Vibe Research is a local financial research workspace in which an AI agent gathers market data, performs multi-step analysis, and preserves reports, evidence, calculations, and research history. It is for investment research across Chinese, US, and Hong Kong stocks, including market reviews, company studies, portfolios, debates, and backtesting. The catalogue contains skills and an instruction for working with this research agent.
Borrowing it
Nothing to install: this file belongs to simonlin1212/Vibe-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.
curl -O https://raw.githubusercontent.com/simonlin1212/Vibe-Research/main/AGENTS.mdgit clone --depth 1 https://github.com/simonlin1212/Vibe-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/instructions/simonlin1212/vibe-research/agents-md)<a href="https://agentmods.dev/instructions/simonlin1212/vibe-research/agents-md"><img src="https://agentmods.dev/badge/instructions/simonlin1212/vibe-research/agents-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.
<a href="https://agentmods.dev/instructions/simonlin1212/vibe-research/agents-md"><img src="https://agentmods.dev/badge/instructions/simonlin1212/vibe-research/agents-md.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.04452 | $0.04452 |
| Opus 5.5 | $0.01781 | $0.01781 |
| Sonnet 5.5 | $0.00890 | $0.00890 |
| Haiku 4.5 | $0.00445 | $0.00445 |
Grade A, and why
Vibe-Research AGENTS.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.
Copies of this mod
1 near-identical copy found in the catalogue:
- Vibe-Research AGENTS.md — 91% identical, 0 lines differ
How it starts
The opening of the file, as written. The whole thing — 173 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Vibe-Research — 给 Agent 的部署与开发指南
你是来帮使用者部署、使用或改造本仓库的 Agent(Claude Code、Codex、WorkBuddy / CodeBuddy、Muse 一类个人云端 Agent……)。动手前先读完这一页。
研究方法论不在这里。研究线程的最高纪律是
methodology/constitution.md(研究宪法), 研究 SOP 在.agents/skills/,计算函数契约在calc/SPEC.md。产品在每个研究阶段把它们放进提示词,对所有大脑一视同仁; 它们约束的是研究线程里的大脑,不是你在本仓库里的工作方式。
1. 这是什么
本地运行的 A 股个股研究工作台:浏览器页面 + 本机服务 + 六阶段研究编排器 + Python 取数层 + 确定性计算库(calc/)。
研究的「大脑」可以换,换了以后受控工具、方法论、校验与合规 gate 都是同一套:
| 大脑 | 接法 | 登录与凭据 |
|---|---|---|
| Claude Code | 本机 claude CLI |
使用者本人在终端用 claude.ai 订阅登录(API key / Bedrock / Vertex 登录不算订阅);产品不读、不存、不复制登录文件 |
| Codex | 本机 codex CLI |
使用者本人在终端 codex login 用 ChatGPT 账号登录(Codex 里配的 API key 登录不认);同上 |
| WorkBuddy / CodeBuddy | 本机 codebuddy CLI(独立 CLI 或 WorkBuddy 桌面版内置) |
使用者本人在终端运行 codebuddy 登录独立 CLI(新版 WorkBuddy 桌面版的登录加密保存,产品借不到);同上 |
| 模型 API | 任意 Chat Completions 兼容接口(模板见 providers/) |
页面里填的 key 只存在浏览器 localStorage,随请求交给本机服务,不落盘;命令行研究从模板声明的环境变量读 key |
研究线程里的大脑没有 Shell、没有网络、没有任意文件读写,只有 5 个受控工具:列文件、读文件、确定性计算、写阶段产物、写报告。 取数由编排器在每个阶段开始前执行完;大脑想收工时,产品先做收工检查,产物缺失或校验不过就把问题清单交回去接着修。
2. 帮使用者部署
环境:Node.js ≥ 22.18、Python ≥ 3.11(推荐 3.12)、git。
git clone https://github.com/simonlin1212/Vibe-Research.git
cd Vibe-Research
scripts/setup # Windows:scripts\setup-windows.cmd
