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/kyh/vibedgames/generatenpx skills add kyh/vibedgames --skill generategit clone --depth 1 https://github.com/kyh/vibedgamesWrote 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/kyh/vibedgames/generate)<a href="https://agentmods.dev/skills/kyh/vibedgames/generate"><img src="https://agentmods.dev/badge/skills/kyh/vibedgames/generate.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 | $0.00134 | $0.01725 |
| Opus 5 | $0.00067 | $0.00863 |
| Sonnet 5 | $0.00027 | $0.00345 |
| Haiku 4.5 | $0.00013 | $0.00172 |
Grade A, and why
generate 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.
4. **Save files with `--download`, not curl.** The CLI handles authentication, naming, and file format detection. How it starts
The opening of the file, as written. The whole thing — 102 lines — stays where its author put it; the contents beside it link to each section on GitHub.
vg generate: model endpoint runner
vg generate is the agent-first CLI for generating images, video, and audio. It works in a terminal for humans (pretty output) and equally well for agents (structured JSON when piped or with --json). All other skills in this repo call vg generate for execution; they do not wrap any model HTTP API directly. Every call is forwarded through a single vibedgames server proc that attaches the credentials and proxies the request.
Vibedgames runtime. Install with
npm install -g vibedgames(orpnpm dogfoodin this repo). The vibedgames server holds the API key, so there is no per-machine setup. The CLI exposesrun,status,models,schema,upload,pricing, anddocs— the read/write surface that maps to the queue, platform, storage, and docs APIs.
For the full command surface (every flag, every option, every example), see references/full-reference.md. For setup details, see the Setup section below.
Critical rules
- Always use
--jsonwhen an agent will read the output. Pretty mode is for humans only. - Never invent endpoint IDs. Use
vg generate models "<query>"to discover,vg generate models --endpoint_id <id>to verify. - Inspect schema before running.
vg generate schema <endpoint_id> --jsonshows the exact field names. Guessed flags fail with 422. - Save files with
--download, not curl. The CLI handles authentication, naming, and file format detection. - Use
--asyncfor long-running generation. Image work usually completes inline; video/audio/3D usually need queue + status polling.
Command index
| Command | Purpose |
|---|---|
vg generate models <query> |
Search the catalog (or --category, or --endpoint_id) |
vg generate schema <endpoint_id> |
Inspect inputs/outputs (compact or --format openapi) |
vg generate run <endpoint_id> --<param> <value> |
Execute a model |
vg generate status <endpoint_id> <request_id> |
Poll an async job (with --result, --cancel, --download) |
vg generate upload <path> |
Upload a local file (returns a URL usable as a model input) |
vg generate pricing <endpoint_id> |
Check cost per call |
vg generate docs <query> |
Search generative-model documentation |
What ships with it
1 file 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 · 102 lines · 134 tokens per session scan A f2920bedb810
generate is a skill published in the GitHub repository kyh/vibedgames (55 stars, last pushed today), licensed MIT. It adds 134 tokens to every session and 1,725 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 2026-08-30.
Other skills, from other repositories
ai-app
Full-stack AI application generator with Next.js, AI SDK, and ai-elements. Use when creating chatbots, agent dashboards, or custom AI applications. Triggers: chatbot, chat app, agent dashboard, AI application, Next.js AI, useChat, streamText, ai-elements, build AI app, create chatbot.
mcp-builder
DEPRECATED: This skill has been replaced by mcp-app-builder. Check if mcp-app-builder is available in the skills folder. If not, install it: npx skills install mcp-use/mcp-use --skill mcp-app-builder Use mcp-app-builder instead of this skill. Build Model Context Protocol (MCP) servers with mcp-use framework. Use when…
cypress-e2e
Write or refactor Cypress E2E tests following Page Object Model, action/assertion separation, and project conventions. Use when creating new tests, refactoring existing ones, or adding page object functions.
trigger-agents
AI agent patterns with Trigger.dev - chat.agent, Sessions, AI Prompts, Trigger Agent Skills, orchestration, parallelization, routing, evaluator-optimizer, and human-in-the-loop. Use when building LLM-powered tasks that need durable AI chat, parallel workers, approval gates, tool calling, or multi-step agent workflows.
Cursor rules for Next
Cursor rules for Next.js development with React 19, Vercel AI, and Tailwind CSS integration.
mcp-builder
Guide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use when building MCP servers to integrate external APIs or services, whether in Python (FastMCP) or Node/TypeScript (MCP SDK).