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 ironyjk/strategy-frameworks --skill real-optionsgit clone --depth 1 https://github.com/ironyjk/strategy-frameworksWrote 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/ironyjk/strategy-frameworks/real-options)<a href="https://agentmods.dev/skills/ironyjk/strategy-frameworks/real-options"><img src="https://agentmods.dev/badge/skills/ironyjk/strategy-frameworks/real-options.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 5.1 | $0.00040 | $0.04580 |
| Opus 5 | $0.00020 | $0.02290 |
| Sonnet 5 | $0.00008 | $0.00916 |
| Haiku 4.5 | $0.00004 | $0.00458 |
Grade A, and why
real-options 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 7d 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 — 407 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Real Options Analysis (실물옵션 분석)
"In an uncertain world, the value of being able to change your mind is enormous."
1. Why NPV Alone Fails — The "Now or Never" Fallacy (전통 NPV의 한계)
Traditional Net Present Value (NPV) analysis assumes a binary, irreversible decision: invest now or never. This "now or never" framing systematically undervalues investments in uncertain environments because it:
- Ignores the value of waiting — new information arrives over time that can improve decisions
- Treats uncertainty as purely negative — higher discount rates penalize uncertain projects, when uncertainty can actually create upside
- Assumes passive management — managers are modeled as automatons who cannot adapt, pivot, or abandon
- Forces a single scenario — collapses a distribution of outcomes into one expected cash flow
The core insight: When you have the right but not the obligation to take future action, uncertainty increases value rather than destroying it. This is identical to how financial options work — a call option becomes more valuable as volatility rises.
NPV says: "This project has negative expected value. Don't invest." Real Options says: "This project has negative expected value if you commit fully today. But a small pilot investment buys you the option to expand if conditions improve — and that option has significant value."
2. Financial Options Analogy (금융옵션과의 유추)
Real options borrow directly from financial option theory:
| Financial Option | Real Option | Analogy |
|---|---|---|
| Stock price (S) | Present value of expected cash flows | What the underlying asset is worth today |
| Strike price (K) | Investment cost to exercise | What you must pay to proceed |
| Time to expiry (T) | Decision window duration | How long you can wait before deciding |
| Volatility (σ) | Uncertainty of cash flows | How much outcomes could vary |
| Risk-free rate (r) | Time value of money | Cost of deferral |
| Dividends | Lost cash flows from waiting | Revenue foregone by not acting now |
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.
- 7d ago First seen · 407 lines · 40 tokens per session scan A 8a8765ffca3a
real-options is a skill published in the GitHub repository ironyjk/strategy-frameworks (11 stars, last pushed 4mo ago), licensed MIT. It adds 40 tokens to every session and 4,580 once invoked, about $0.0002 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 skills, from other repositories
advisory-finance-accounting
Finance advisory panel featuring Warren Buffett (Berkshire), Christine Lagarde (ECB), James Mwangi (Equity Bank), Ho Ching (Temasek), Ray Dalio (Bridgewater), Lubna Olayan (Olayan Group), and Charlie Munger.
advisory-ma-corporate-development
M&A advisory panel featuring Bernard Arnault (LVMH), Mukesh Ambani (Reliance), Tony Elumelu (Heirs Holdings), Henry Kravis (KKR), Safra Catz (Oracle), and Patrice Motsepe (ARM).
advisory-real-estate-investing
Real Estate & Investing advisory panel featuring Sam Zell, Li Ka-shing, Folorunso Alakija, Zhang Xin, George Soros, Cathie Wood, and Masayoshi Son.
model
A business-modeling guide that creates a Lean Canvas, a one-page business plan, and a unit-economics workbook showing revenue, costs, customer value, and scenarios.
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.
strategy-pivot-designer
Detect backtest iteration stagnation and generate structurally different strategy pivot proposals when parameter tuning reaches a local optimum.