scripts/start # Windows:scripts\start.cmd
scripts/setup创建.venv、安装依赖、生成产品私有层.local/并跑体检;scripts/doctor可单独再跑(--json给机器读)。scripts/start同时拉起本机 API 与页面,健康检查通过后打开http://127.0.0.1:5930。 默认端口(页面 5930、API 8765)被占用或被系统保留时自动换空闲端口并在终端说明,以终端打印的地址为准; 换了页面端口时,浏览器里存的模型 API 设置和对话记录按地址分开,要在新地址重新设置(终端会提醒;默认端口空出来后重启就回到原来的); 要固定端口用--port/--api-port(Windows-Port/-ApiPort)或环境变量VRA_UI_PORT/VRA_API_PORT,指定的端口不能用时直接报错。 启动时提示「已经有一个 Vibe Research 在运行」:让使用者直接打开那个地址,不要终止别的进程去抢端口。- 页面打开后到左侧栏最下方的「接入 AI」选大脑并做一次真实对话测试,测试通过才会保存。
本机 CLI 要先由使用者本人登录(
claude/codex login/codebuddy);登录发生在使用者自己的终端和浏览器里,你不代填、不转存任何账号信息。 - Windows 上 WorkBuddy 装在别的盘也会从「已安装的程序」登记或正在运行的 WorkBuddy 里自动找到;
仍显示「未安装」时:先打开 WorkBuddy 再点「重新检测」,或在「接入 AI」的 WorkBuddy 卡片里填它的安装文件夹,
或在启动前设环境变量
CODEBUDDY_BIN/CLAUDE_BIN/CODEX_BIN(设了就只认它)。 - 所有私有数据(配置、运行产物、对话、台账、上传资料)都在
.local/,已被 git 忽略。不要把它提交、打包或发给任何第三方。 - 使用者不想装 Node / Python / git 时,让他到 Releases 下载免安装包(Windows x64 / Apple 芯片 / Intel Mac),解压后双击
Start-VibeResearch; 数据在包文件夹的.local/,升级 = 新版本解压到新文件夹再把.local/整个复制过去。包由.github/workflows/portable.yml构建 (本机构建:node scripts/portable/build.mts;冒烟:node scripts/portable/smoke.mts <解压出来的目录>), 包里 Node / Python 的版本、下载地址和 SHA256 只写在scripts/portable/runtimes.json,升级运行时只改这一个文件。 - 页面每天查一次 GitHub 最新正式版本(只带版本号;没查成隔一小时再试);设环境变量
VRA_UPDATE_CHECK=0完全不联网。
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.
- 8d ago Changed · +26 tokens per session 2dbbbb64f345
- 26d ago Changed · +6 lines · +302 tokens per session cb23f2d474b6
- 27d ago Changed · +11 lines · -698 tokens per session 327e92c301a5
- 1mo ago Changed · +2 lines · +102 tokens per session 6900edcfc570
- 1mo ago Changed · -1 lines · -22 tokens per session d285024abc81
- 2mo ago Changed · +7 lines · +273 tokens per session 5c9a049dc215
- 2mo ago First seen · 148 lines · 4,469 tokens per session scan A 3aa886e6e631
Vibe-Research AGENTS.md is an instructions file published in the GitHub repository simonlin1212/Vibe-Research (3,504 stars, last pushed 8d ago), licensed MIT. It adds 4,452 tokens to every session, about $0.0178 per session on Opus 5.5. 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.
Vibe-Research AGENTS.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| Vibe-Research AGENTS.mdsimonlin1212/Vibe-Research | Instructions file | 3.5k | 8d ago | MIT | A | 4,452 | Codex, OpenCode |
| vscode buildNext.instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 9,719 | GitHub Copilot |
| next.js AGENTS.mdvercel/next.js | Instructions file | 143k | today | MIT | A | 7,461 | Codex, OpenCode |
| vscode oss-third-party-notices.instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 5,516 | GitHub Copilot |
| langchain AGENTS.mdlangchain-ai/langchain | Instructions file | 149k | today | MIT | A | 4,680 | Codex, OpenCode |
| vscode copilot-instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 3,093 | GitHub Copilot |
| deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness | Instructions file | 274k | 2d ago | MIT | A | 4,313 | Codex, OpenCode |