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/ly1836/spring-ai-rag-demo/ai-codinggit clone --depth 1 https://github.com/ly1836/spring-ai-rag-demoWhat 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 | $0.00314 | $0.00314 |
| Opus 5 | $0.00157 | $0.00157 |
| Sonnet 5 | $0.00063 | $0.00063 |
| Haiku 4.5 | $0.00031 | $0.00031 |
Grade A, and why
ai-coding 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 yesterday.
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
AI 协作规则
语言
- 所有对话、注释说明、提交信息优先使用中文
- 注释规则覆盖所有源码：Java / SQL / JavaScript / CSS / HTML（前端用 JSDoc 中文注释）
Commit 格式
<type>: <中文描述>
AI-Generated: true
AI-Tool: Cursor
Reviewed-by: <git config user.name>
type: feat / fix / refactor / docs / style / test / chore
AI 行为约束
- 优先小提交（<500 行变更）
- 安全敏感代码必须经过人工审核
- 不确定的技术决策主动询问，不擅自决定
- 修改代码前先阅读相关上下文，理解现有设计意图
- 后端 API 改动时主动评估对前端的连带影响（请求/响应结构、错误码、SSE 协议），同步更新
static/下相关文件 - 修改
static/app.js/static/style.css/static/vendor/*后，必须更新static/index.html中对应资源的?v=N版本号，避免浏览器缓存导致前端不刷新
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.
- yesterday First seen · 34 lines · 314 tokens per session scan A df5f08da58b2
ai-coding is a cursor rule published in the GitHub repository ly1836/spring-ai-rag-demo (84 stars, last pushed 29d ago), licensed Apache-2.0. It adds 314 tokens to every session, about $0.0016 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 2026-08-30.
Other cursor rules, from other repositories
000-core
Core principles for LMForge - production-grade LLMOps platform.
020-flask
Flask API Gateway conventions for LMForge.
030-langchain
LangChain/LangGraph rules for LMForge agents and workflows.
010-python
Python best practices for LMForge.
040-api-security
Security, auth, and async tasks for LMForge API.
selectools-providers
Rules for working with LLM provider adapters in selectools.