Borrowing it
Nothing to install: this file belongs to Veblin/invest-skills. 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/Veblin/invest-skills/main/AGENTS.mdgit clone --depth 1 https://github.com/Veblin/invest-skillsWrote 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/veblin/invest-skills/agents-md)<a href="https://agentmods.dev/instructions/veblin/invest-skills/agents-md"><img src="https://agentmods.dev/badge/instructions/veblin/invest-skills/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/veblin/invest-skills/agents-md"><img src="https://agentmods.dev/badge/instructions/veblin/invest-skills/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 | $0.02350 | $0.02350 |
| Opus 5 | $0.01175 | $0.01175 |
| Sonnet 5 | $0.00470 | $0.00470 |
| Haiku 4.5 | $0.00235 | $0.00235 |
Grade A, and why
invest-skills 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 5d 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 — 194 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md — AI 协作规则
本文档定义 AI Agent 在本项目中的行为边界、设计哲学和质量标准。 所有贡献者(人类和 AI)都应遵守这些规则。
五条硬约束
约束 1:禁止荐股
不输出任何形式的"买入/卖出/持有"建议、仓位建议。允许多情景估值参考价,但必须标注假设前提、概率权重,并明确"仅供参考,不构成投资建议";不允许无假设前提的单一目标价数字。这是法律红线,也是能力边界——LLM 没有资格做投资建议。
约束 2:LLM 不可作为投资决策的主要信源
LLM 存在幻觉问题——在专业金融领域,这些幻觉极难被非专业人士识别。AI 的输出只能作为"学习材料的整理和解读",不能作为"投资决策的依据"。关键财务数据必须标注原始来源(财报 PDF / akshare / Tushare),让用户有能力追溯验证。
约束 3:所有分析解释必须依赖数据源,引用来源
这是本 Skill 最核心的质量标准。LLM 生成的分析性文本(趋势解读、行业判断、估值讨论)必须建立在可追溯的数据源之上,而非 LLM 的"知识记忆"。标准对标学术论文:每个论述要么标注数据来源,要么明确声明为"待验证的推测"。没有数据支撑的分析不输出。
约束 4:项目文档不提供社交功能入口
不建群、不设讨论区、不做用户间互动。项目是个人学习工具,开源分享。
约束 5:先服务于自己的学习需求,但以可分发标准设计
项目源于作者自身的 A 股/港股投资学习实践。功能迭代以解决自己遇到的真问题为导向,不追求覆盖所有假想需求。同时,项目按 Agent Skills 开放格式构建,面向 Claude Code / Hermes / WorkBuddy 等多平台分发——配置步骤须有文档、数据源须有 fallback、关键路径须在无 Python 环境(MCP 模式)下同样可用。WorkBuddy 分发通道(3 步安装 / token 配置 / 用户级 AGENTS 与 MEMORY 模板 / 真机验收表)见 docs/workbuddy/ 与 README「WorkBuddy 安装」节。
目标用户画像
用户画像:能够在 Claude Code 或 Hermes 中安装并使用 Skills 的用户,普遍具备较强的信息获取和自主判断能力——学习能力强、能自行验证信息、不会被营销话术左右。
这意味着:
- 不需要"简单化":可以用专业术语,可以展示复杂逻辑
- 需要"可验证":每个结论都要追溯到数据源头,让用户独立判断
- 需要"方法论":用户要的是分析框架和思考工具,不是结论
- 不存在商业变现动机:项目是开源学习工具,没有"流量变现"/"知识付费"等商业逻辑
设计哲学
用户能力模型:
不是"需要被告知该做什么的小白"
而是"想要理解事情如何运作的聪明人"
产品逻辑:
不是"信任我,我帮你判断"
而是"这是数据,这是分析方法,这是不确定性,你自己判断"
迭代逻辑:
不是"用户想要什么功能"
而是"我在投资学习中遇到了什么问题,需要一个工具来解决"
技术指标规范
MA5/MA10/MA20/MA60 和 MACD(DIF/DEA)等指标仅用于理解市场状态,不用于生成交易信号:
- ✅ 描述当前价格与均线的位置关系(如"价格位于 MA60 上方""MA20 走平")
- ✅ 描述 MACD 的 DIF/DEA 位置和方向(如"DIF 在零轴上方""DIF 向下靠近 DEA")
- ✅ 结合均线和 MACD 理解"市场参与者的共识趋势"
- ❌ 输出"金叉买入""死叉卖出""MACD 底背离抄底"等交易信号
- ❌ 基于技术指标给出任何操作建议
数据源分层(A股/港股 + 全球宏观)
A 股数据源(优先级)
有 Token: Tushare ∥ akshare → 腾讯行情 → 标注不可得
无 Token: akshare → 腾讯行情 → 标注不可得
- Tushare 与 akshare 并列并行(先到先用),非前置拦截器
- Tushare Token 无效时静默跳过,不影响主 fallback 链
- TickFlow ✅ 已接入(v0.1.6)— 免费免注册独立 K 线数据源,提供第四源交叉验证
港股数据源(优先级)
akshare(东方财富港股频道)→ 标注不可得
yfinance(.HK 后缀)计划在未来版本接入。
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.
- 5d ago First seen · 194 lines · 2,350 tokens per session scan A 5d1c7ad31e23
invest-skills AGENTS.md is an instructions file published in the GitHub repository Veblin/invest-skills (14 stars, last pushed 2d ago), licensed MIT. It adds 2,350 tokens to every session, about $0.0118 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 2026-09-04.
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.
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.
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).
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).
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.
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.