agentmods.dev

poyo-ai-models

poyo-ai-models is a skill for Codex from PoyoAPI/poyo-devtools. It costs 74 tokens per session (545 once invoked), scanned A, original, MIT.

A skill for finding and running chat and media-generation models through PoYo. It checks the available model catalogue, input requirements, pricing, and the correct way to submit or monitor a job.

In plain words
What is it for?
Use it to compare models, check costs and inputs, run chat, generate media, submit long-running jobs, monitor them, and report credits or failures.
Why use it?
It reduces the risk of choosing an unavailable model or sending unsupported inputs. It also provides a consistent process for short responses and longer image, video, audio, or 3D tasks.

Skill for Codex

Written for Codex: agents/openai.yaml present. Also seen: mentions Codex.

not rated 1repo +1 7d ago A scan 74 tokens original MIT

Good fit Use it to compare models, check costs and inputs, run chat, generate media, submit long-running jobs, monitor them, and report credits or failures.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/poyoapi/poyo-devtools/poyo-ai-models
View source ↗ PoyoAPI/poyo-devtools
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.

Any agent
npx skills add PoyoAPI/poyo-devtools --skill poyo-ai-models
Clone the repo
git clone --depth 1 https://github.com/PoyoAPI/poyo-devtools

Made for: Codex.

Wrote 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.

agentmods badge for poyo-ai-models

README.md
[![agentmods](https://agentmods.dev/badge/skills/poyoapi/poyo-devtools/poyo-ai-models.svg)](https://agentmods.dev/skills/poyoapi/poyo-devtools/poyo-ai-models)
Your own site
<a href="https://agentmods.dev/skills/poyoapi/poyo-devtools/poyo-ai-models"><img src="https://agentmods.dev/badge/skills/poyoapi/poyo-devtools/poyo-ai-models.svg" alt="Measured on agentmods" height="20"></a>
Per session 74 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 545 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00074 $0.00545
Opus 5 $0.00037 $0.00272
Sonnet 5 $0.00015 $0.00109
Haiku 4.5 $0.00007 $0.00055

Measured 7d ago against content hash a40a833cb915, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

poyo-ai-models scanned grade A with 0 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 7d 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.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

skills/poyo-ai-models/SKILL.md · 40 lines

How it starts

The opening of the file, as written. The whole thing — 40 lines — stays where its author put it; the contents beside it link to each section on GitHub.

PoYo AI Models

Use the production Capability Catalog as the source of truth. Never invent model IDs or parameters.

Choose the integration

  1. Prefer hosted MCP at https://api.poyo.ai/mcp.
  2. After discovery, prefer ?models=MODEL_A,MODEL_B when a small strongly typed tool set is useful. Use ?categories=... only for bounded exploration, and never combine both filters.
  3. Use npx @poyoapi/mcp for clients that only support stdio.
  4. Use npx @poyoapi/cli for chat SSE or when MCP is unavailable.
  5. Mark Skill executions with _request_source: "skill" in MCP or --request-source skill in CLI.

Keep POYO_API_KEY in the environment or system keyring. Never put it in prompts, query strings, committed files, or retained shell history.

Execute

  1. Restate the desired modality, model constraints, inputs, output requirements, and budget.
  2. Search the catalog and inspect the selected model's schema and pricing.
  3. Validate every input against that schema.
  4. For chat, use poyo_chat; use CLI poyo chat MODEL --stream only when incremental output is required.
  5. For short generation, use poyo_run_model. For video, 3D, music, or other long work, use poyo_submit_job.
  6. Treat queued and running as incomplete. Poll with poyo_check_job until succeeded or failed.
  7. Report model ID, final status, credits, output URLs, and any partial or failed result.

Read the generated reference matching the requested category when it exists in references/. For every Suno model or workflow, also read references/suno.md before validating inputs or submitting a task.

Guardrails

  • Check account credits before expensive or repeated generation.
  • Do not automatically resubmit a paid request after a timeout or transport failure; first determine whether a task was created.
  • Do not claim completion while a task is queued or running.
  • Do not pass stream: true to MCP chat; MCP returns one complete tool result.
  • Preserve task IDs so interrupted work can resume without resubmission.

Read the full file on GitHub · 40 lines

Files

What ships with it

17 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.

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.

  1. 7d ago First seen · 40 lines · 74 tokens per session scan A a40a833cb915

Subscribe to this mod's changes

poyo-ai-models is a skill published in the GitHub repository PoyoAPI/poyo-devtools (1 stars, last pushed 7d ago), licensed MIT. It adds 74 tokens to every session and 545 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Creative and mediaData and AI
Related

Other skills, from other repositories

stable-diffusion

Text-to-image generation, inpainting, and img2img.

NousResearch/hermes-agent · 18 tokens

huggingface-lora-space-builder

Build and publish a Gradio demo on Hugging Face Spaces for a user-provided LoRA. Use when someone asks to create, generate, ship, or publish a Space, demo, Gradio app, or playground for a LoRA — including LoRAs for Qwen-Image, Qwen-Image-Edit, LTX-Video, Wan, FLUX, SDXL, or other diffusion base models. Also triggers…

huggingface/skills · 187 tokens

baoyu-danger-gemini-web

Generates images and text via reverse-engineered Gemini Web API. Supports text generation, image generation from prompts, reference images for vision input, and multi-turn conversations. Use when other skills need image generation backend, or when user requests "generate image with Gemini", "Gemini text generation"…

JimLiu/baoyu-skills · 74 tokens

seedance-antislop

This skill should be used when a Seedance 2.0 prompt contains generic AI filler, hollow superlatives, vague cinematic language, bloated adjectives, weak verbs, or needs sharper production-specific wording.

Emily2040/seedance-2.0 · 48 tokens

seedance-filter

This skill should be used when a Seedance 2.0 prompt is blocked or rejected, when moderation is a suspected cause of a problem, or when the user asks for a content-boundary review or safer alternative. Assess the actual request before offering a clarification.

Emily2040/seedance-2.0 · 57 tokens

seedance-vocab-en

This skill should be used when an English Seedance 2.0 prompt needs clearer production wording, less generic prose, or precise vocabulary for camera, lighting, motion, VFX, audio, and constraints. Route blocked prompts through seedance-filter for context and boundary review.

Emily2040/seedance-2.0 · 61 tokens