finai-research: Instructions file for GitHub Copilot

.github/copilot-instructions.md

finai-research copilot-instructions.md is an instructions file for GitHub Copilot from csmar432/finai-research. It costs 2,745 tokens per session, scanned A, original, MIT.

Repository instructions for AI coding assistants working on a finance-research project. The project automates research tasks from reviewing papers and reports to preparing a paper for submission, using Python and data services.

In plain words
What is it for?
Starting and diagnosing the research system, asking for a research topic, coordinating its workflow, and explaining its project structure.
Why use it?
It gives coding assistants project context, startup checks, and rules for handling missing API keys or unavailable language models. This helps keep conversations and research runs consistent.

Instructions file for GitHub Copilot

Written for GitHub Copilot: a Copilot instructions file. Also seen: mentions Claude Code; mentions Codex.

This is csmar432/finai-research's own configuration. It tells GitHub Copilot 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 →

Needs its repository: it runs a file that does not travel with it, so clone the repository first. The line is ② 后台运行 python scripts/health_check.py --json.

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/.github/copilot-instructions.md
Clone the repo
git clone --depth 1 https://github.com/csmar432/finai-research

Made for: GitHub Copilot.

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 copilot-instructions.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/csmar432/finai-research/copilot-instructions.svg)](https://agentmods.dev/instructions/csmar432/finai-research/copilot-instructions)
Your own site
<a href="https://agentmods.dev/instructions/csmar432/finai-research/copilot-instructions"><img src="https://agentmods.dev/badge/instructions/csmar432/finai-research/copilot-instructions.svg" alt="Measured on agentmods" height="20"></a>
Per session 2,745 This file is loaded in full into every session.
When invoked 2,745 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 $0.02745 $0.02745
Opus 5 $0.01373 $0.01373
Sonnet 5 $0.00549 $0.00549
Haiku 4.5 $0.00275 $0.00275

Measured 8d ago against content hash eeb0479cb24d, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

finai-research copilot-instructions.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 8d 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.

.github/copilot-instructions.md · 267 lines

How it starts

The opening of the file, as written. The whole thing — 267 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Copilot Instructions for 论文-研报工作流

This file provides GitHub Copilot with project context and instructions. Place in .github/copilot-instructions.md at the repository root.

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

项目概述

论文-研报工作流 (FinResearch Agent) 是经济金融领域的 AI 研究助手,自动化从文献综述到可投稿论文的全流程。

  • 语言: Python 3.10+
  • 数据: MCP (Model Context Protocol) 服务器,{{MCP_COUNT}} 个数据源(见 scripts/count_mcp.py
  • 关键: 大部分数据源无需 API Key(世界银行、IMF、OECD 等免费数据)

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 后台运行 python scripts/health_check.py --json
        ↓
  ┌─ API Key 缺失 → 简短提示(不阻塞)
  ├─ LLM 不可用 → 询问是否继续
  └─ 系统就绪 → 等待研究方向
        ↓
③ 询问研究方向 → 用户描述 → 开始研究

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。

诊断交互(三平台统一)

  1. 运行诊断脚本,打印四类问题分类报告
  2. 读取 InteractionResult 结构
  3. 对话中向用户展示问题,等待回复
  4. 根据用户回复执行操作

API Key 缺失:AI 在对话中询问,用户回复后执行配置或继续 LLM 不可用:AI 在对话中展示问题 + 修复步骤,询问是否继续

Claude Code 和 Codex 不支持 input(),必须通过对话交互。


项目结构

scripts/
├── health_check.py           # 系统诊断(每次启动时运行)
├── setup_wizard.py          # 交互式配置向导
├── agent_pipeline.py        # 主编排器
├── research_framework/      # 研究执行层(30个模块)
│   ├── pipeline.py         # 研究执行
│   ├── modern_did.py       # 现代 DID
│   ├── regression_engine.py  # OLS/DID/PSM/IV/GMM
│   ├── fin_charts.py      # matplotlib 图表(≥300 DPI)
│   └── data_fetcher.py    # MCP 数据获取
├── core/                   # Agent 编排模块
├── research_directions/     # 研究方向(12个)
mcp_servers/               # `{{MCP_COUNT}}` 个 MCP 数据服务器
knowledge/skills/           # 17 个技能文档(真相源)

关键能力

数据获取(MCP)

数据类型 MCP 服务器 需要 Key
A股行情/财务 user-tushare TUSHARE_TOKEN
中国宏观 user-financial
美联储/FOMC user-fed-data
世界银行 user-wb-data
IMF user-imf-data
OECD user-oecd-data
国债收益率 user-eodhd EODHD_API_KEY
研报/新闻 user-eastmoney-reports
外汇/大宗 user-enhanced-finance
NBER Working Papers user-nber-wp

Read the full file on GitHub · 267 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. 8d ago First seen · 267 lines · 2,745 tokens per session scan A eeb0479cb24d

Subscribe to this mod's changes

finai-research copilot-instructions.md is an instructions file published in the GitHub repository csmar432/finai-research (114 stars, last pushed today), licensed MIT. It adds 2,745 tokens to every session, about $0.0137 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

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 · 5,182 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

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

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

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

spec-kit AGENTS.md

AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.

github/spec-kit · 7,104 tokens