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 skills/openminis/minisskills/reverse-dcfnpx skills add OpenMinis/MinisSkills --skill reverse-dcfgit clone --depth 1 https://github.com/OpenMinis/MinisSkillsWrote 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/openminis/minisskills/reverse-dcf)<a href="https://agentmods.dev/skills/openminis/minisskills/reverse-dcf"><img src="https://agentmods.dev/badge/skills/openminis/minisskills/reverse-dcf.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 | $0.00158 | $0.02650 |
| Opus 5 | $0.00079 | $0.01325 |
| Sonnet 5 | $0.00032 | $0.00530 |
| Haiku 4.5 | $0.00016 | $0.00265 |
Grade A, and why
reverse-dcf 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 — 215 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Reverse DCF: Deriving Market-Implied Expectations
Core Idea
Forward DCF: given assumptions, calculate a target price. The parameters can be adjusted arbitrarily and end up "serving the conclusion."
Reverse DCF: given the market price, back-solve the implied growth rate and translate "expensive" or "cheap" into a verifiable proposition.
The essential difference:
- Forward DCF outputs "fair value." It is abstract, and you can always be right, but your wallet will not get any thicker.
- Reverse DCF outputs "market expectations": specific, verifiable numbers that can be compared with reality.
Applicability
Necessary condition: base-year FCFF must be positive.
Applying a standard two-stage DCF to companies with negative FCFF, such as early-stage high-growth companies or companies in an asset-heavy expansion phase, produces meaningless results.
Alternative: use PS-implied revenue back-solving (see "Handling Special Cases" below).
Data requirements:
- Latest complete annual report (income statement, balance sheet, and cash flow statement)
- Current stock price/market capitalization
- Details of interest-bearing debt (short-term borrowings, long-term borrowings, lease liabilities, etc.)
- Risk-free rate (10-year government bond yield)
- Industry β and ERP (Damodaran data recommended)
Practical Steps
Step 1: Determine Enterprise Value (EV)
EV = Market Capitalization + Net Debt
Net Debt = Interest-Bearing Debt - Cash and Cash Equivalents - Financial Assets Held for Trading
Notes:
- For companies like SK Hynix that are in a "net cash" position (cash > interest-bearing debt), EV will be lower than market capitalization.
- For A-share companies, check whether financial assets held for trading include wealth management products, which are treated as cash equivalents.
- STAR Market companies often have large amounts of IPO or financing proceeds sitting on the balance sheet, so EV may be far lower than market capitalization.
Step 2: Calculate Base-Year FCFF (the core step and the easiest place to make mistakes)
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 · 215 lines · 158 tokens per session scan A b22b7a8e6402
reverse-dcf is a skill published in the GitHub repository OpenMinis/MinisSkills (396 stars, last pushed 15d ago), licensed MIT. It adds 158 tokens to every session and 2,650 once invoked, about $0.0008 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
convex-add
Add a capability to the CURRENT Convex app — consults the served Convex capability catalog for always-current procedures (billing, crons, auth, agent, search, …); falls back to built-in hosting or @convex-dev component search. TRIGGER when the user runs /add, or asks to add hosting/publishing or any backend capability…
twitter-reader
Read Twitter/X for financial research using opencli (read-only). Use this skill whenever the user wants to read their Twitter feed, search for financial tweets, view bookmarks, look up user profiles, or gather market sentiment from Twitter/X. Triggers include: "check my feed", "search Twitter for", "show my…
chenhao-limit-up
Use when evaluating A-share limit-up (涨停板) setups through Chen Hao's sentiment and momentum lens: market emotion cycles, board strength, follow-through, and short-term aggressive momentum trading.
trading-risk-gate
Unified pre-trade safety gate: Ruin check (Law #1), ergodicity audit, and win-rate dominance validation. Absorbs: ergodicity-check, law-of-ruin, win-rate-dominance.
cwv-optimizer
Diagnose and fix Core Web Vitals issues on AEM Edge Delivery Services pages. Goes deeper than generic CWV advice by understanding EDS-specific performance patterns including the 100KB LCP budget, E-L-D loading phases, block rendering behavior, and third-party script impact. Produces specific fixes for LCP, CLS, and…
multi-expert-analyzer
针对通用问题进行多领域专家联合分析, 综合稿产生前必经 fact-checker 与 red-team 两道独立校验。适用场景: 用户提出跨领域或不确定领域的复杂问题, 需要从多个专家角度分别搜证并相互校验后综合成文, 例如该不该买房、该不该跳槽、是否进入某个赛道等。触发关键词: 多角度分析、专家分析、综合分析、多视角、跨领域分析、从不同角度看、深度分析。问题只属于单一明确领域时, 优先使用该领域的专门 skill, 例如纯财务用 finance-core-analysis、纯技术用 software-architect。输出 (全部 markdown 保存到当前项目 markdown/ 目录): (1) 每位专家的中间分析稿…