Configuration rules for creating language models through one shared ModelConfig interface, with support for several hosted providers and local Ollama models. The configuration can include the model, provider, temperature, token limit, reasoning, and web-search settings.

Choosing OpenRouter by default or connecting directly to OpenAI, Google, Anthropic, Alibaba, Volcengine, or Ollama, while setting model behavior and request limits.

They give the application one consistent way to select models and provider-specific connections instead of scattering model setup throughout the code.

models — Cursor rule by linhai0872

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/linhai0872/agno-agent-starter/models

Clone the repo

git clone --depth 1 https://github.com/linhai0872/agno-agent-starter

Made for: Cursor.

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

When invoked 700 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. 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	$0.00700
Opus 5	$0.00000	$0.00350
Sonnet 5	$0.00000	$0.00140
Haiku 4.5	$0.00000	$0.00070

Measured 2d ago against content hash fa149090b376, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

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 2d 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.

.cursor/rules/models.mdc · 117 lines

How it starts

The opening of the file, as written. The whole thing — 117 lines — stays where its author put it; the contents beside it link to each section on GitHub.

模型配置规范

核心接口

使用 ModelConfig 统一配置，支持 8 大厂商。

基础配置

from app.models import ModelConfig, create_model

config = ModelConfig(
    model_id="google/gemini-2.5-flash-preview-09-2025",
    temperature=0.1,
    max_tokens=16384,
)

model = create_model(config)

多厂商支持

from app.models import ModelConfig, ModelProvider

# OpenRouter（默认）
config = ModelConfig(model_id="google/gemini-2.5-flash-preview-09-2025")

# OpenAI 直连
config = ModelConfig(
    provider=ModelProvider.OPENAI,
    model_id="gpt-4o",
)

# Google Gemini 直连
config = ModelConfig(
    provider=ModelProvider.GOOGLE,
    model_id="gemini-2.5-flash",
)

# Anthropic Claude
config = ModelConfig(
    provider=ModelProvider.ANTHROPIC,
    model_id="claude-sonnet-4",
)

# 阿里云 DashScope
config = ModelConfig(
    provider=ModelProvider.DASHSCOPE,
    model_id="qwen-plus",
)

# 火山方舟
config = ModelConfig(
    provider=ModelProvider.VOLCENGINE,
    model_id="doubao-seed-1-6-251015",
)

# Ollama 本地
config = ModelConfig(
    provider=ModelProvider.OLLAMA,
    model_id="llama3.2:latest",
)

高级配置

from app.models import ReasoningConfig, WebSearchConfig

# 启用思考模式
config = ModelConfig(
    model_id="google/gemini-2.5-flash-preview-09-2025",
    reasoning=ReasoningConfig(enabled=True, effort="medium"),
)

# 启用网络搜索
config = ModelConfig(
    model_id="google/gemini-2.5-flash-preview-09-2025",
    web_search=WebSearchConfig(enabled=True),
)

API Key 优先级

from app.models import ModelConfig, ProjectConfig

# Agent 级（最高优先级）
config = ModelConfig(api_key_env="MY_AGENT_KEY")

# Project 级（Workflow/Team 共享）
project = ProjectConfig(api_key_env="MY_PROJECT_KEY")
model = create_model(config, project)

# Global 级（兜底）
# 使用环境变量 OPENROUTER_API_KEY

支持的厂商

Provider	说明
OPENROUTER	统一网关，100+ 模型
OPENAI	GPT-4o, o1/o3 系列
GOOGLE	Gemini 2.5 系列
ANTHROPIC	Claude Sonnet 4, Opus 4
DASHSCOPE	Qwen 系列
VOLCENGINE	豆包 Seed, DeepSeek
OLLAMA	本地部署
LITELLM	统一网关

Read the full file on GitHub · 117 lines

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.

2d ago First seen · 117 lines · 0 tokens per session scan A fa149090b376

Subscribe to this mod's changes

models is a cursor rule published in the GitHub repository linhai0872/agno-agent-starter (6 stars, last pushed 7mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 700 tokens. 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.

Data and AI LLM Multi-Agent agentos agno ai-agent openrouter

models

Getting it into your agent

What it costs to keep this loaded

Grade A, and why

Nothing flagged

How it starts

模型配置规范

核心接口

基础配置

多厂商支持

高级配置

API Key 优先级

支持的厂商

What this file has done since we first saw it

Other cursor rules, from other repositories

prompt-design

api-key-controls

rag-design-for-overall-program

part-1-and-part-2-cointeraction-architecture

json-prompt-design

clarify-first-prompting