finai-research: Instructions file for Claude Code

CLAUDE.md

finai-research CLAUDE.md is an instructions file for Claude Code from csmar432/finai-research. It costs 5,979 tokens per session, scanned A, original, MIT.

Project instructions for an AI research assistant focused on economics and finance. They describe workflows for literature reviews, research ideas, empirical studies, paper drafts, LaTeX documents, and review support.

In plain words
What is it for?
They are for guiding research projects from topic selection through literature review, causal analysis, drafting, compilation, and testing.
Why use it?
They give the agent a defined research process and warn that generated research must be checked by a human before submission.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: reads .claude/ paths; mentions CLAUDE.md; mentions Claude Code.

This is csmar432/finai-research's own configuration. It tells Claude Code how to work on finai-research itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything finai-research configures →

Reuse

Borrowing it

Nothing to install: this file belongs to csmar432/finai-research. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/csmar432/finai-research/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/csmar432/finai-research

Made for: Claude Code.

Wrote 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.

agentmods badge for finai-research CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/csmar432/finai-research/claude-md/github.svg)](https://agentmods.dev/instructions/csmar432/finai-research/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/csmar432/finai-research/claude-md"><img src="https://agentmods.dev/badge/instructions/csmar432/finai-research/claude-md/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.

agentmods 80×15 button for finai-research CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/csmar432/finai-research/claude-md"><img src="https://agentmods.dev/badge/instructions/csmar432/finai-research/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 5,979 This file is loaded in full into every session.
When invoked 5,979 The same file — it is already loaded in full.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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.

ModelPer sessionOnce invoked
Fable 5.1 $0.05979 $0.05979
Opus 5 $0.02989 $0.02989
Sonnet 5 $0.01196 $0.01196
Haiku 4.5 $0.00598 $0.00598

Measured yesterday against content hash 3663b405b4eb, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

finai-research CLAUDE.md 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.

CLAUDE.md · 385 lines

How it starts

The opening of the file, as written. The whole thing — 385 lines — stays where its author put it; the contents beside it link to each section on GitHub.

论文-研报工作流 · FinResearch Agent

📌 占位符约定:本文档中提及的 MCP 总数使用 {{MCP_COUNT}} 占位符。 实际数字由 python scripts/count_mcp.py 自动扫描 mcp_servers/user_* 目录后写入 .docs-cache/MCP_COUNT.txt。新增/删除 MCP 目录后,跑一次该脚本即可让所有引用保持准确。

CI 状态:PR-1 ~ PR-7 全部 merge,16/16 CI 全绿(3165d09)。

经济金融领域 AI 研究助手。生成论文草稿,集成 MCP 数据获取、因果推断、LaTeX 排版和 AI 辅助 review。

⚠️ 重要声明:本工具生成的论文草稿必须经研究者逐字审阅后方可投稿。所有因果识别策略、统计结果和引用必须由研究者独立核实。

适用工具: Claude Code · GitHub Copilot · Cursor(通用 AI 编码工具均可)


一句话

"告诉我研究主题,我帮你:从文献综述 → 想法生成 → 实证设计 → 论文草稿 → LaTeX 编译。(草稿需研究者审阅后投稿。)"


快速开始

不需要记命令。直接说研究方向:

"我想研究关税政策对A股出口型企业创新的影响,设计一篇发表在经济研究的实证论文"
"帮我做数字金融领域的文献综述"
"有什么新的研究想法关于企业ESG表现和融资成本"

或用脚本直接运行:

# 写作轨
python scripts/agent_pipeline.py --topic "碳排放权交易对企业绿色创新的影响" --use-hitl
# 实证轨(现代 DID)
python -m scripts.research_framework.enhanced_pipeline --topic "碳排放权交易对企业绿色创新的影响"
pytest tests/ -v

自动启动流程(每次对话必须执行)

