A, and why

Makes network callslowCapability

What it actually says

Createya Creative Director

Workflow

Key Rules

Available MCP Tools

REST Fallback (if MCP unavailable)

What this file has done since we first saw it

Other cursor rules, from other repositories

core

billing

test-manim

angular-20

dev-standard

typescript