agentmods.dev

research

research is a command for Claude Code from csmar432/finai-research. It costs 0 tokens per session (335 once invoked), scanned A, original, MIT.

A command that starts an end-to-end economics and finance research workflow. It can take a topic from literature review through idea generation, study design, data work, analysis, paper writing, and review.

In plain words
What is it for?
Use it with a topic such as tariffs and innovation among export-focused Chinese companies, carbon trading and innovation, or ESG and financing costs. It supports literature searches, candidate ideas, methods such as difference-in-differences, instrumental variables, regression discontinuity, and matching, data retrieval, statistical analysis, LaTeX writing, and review.
Why use it?
It gathers the major stages of a research project into one process instead of requiring each stage to be started separately. This gives a topic a path from an initial question to a paper draft.

Command for Claude Code

Written for Claude Code: installed under .claude/.

Needs its repository: it runs a file that does not travel with it, so clone the repository first. The line is python scripts/agent.py --goal "<topic>".

not rated 109repo +1 3d ago A scan 0 tokens original MIT

Good fit Use it with a topic such as tariffs and innovation among export-focused Chinese companies, carbon trading and innovation, or ESG and financing costs. It supports literature searches, candidate ideas, methods such as difference-in-differences, instrumental variables, regression discontinuity, and matching, data retrieval, statistical analysis, LaTeX writing, and review.

Compare 6 commands from other repositories ↓
View source ↗ csmar432/finai-research csmar432.github.io
Install

Getting it into your agent

It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.

Clone the repo
git clone --depth 1 https://github.com/csmar432/finai-research
agentmods
npx agentmods add commands/csmar432/finai-research/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 research

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

Your own site · 80×15
<a href="https://agentmods.dev/commands/csmar432/finai-research/research"><img src="https://agentmods.dev/badge/commands/csmar432/finai-research/research.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 335 The whole file, excluding the scripts and references it only reads on demand.
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 $0.00000 $0.00335
Opus 5.5 $0.00000 $0.00134
Sonnet 5.5 $0.00000 $0.00067
Haiku 4.5 $0.00000 $0.00034

Measured 2mo ago against content hash 76acf88d9fed, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

research 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 2mo 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.

.claude/commands/research.md · 48 lines

What it actually says

research — 启动完整研究流程

description: 启动经济金融领域的完整研究流水线（从文献综述到论文草稿）

arguments

  • <topic>: 研究主题（中文或英文均可）

描述

启动论文-研报工作流的完整端到端研究流程。

等价于：

python scripts/agent.py --goal "<topic>"

或直接用 AI Agent 自然语言交互：

"帮我研究 [你的研究方向]，发表在经济研究"

示例

/research 关税政策对A股出口型企业创新的影响
/research carbon trading innovation Chinese A-shares
/research ESG and cost of capital

工作流程

  1. 文献综述 — arXiv / NBER / OpenAlex 搜索
  2. 研究想法生成 — 8-12 个候选想法，数据验证
  3. 实证设计 — DID / IV / RDD / PSM 识别策略
  4. 数据获取 — {{MCP_COUNT}} 个 MCP 服务器自动拉取
  5. 回归分析 — 38+ 种计量方法
  6. 论文写作 — LaTeX 输出（JF / JFE / RFS / 经济研究）
  7. 对抗性 review — 多轮迭代直到发表标准

环境要求

  • Python 3.10+
  • 大部分 MCP 服务器无需 API Key
  • LaTeX（xelatex，用于中文期刊）
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. 2mo ago First seen · 48 lines · 0 tokens per session scan A 76acf88d9fed

Subscribe to this mod's changes

research is a command published in the GitHub repository csmar432/finai-research (109 stars, last pushed 3d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 335 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 2026-08-30.

Finance and fintechResearchacademic-researchcausal-inferencediddifference-in-differenceseconometrics
Related

research compared with commands from other repositories

research next to 6 commands from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
researchcsmar432/finai-researchCommand1093d agoMITA0Claude Code
valuation-methodsagentii-ai/agentii-investment-intelligenceCommand21011d agoApache-2.0A17Claude Code
synthesise-reviewsflonat/flonat-researchCommand1493d agoMITA47Claude Code
scanprajapatimehul/claude-aws-cost-saverCommand244mo agoMITA6Claude Code
archive-ledgerArieGoldkin/claude-forgeCommand73mo agoMITA0Claude Code
dcfyuping322/financial-services-plugins-newCommand188mo agoApache-2.0A11Claude Code
checklistgithub/spec-kitCommand148kyesterdayMITA13Claude Code