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.
/plugin marketplace add yennanliu/InvestSkillnpx agentmods add plugins/yennanliu/investskill/us-stock-analysisgit clone --depth 1 https://github.com/yennanliu/InvestSkillGrade A, and why
us-stock-analysis 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 3d 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.
What it actually says
{
"name": "us-stock-analysis",
"description": "Comprehensive US stock evaluation with fundamental, technical, economic, valuation, financial report, and position-management analysis — 26 analysis frameworks",
"version": "1.11.0",
"author": {
"name": "yennanliu"
},
"homepage": "https://github.com/yennanliu/InvestSkill",
"license": "MIT",
"keywords": [
"stock",
"investment",
"analysis",
"us-markets",
"finance",
"technical-analysis",
"fundamental-analysis",
"visualization",
"reports",
"insider-trading",
"institutional-ownership",
"earnings-calls",
"dcf",
"options",
"dividends",
"short-interest",
"competitive-analysis",
"moat",
"research",
"financial-reports",
"10-k",
"10-q",
"valuation",
"comparable-company",
"position-sizing",
"cost-basis"
]
}
What it installs
The manifest is a name and a version. 27 skills travel with it, and installing the plugin installs all of them — 504 tokens a session between them. Each is measured on its own page, and each can be installed alone.
- Skill dividend-analysis A 21 tokens
- Skill position-ladder A 44 tokens
- Skill report-generator A 11 tokens
- Skill stock-eval A 9 tokens
- Skill stock-valuation A 19 tokens
- Skill technical-analysis A 9 tokens
- Skill chart-master A 36 tokens
- Skill competitor-analysis A 12 tokens
- Skill financial-report-analyst A 20 tokens
- Skill institutional-ownership A 15 tokens
- Skill options-analysis A 13 tokens
- Skill sector-analysis A 8 tokens
- Skill catalyst-calendar A 18 tokens
- Skill economics-analysis A 9 tokens
- Skill industry-map A 36 tokens
- Skill insider-trading A 14 tokens
- Skill portfolio-review A 8 tokens
- Skill short-interest A 12 tokens
- Skill 10k-digest A 34 tokens
- Skill bear-case A 33 tokens
- Skill earnings-call-analysis A 13 tokens
- Skill full-report A 23 tokens
- Skill stock-screener A 18 tokens
- Skill result-validator A 16 tokens
- Skill research-bundle A 31 tokens
- Skill dcf-valuation A 13 tokens
- Skill fundamental-analysis A 9 tokens
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.
- 3d ago First seen · 39 lines scan A fcd2b5d69605
us-stock-analysis is a plugin published in the GitHub repository yennanliu/InvestSkill (196 stars, last pushed 3d ago), licensed MIT. Its token cost is not measured: this kind of file is read by the harness, not the model. 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 plugins, from other repositories
ctx
Docs lookup server.
korean-dart-marketplace
Plugin marketplace listing 1 plugin: korean-dart.
octagon-mcp-server
Skills-first Claude Code plugin for Octagon market intelligence, prediction market research, and financial analysis workflows.
cobrew
Workflow skills and shared instructions for coding agents.
humanizer
Rewrite AI-sounding text so it reads naturally without changing what it says.
nextjs
Official Next.js skills: adopt and optimize Cache Components, adopt Partial Prefetching, and verify runtime behavior against a running dev server.