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 rules/wangtingyeye/llm-agent-study/agnogit clone --depth 1 https://github.com/WangTingYeYe/llm-agent-studyWhat 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 | $0.00842 |
| Opus 5 | $0.00000 | $0.00421 |
| Sonnet 5 | $0.00000 | $0.00168 |
| Haiku 4.5 | $0.00000 | $0.00084 |
Grade A, and why
agno 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.
What it actually says
description: 该规则解释了 Agno 多智能体系统框架的约定和最佳实践。 globs: **/*.py alwaysApply: false
Agno 规则
基础概念
- Agno 是用于构建多智能体系统的 Python 框架，支持共享内存、知识和推理
- 支持5个级别的智能体构建：工具智能体、知识智能体、记忆智能体、团队智能体、工作流智能体
智能体构建规范
- 使用
Agent类创建基础智能体：Agent(model=model, tools=tools, instructions="...") - 为复杂任务使用推理智能体，导入
ReasoningTools(add_instructions=True) - 所有智能体都应设置清晰的
instructions参数 - 使用
markdown=True参数启用 Markdown 格式输出
模型使用规范
- 框架支持23+模型提供商，使用统一接口避免供应商锁定
- 导入特定模型：
from agno.models.anthropic import Claude - 推荐使用最新的推理模型如
Claude(id="claude-sonnet-4-20250514") - 根据任务需求选择合适的模型提供商
工具集成规范
- 使用
tools参数为智能体添加功能：tools=[ReasoningTools(), YFinanceTools()] - 工具导入格式：
from agno.tools.toolname import ToolClass - 为工具指定具体功能参数，如
YFinanceTools(stock_price=True, analyst_recommendations=True) - 优先使用内置工具，避免重复实现
团队协作规范
- 使用
Agent Teams构建多智能体协作系统 - 团队智能体支持推理、记忆和共享上下文
- 为团队设置明确的角色分工和协作机制
- 实现智能体间的有效通信和状态共享
知识和记忆规范
- 使用内置的
Storage和Memory驱动为智能体提供长期记忆 - 集成20+向量数据库实现智能体搜索功能
- 使用异步高性能的 Agentic RAG 进行知识检索
- 为智能体提供领域特定知识库
结构化输出规范
- 使用模型提供的结构化输出或
json_mode返回类型化响应 - 智能体原生支持多模态：文本、图像、音频、视频输入输出
- 使用表格格式展示数据：
instructions="Use tables to display data."
工作流规范
- 使用 Agentic Workflows 构建确定性、有状态的多智能体工作流
- 工作流支持状态管理和流程控制
- 实现工作流的可监控和可调试性
部署和监控规范
- 使用预构建的 FastAPI 路由快速部署智能体服务
- 在 agno.com 平台监控智能体会话和性能
- 使用 Playground 进行智能体测试和调试
- 实现智能体的评估和持续改进
性能优化规范
- 智能体实例化时间约3μs，内存使用约6.5Kib
- 优先使用异步操作提高性能
- 合理配置智能体的内存和存储参数
- 使用缓存机制优化重复操作
最佳实践
- 从简单的工具智能体开始，逐步构建复杂系统
- 为智能体设置清晰的指令和角色定义
- 使用推理功能提高智能体的可靠性
- 实现适当的错误处理和异常管理
- 定期评估和优化智能体性能
- 使用监控工具跟踪智能体行为和效果
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 · 88 lines · 0 tokens per session scan A c0086e01b3ef
agno is a cursor rule published in the GitHub repository WangTingYeYe/llm-agent-study (4 stars, last pushed 1y ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 842 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.
Other cursor rules, from other repositories
angular-20
This rule provides comprehensive best practices and coding standards for Angular development, focusing on modern TypeScript, standalone components, signals, and performance optimizations.
dev-standard
Apache Superset development standards and guidelines for Cursor IDE.
cli-error-handling
CLI command error handling patterns.
prefer-direct-imports-over-module-mocks
Prefer extracting a testable core over vi.mock / vi.resetModules when unit tests need to reach production logic entangled with config, env, or singletons.
control-plane-descriptors
Control plane descriptor and instance implementation patterns.
family-instance-domain-actions
Family instance domain action implementation patterns.