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 spawnpoint-inc/spawnpoint-plugin --skill open-modelsgit clone --depth 1 https://github.com/spawnpoint-inc/spawnpoint-pluginWrote 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/spawnpoint-inc/spawnpoint-plugin/open-models)<a href="https://agentmods.dev/skills/spawnpoint-inc/spawnpoint-plugin/open-models"><img src="https://agentmods.dev/badge/skills/spawnpoint-inc/spawnpoint-plugin/open-models/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/spawnpoint-inc/spawnpoint-plugin/open-models"><img src="https://agentmods.dev/badge/skills/spawnpoint-inc/spawnpoint-plugin/open-models.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 | $0.00095 | $0.01628 |
| Opus 5.5 | $0.00038 | $0.00651 |
| Sonnet 5.5 | $0.00019 | $0.00326 |
| Haiku 4.5 | $0.00010 | $0.00163 |
Grade A, and why
open-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 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.
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.
How it starts
The opening of the file, as written. The whole thing — 91 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Open models on spawnpoint
spawnpoint can run an app's model calls on open models (gpt-oss, GLM, Gemma, DeepSeek, bge) through its own endpoint. The user needs no provider account and no key: the deploy mints the project's key and ships it as env. The user chooses, once, per project.
1. Detect
Before deploy_project, look at the bundle for a provider call:
| Signal | Means |
|---|---|
openai in package.json or requirements.txt; new OpenAI(, from openai import |
OpenAI SDK: chat, embeddings, or both |
@anthropic-ai/sdk or anthropic; new Anthropic(, from anthropic import |
Anthropic SDK, Messages format |
ai with @ai-sdk/openai or @ai-sdk/anthropic |
Vercel AI SDK over one of the two |
langchain_openai, langchain_anthropic, @langchain/openai, @langchain/anthropic |
LangChain over one of the two |
api.openai.com or api.anthropic.com in source |
Raw HTTP to a provider |
OPENAI_API_KEY or ANTHROPIC_API_KEY read from env or in .env |
The key the switch removes |
Note what the calls do: chat, tool calling, embeddings, images in the messages, image generation, audio, structured JSON. The choice depends on it.
2. Ask, once
One question, before the deploy, naming what was found and the model you would pick, with keeping the provider as a plain option:
This app calls OpenAI for chat and embeddings. spawnpoint can run it on open models (gpt-oss-120b for chat, bge-m3 for embeddings) with no OpenAI key and no provider account. Switch, or keep OpenAI?
Never switch without the answer. Never ask twice for one project: a project that
already exists without an ai block on get_project was deployed on the provider on
purpose, so redeploy it as it is unless the user raises it. When the user already said
which they want (in the request, or earlier in the conversation), skip the question.
An app you are writing from scratch that needs a model: use the open model with no
question, since there is no provider to keep.
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 · 91 lines · 95 tokens per session scan A 2d7e47496844
open-models is a skill published in the GitHub repository spawnpoint-inc/spawnpoint-plugin (0 stars, last pushed yesterday), licensed MIT. It adds 95 tokens to every session and 1,628 once invoked, about $0.0004 per session on Opus 5.5. 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 2026-10-14.
Other skills, from other repositories
pinme-llm
Use this skill when a PinMe project (Worker TypeScript) needs to call OpenRouter-backed LLM APIs, including models, chat/completions, streaming, or OpenRouter web search. Guides AI to generate correct Worker TS code.
add-ai-webapi
Integrates Power Pages generative-AI summarization APIs (PREVIEW) into a Single Page Application (SPA) site — the Search Summary API and the Data Summarization API — on any record-detail or list page. Generates per-target service code (CSRF-handled) and AI site settings; delegates Web API settings, table permissions…
pinme-share
A tool for packaging a result as a static web page and publishing it through PinMe. A static page is a self-contained page that does not need a server to generate its content.
ai-ml-governance
Governs models and AI systems in production — intended use, evaluation, monitoring, human oversight, documentation, and the decision to deploy or retire. Use this before deploying a model or AI feature, when defining evaluation criteria, when a model's behavior has drifted, when assessing AI risk or regulatory…
nano-banana
This skill should be used for Python scripting and Gemini image generation. Use when users ask to generate images, create AI art, edit images with AI, or run Python scripts with uv. Trigger phrases include "generate an image", "create a picture", "draw", "make an image of", "nano banana", or any image generation…
cortex-model
Build an ML pipeline — from data to trained model to serving endpoint. Use when asked to "build ML model", "train a model", "prediction pipeline", "classification", or "regression".