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 skills add surplus96/pm-mcp --skill pm-mcp-directorgit clone --depth 1 https://github.com/surplus96/pm-mcpWrote 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/skills/surplus96/pm-mcp/pm-mcp-director)<a href="https://agentmods.dev/skills/surplus96/pm-mcp/pm-mcp-director"><img src="https://agentmods.dev/badge/skills/surplus96/pm-mcp/pm-mcp-director/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/skills/surplus96/pm-mcp/pm-mcp-director"><img src="https://agentmods.dev/badge/skills/surplus96/pm-mcp/pm-mcp-director.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 | $0.00232 | $0.02642 |
| Opus 5.5 | $0.00093 | $0.01057 |
| Sonnet 5.5 | $0.00046 | $0.00528 |
| Haiku 4.5 | $0.00023 | $0.00264 |
Grade A, and why
pm-mcp-director 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 13d 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 — 102 lines — stays where its author put it; the contents beside it link to each section on GitHub.
pm-mcp 워크플로우 디렉터
pm-mcp는 시장 데이터·기술적/재무/감성 분석·랭킹·백테스트·차트·리포트를 제공하는 포트폴리오 매니저 MCP 서버다(도구 25개, v2). 이 스킬은 사용자의 자연어 요청을 적절한 도구 시퀀스로 변환하는 방법을 안내한다.
전체 도구와 파라미터는 references/tool-catalog.md를 참조한다. 아래는 의도별 표준 워크플로우다.
핵심 원칙
- 의도를 먼저 분류한다. 단일 종목 분석인지, 다종목 비교인지, 포트폴리오 점검인지, 테마 발굴인지에 따라 시작 도구가 다르다.
- 종합 도구를 우선 사용한다.
stock_snapshot,stock_factors,portfolio_analyze(aspect="comprehensive")가 기본이다. 특정 지표만 물으면stock_factors(sections=[...])처럼 범위를 좁힌다. - 시장 컨텍스트를 곁들인다. 매수/매도 판단이 걸린 요청이면
market_overview를 함께 호출해 강세/약세/횡보 맥락을 답변에 반영한다. - 오류는 그대로 전달된다. 도구 실패는
isError와 사유 메시지로 돌아온다. 사유를 사용자에게 알리고 대체 경로를 시도한다. - 투자 조언 면책. 결과는 항상 정보 제공 목적임을 밝히고, 최종 판단은 사용자 몫임을 답변 말미에 짧게 명시한다.
입력 형식 규칙
- 티커: 미국 주식은 심볼(AAPL), 한국 주식은 종목코드(005930) +
market="KR". - tickers: 문자열 배열
["AAPL", "MSFT", "NVDA"]. - holdings_text (
portfolio_analyze,portfolio_store,chart):"TICKER:SHARES@ENTRY_PRICE, ..."예:"AAPL:10@150, MSFT:5@400". 현금은cash. - 자연어 보유주 (
portfolio_quick_check):"AAPL@2024-10-01:185, LLY 2024-09-15 520, NVO"처럼 느슨한 형식 허용.
의도별 워크플로우
1. 단일 종목 분석 — "AAPL 어때?", "삼성전자 분석해줘"
stock_snapshot(ticker, include_signal=True)— 가격/변동성 + 밸류에이션·수익성·성장성 + 애널리스트 + 뉴스 감성 + 기술적 신호 + Buy/Hold/Sell 신호. 단일 종목의 기본 선택(US/KR).stock_factors(ticker, market)— 기술(10)·재무(20)·감성(10) 팩터와 섹션 점수, 종합 점수·추천 등급. 한국 주식은market="KR".- 시각화 요청 시
chart(kind="dashboard", ticker)(캔들+기술지표+수익률분포+상대강도).
기술적 지표만 빠르게: stock_factors(ticker, sections=["technical"]).
2. 다종목 비교/랭킹 — "이 중에 뭐가 제일 나아?"
- 2~5개 간단 비교:
stock_compare(tickers) - 팩터 기반 랭킹:
stock_rank(tickers, method="factor", market)— 종합점수·추천 등급 - 섹터 가중치·시장 국면 반영:
stock_rank(tickers, method="advanced") - 펀더멘털 + 낙폭 보너스:
stock_rank(tickers, method="fundamental") - 차트 비교:
chart(kind="comparison", tickers, normalize=True)
3. 테마 발굴 → 종목 선정 — "요즘 뜨는 테마 뭐야?"
theme_propose(lookback_days, max_themes)— 뉴스 기반 테마 추천- 사용자가 테마를 고르면
theme_explore(theme)— 대표 종목 후보 + 개요 theme_analyze(theme, market, top_n)— 팩터 점수로 상위 종목 선정(선택:include_backtest=True)- 리포트:
report_create(kind="theme", theme, tickers)또는kind="theme_overview"(with_images 가능), 선택 종목 요약은kind="selection"
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 13d ago First seen · 102 lines · 232 tokens per session scan A 9b4b2a701676
pm-mcp-director is a skill published in the GitHub repository surplus96/pm-mcp (1 stars, last pushed 14d ago), licensed MIT. It adds 232 tokens to every session and 2,642 once invoked, about $0.0009 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 2026-09-29.
Other skills, from other repositories
sector-rotation
An analysis framework for comparing industries in the Chinese A-share stock market, using business conditions, price momentum, valuation, and money flows. It produces rankings and higher- or lower-allocation suggestions.
twitter-reader
Read Twitter/X for financial research through opencli: the user's home timeline, tweet search, trending topics, bookmarks, a user's recent tweets, threads, articles, profiles, followers and following, and notifications. Use this skill whenever the user wants to know what people are saying on Twitter/X or fintwit about…
strategy-pivot-designer
Detect backtest iteration stagnation and generate structurally different strategy pivot proposals when parameter tuning reaches a local optimum.
energy-procurement
Codified expertise for electricity and gas procurement, tariff optimization, demand charge management, renewable PPA evaluation, and multi-facility energy cost management. Informed by energy procurement managers with 15+ years experience at large commercial and industrial consumers. Includes market structure analysis…
china-portfolio-monitoring
A monitoring framework for tracking the financial results, operating measures, strategic milestones, and risks of companies held by China-focused private-equity funds. It uses measures such as revenue growth, margins, debt, cash flow, and return on equity.
chenhao-limit-up
A framework for judging Chinese A-share stocks that have reached the daily price-rise limit, using market mood, sector leadership, and trading momentum.