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 instructions/createya-ai/createya-mcp/agents-mdgit 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/instructions/createya-ai/createya-mcp/agents-md)<a href="https://agentmods.dev/instructions/createya-ai/createya-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/createya-ai/createya-mcp/agents-md.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 | $0.01597 | $0.01597 |
| Opus 5 | $0.00798 | $0.00798 |
| Sonnet 5 | $0.00319 | $0.00319 |
| Haiku 4.5 | $0.00160 | $0.00160 |
Grade D, and why
Createya-mcp AGENTS.md scanned grade D with 3 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 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.
Downloads and executes remote codehighSupply chain
curl | sh runs whatever the server returns today, which is not necessarily what it returned when this was reviewed.
curl -fsSL https://api.createya.ai/install | bash -s -- crya_sk_YOUR_KEY Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
| OpenAI Codex CLI | ✅ `~/.codex/config.toml` | `~/.agents/skills/<skill>/` (+ `~/.codex/AGENTS.md`) | Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -fsSL https://api.createya.ai/install | bash -s -- crya_sk_YOUR_KEY How it starts
The opening of the file, as written. The whole thing — 154 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent instructions — Createya MCP
What this repo is
- MCP server at
https://api.createya.ai/mcp— 100+ AI generation models (FLUX, Kling, Runway, Sora 2, Veo 3.1, Midjourney, Higgsfield, Seedance, Nano Banana and more) - Skills in
skills/:createya— base MCP integration (model catalogue, run, balance)creative-director— AI creative director for photo shoots, lookbooks, UGC, editorial seriescharacter-sheet— generate persistent character reference sheets via GPT Image 2 (6 close-ups + tall full-body), saved intocreateya/characters/<slug>/for reuse across photo and video generations
- Codex plugin in
plugins/createya-mcp/:.codex-plugin/plugin.json— Codex Plugins UI metadata (name, logo, starter prompts).mcp.json— Createya MCP endpoint for Codex plugin install/auth flows- docs:
docs/codex-plugin.md skills/andassets/— generated copies synced from repo root
- Local workspace is created per-project in
<cwd>/createya/(assets, sessions, characters) — never on Desktop or in~. Run~/.claude/skills/creative-director/scripts/setup.shonce inside the project root to scaffold it.
Setup — one command
curl -fsSL https://api.createya.ai/install | bash -s -- crya_sk_YOUR_KEY
Get a key first: https://createya.ai/settings/api-keys (format: crya_sk_<32hex>)
This single command:
- Installs
createyaandcreative-directorskills for your agent - Registers the MCP server with your API key
- Auto-detects your agent type (Claude Code, Cursor, Codex, OpenClaw)
After install, restart your agent. MCP tools and skills are immediately available.
What gets installed per agent
| Agent | MCP registered | Skills target |
|---|---|---|
| Claude Code | ✅ claude mcp add |
~/.claude/skills/<skill>/ |
| OpenAI Codex CLI | ✅ ~/.codex/config.toml |
~/.agents/skills/<skill>/ (+ ~/.codex/AGENTS.md) |
| Cursor (2.x+) | — | ~/.agents/skills/<skill>/ (+ legacy ~/.cursor/skills/) |
| OpenClaw | — | ~/.agents/skills/<skill>/ (+ legacy ~/.openclaw/skills/) |
| opencode | — | uses ~/.claude/skills/ directly (no separate target) |
| Cline / Windsurf / Continue | — | manual JSON in configs/ |
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.
- 3d ago First seen · 154 lines · 1,597 tokens per session scan D 481388acfeef
Createya-mcp AGENTS.md is an instructions file published in the GitHub repository Createya-ai/Createya-mcp (4 stars, last pushed 3mo ago), licensed MIT. It adds 1,597 tokens to every session, about $0.0080 per session on Opus 5. A static security scan graded it D with 3 findings (downloads and executes remote code, reads agent configuration directories, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other instructions, from other repositories
wavespeed-cli CLAUDE.md
Instructions for WaveSpeedAI/wavespeed-cli, covering claude.md, commands and architecture.
visual-storytelling-skills AGENTS.md
Instructions for leynos/visual-storytelling-skills, a project described as: Agent skills for AI film production — from prose to picture.
creators-studio CLAUDE.md
Instructions for juliandickie/creators-studio, covering claude.md -- development context for creators-studio, third-party api reference (workspace-level), what this repo is, plugin structure and model status (as of march 2026).
dynatrace-mcp copilot-instructions.md
Instructions for dynatrace-oss/dynatrace-mcp, covering dynatrace mcp server, guidelines, repo structure, coding guidelines and dependencies.
claude-code-templates CLAUDE.md
Claude Code instructions for Justdvp/claude-code-templates, covering claude.md, project overview, development commands, package management and application commands.
agent-toolkit AGENTS.md
Instructions for Arnosdeus/agent-toolkit, covering shared agent instructions, repository inspection, existing architecture, frontend and ui quality and testing.