Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add rules/yennanliu/investskill/invest-skillgit clone --depth 1 https://github.com/yennanliu/InvestSkillWrote 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/rules/yennanliu/investskill/invest-skill)<a href="https://agentmods.dev/rules/yennanliu/investskill/invest-skill"><img src="https://agentmods.dev/badge/rules/yennanliu/investskill/invest-skill.svg" alt="Measured on agentmods" 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 | $0.03865 | $0.03865 |
| Opus 5 | $0.01932 | $0.01932 |
| Sonnet 5 | $0.00773 | $0.00773 |
| Haiku 4.5 | $0.00386 | $0.00386 |
Grade A, and why
invest-skill 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 4d 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 — 553 lines — stays where its author put it; the contents beside it link to each section on GitHub.
InvestSkill — Cursor Rules & Setup Guide
This is the InvestSkill repository — a collection of 26 professional investment analysis frameworks for US stocks. These rules automatically apply when you work in this project.
Installation & Setup
Automatic Setup
Cursor automatically loads this file when you open the InvestSkill repository. No manual installation required.
-
Clone the repository:
git clone https://github.com/yennanliu/InvestSkill.git -
Open in Cursor:
cd InvestSkill cursor . -
Open AI Chat (usually
Cmd+K)- Cursor automatically loads the investment analysis rules
- All 26 frameworks are immediately available
Verify Setup
In Cursor AI Chat, try:
@prompts/stock-valuation.md Analyze Apple (AAPL)
If the framework loads, setup is complete!
Available Analysis Frameworks (26 frameworks + 1 output tool)
Core Stock Analysis (6 frameworks)
| Framework | File | Best For |
|---|---|---|
| Stock Evaluation | @prompts/stock-eval.md |
Piotroski scoring, quality metrics |
| Stock Valuation | @prompts/stock-valuation.md |
DCF + comparable companies + EV multiples |
| Fundamental Analysis | @prompts/fundamental-analysis.md |
Financial statement deep dive |
| Technical Analysis | @prompts/technical-analysis.md |
Chart patterns, volume, indicators |
| DCF Valuation | @prompts/dcf-valuation.md |
Intrinsic value modeling |
| Economics Analysis | @prompts/economics-analysis.md |
Macro indicators, recession probability |
Financial Report Analysis (3 frameworks)
| Framework | File | Best For |
|---|---|---|
| Financial Report Analyst | @prompts/financial-report-analyst.md |
10-K, 10-Q, annual reports |
| 10-K Report Digest | @prompts/10k-digest.md |
Structured digest doc — abstract, section summaries, metrics, refs (EN/繁中) |
| Earnings Call Analysis | @prompts/earnings-call-analysis.md |
Management tone, guidance, themes |
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.
- 4d ago First seen · 553 lines · 3,865 tokens per session scan A 6cfce475df47
invest-skill is a cursor rule published in the GitHub repository yennanliu/InvestSkill (198 stars, last pushed yesterday), licensed MIT. It adds 3,865 tokens to every session, about $0.0193 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.
Other cursor rules, from other repositories
workflow
BDD-style workflow, UI screenshots in the PR, HTTP OpenAPI and config schema sync before lint, final checks.
code-style
Formatting, lint, comments language.
instruct-ut
基于用户的目标，生产 todo list 并按顺序执行.
performance-optimization
@rule 性能优化规范 @description 前端应用性能优化的完整指南和最佳实践 @priority high @category performance.
shadcn-tailwind-guide
本规范定义了使用 shadcn/ui 和 Tailwind CSS 开发新组件的标准流程和最佳实践。.
spec-for-ut
Unit testing is essential to ensure the reliability and stability of code, especially for React components and functions. Adhering to best practices and ensuring high test coverage is critical to maintaining a robust codebase.