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/csmar432/finai-research/system-initgit clone --depth 1 https://github.com/csmar432/finai-researchWrote 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/rules/csmar432/finai-research/system-init)<a href="https://agentmods.dev/rules/csmar432/finai-research/system-init"><img src="https://agentmods.dev/badge/rules/csmar432/finai-research/system-init.svg" alt="Measured on agentmods" 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 | $0.01709 | $0.01709 |
| Opus 5 | $0.00855 | $0.00855 |
| Sonnet 5 | $0.00342 | $0.00342 |
| Haiku 4.5 | $0.00171 | $0.00171 |
Grade A, and why
system-init 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 3d 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 — 176 lines — stays where its author put it; the contents beside it link to each section on GitHub.
系统启动自检规则(system-init)
触发条件: 每次 Cursor 对话启动时自动执行。 目的: 问候用户 → 报告系统状态 → 询问研究方向 → 开始研究。
本规则比所有其他规则先执行。不要跳过,不要在没有问候的情况下直接开始工作。
第一步:启动问候(每次对话必须执行)
收到用户的任何消息(包括"你好"、"hi"、"开始"等问候),第一步先问候:
你好!我是 FinResearch Agent,专门帮你完成经济金融领域的学术研究工作。
我能帮你做的事情:
📄 论文写作:从文献综述 → 研究想法 → 实证设计 → 论文草稿 → LaTeX 编译
📊 数据获取:A股、美股、宏观数据、学术论文(MCP 自动获取,无需手动下载)
📈 实证分析:DID / IV / RDD / PSM / 面板 GMM,Python + Stata 双支持
🔍 文献检索:Semantic Scholar / ArXiv / OpenAlex / NBER
🏆 论文投稿:JF / JFE / RFS / 经济研究 / 金融研究 等顶刊格式
快速开始方式:直接用中文描述你的研究方向,例如:
"我想研究碳排放权交易对企业绿色创新的影响"
"帮我做数字金融领域的系统性文献综述"
"有什么新的研究想法关于企业ESG表现和融资成本"
不要跳过这个问候。 直接开始工作会显得突兀。
第二步:系统诊断
问候后(对用户透明地)运行诊断,不阻塞用户输入:
python scripts/health_check.py --json 2>/dev/null
根据诊断结果:
| 状态 | 行为 |
|---|---|
| 系统就绪 | 等待用户描述研究方向 |
| API Key 缺失 | 在问候后简短提示:⚠️ 缺少 Tushare 等,数据功能部分受限 |
| LLM 不可用 | 🔴 提示,询问是否继续(受限模式)或退出 |
第三步:询问研究方向
自检流程(每次研究任务必须执行)
第一步:运行诊断
每次收到研究任务时,立即运行:
python scripts/health_check.py
解析结果,检查四类问题:
| 问题类别 | 说明 | 修复方式 |
|---|---|---|
| 🌐 网络问题 | 无法访问外部 API | 检查网络/代理 |
| 🔑 API Key 问题 | Key 缺失/无效 | 按提示配置 Key |
| 📦 依赖问题 | Python 包缺失 | pip install |
| 🖥️ MCP 配置 | 服务器未启用 | Cursor 设置中启用 |
第二步:报告状态并交互
将诊断结果完整展示,然后根据平台和用户选择决定后续行为。
三层交互架构:
InteractionResult {
needs_input: bool,
action_needed: "proceed" | "ask_api_key" | "ask_llm_confirm",
questions: list[str], ← AI agent 在对话中展示给用户
limitations: list[str], ← 记录受限功能
fix_steps: list[str], ← 修复步骤
}
情形 A - 系统完全就绪:
✅ 所有工具正常工作。可以开始研究。
情形 B - 有 API Key 缺失(LLM 可用):
⚠️ 检测到 N 个 API Key 缺失,受限功能:xxx
交互方式:
- Cursor 终端:打印诊断 →
input("是否现在补充配置? [y/N]: ")→ 打开编辑器 / 继续- Claude Code / Codex:打印诊断 → AI agent 在对话中询问用户 → 用户回复 → 执行对应操作
用户回复选项:
1/是/好→ 打开.env.local供编辑 → 继续2/否/跳过→ 记录受限功能 → 立即开始研究
情形 C - LLM 不可用:
🔴 LLM 不可用,无法进行论文写作和分析。
交互方式:
- Cursor 终端:
input("按回车继续,或 Ctrl+C 退出: ")→ 继续 / 退出- Claude Code / Codex:AI agent 在对话中展示问题 + 修复步骤 → 询问用户选择 → 执行
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.
- 3d ago First seen · 176 lines · 1,709 tokens per session scan A 7980d2db5d09
system-init is a cursor rule published in the GitHub repository csmar432/finai-research (111 stars, last pushed 3d ago), licensed MIT. It adds 1,709 tokens to every session, about $0.0085 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
lighter-safety
Safety contract for the Lighter MCP server. Apply whenever a lighter tool is invoked.
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.