用户打开对话
        ↓
① 问候 + 能力介绍(固定文案,不跳过)
        ↓
② 快速诊断:python scripts/startup_check.py(轻量,<3秒)
        ↓
③ 详细诊断(可选):python scripts/health_check.py --verify
        ↓
④ MCP 注册检查:python scripts/register_mcp_servers.py --list
        ↓
  ┌─ API Key 缺失 → 简短提示(不阻塞)
  ├─ LLM 不可用 → 询问是否继续
  ├─ MCP 未注册 → 提示运行 `python scripts/register_mcp_servers.py`
  └─ LaTeX 缺失 → 提示安装 tectonic / MacTeX
        ↓
⑤ 等待研究方向 → 用户描述 → 开始研究
        ↓
⑥ 推荐路径(两条,勿混用文档死链):
     · 新用户澄清:python scripts/start_research.py --topic "..."
       (锁定 research_profile.json;默认不自动开跑)
       可选:加 --continue --use-hitl 进入写作流水线
     · 直接写作:python scripts/agent_pipeline.py --topic "..." [--use-hitl]
       (--use-hitl 默认停 outline/literature/draft)
     · HITL:agent_pipeline 的 HITLGate;InteractivePipelineCheckpoint
       仅供技能/脚本手动 import,不自动挂入主流水线

第一步问候是强制要求,不要跳过。直接开始工作会显得突兀。


核心能力

数据获取(MCP,{{MCP_COUNT}} 个服务器目录)

重要说明{{MCP_COUNT}} 个 MCP 目录中,28 个完全免费(无需 API Key),12 个需要 API Key,3 个为 opt-in 法律风险。详见 python scripts/count_assets.py

你要什么 用这个 MCP
A股行情/财务/融资融券 user-tushare(需 TUSHARE_TOKEN)
中国宏观(GDP/CPI/M2) user-financial
美联储/FOMC user-fed-data
世界银行宏观 user-wb-data
IMF数据 user-imf-data
OECD数据 user-oecd-data
美国经济分析局GDP user-bea-data
国债收益率/经济日历 user-eodhd(需Key)或 user-fed-data
美股/ETF/期权/财务 user-yfinance
研报/新闻/板块/分析师 user-eastmoney-reports
公募基金 user-eastmoney-fund
债券数据 user-eastmoney-bond
期权数据 user-eastmoney-option
外汇/航运/大宗商品 user-enhanced-finance
加密货币 user-cryptocompare
SEC 10-K/10-Q/8-K user-sec-edgar
学术论文(全文) user-openalexuser-arxivuser-context7user-semantic-scholar
NBER工作论文 user-nber-wp
中文文献(CSSCI/CNKI) user-chinese-literatureuser-wanfanguser-csmar
中国专利数据 user-sipo
中国海关数据 user-chinese-customs
Wind数据 user-wind(需账号)
CSMAR国泰安 user-csmar(需Key)
CEIC宏观 user-macro-ceic
省级/市级统计 user-province-statsuser-hubei-statsuser-wuhan-stats
新闻搜索 user-newsapi(需Key)、user-brave-search(需Key)
云端代码执行 user-e2b-mcp(需Key)
浏览器自动化 user-playwright-mcp
数据处理 user-pandas-mcp
LaTeX排版检查 user-latex-mcp
文件系统操作 user-filesystem-mcp

Read the full file on GitHub · 385 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.

  1. yesterday Changed 3663b405b4eb
  2. 4d ago Changed · +5 tokens per session d67e02374c9a
  3. 10d ago First seen · 385 lines · 5,974 tokens per session scan A d7b449c32553

Subscribe to this mod's changes

finai-research CLAUDE.md is an instructions file published in the GitHub repository csmar432/finai-research (115 stars, last pushed yesterday), licensed MIT. It adds 5,979 tokens to every session, about $0.0299 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.

Related

Other instructions, from other repositories

next.js AGENTS.md

AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,153 tokens

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 6,785 tokens

vscode oss-third-party-notices.instructions.md

Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).

microsoft/vscode · 5,001 tokens

langchain AGENTS.md

AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.

langchain-ai/langchain · 4,469 tokens

deepseek-harness AGENTS.md

AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.

deepseek-ai/deepseek-harness · 3,735 tokens