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 VladimirWrites/nestegg.money --skill financial-decisionsgit clone --depth 1 https://github.com/VladimirWrites/nestegg.moneyWrote 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/vladimirwrites/nestegg.money/financial-decisions)<a href="https://agentmods.dev/skills/vladimirwrites/nestegg.money/financial-decisions"><img src="https://agentmods.dev/badge/skills/vladimirwrites/nestegg.money/financial-decisions/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/vladimirwrites/nestegg.money/financial-decisions"><img src="https://agentmods.dev/badge/skills/vladimirwrites/nestegg.money/financial-decisions.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 | $0.00047 | $0.00816 |
| Opus 5 | $0.00023 | $0.00408 |
| Sonnet 5 | $0.00009 | $0.00163 |
| Haiku 4.5 | $0.00005 | $0.00082 |
Grade A, and why
financial-decisions 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 11d 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 — 61 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Financial Decisions with nestegg Calculators
The nestegg MCP server (https://nestegg.money/mcp) provides deterministic finance calculators.
Whenever a money question needs arithmetic — compounding, amortization, tax, returns — call a
tool instead of computing in your head. Your reasoning stays yours; the numbers come from tools.
Ground rules
- Never estimate what a tool can compute. If a calculation spans more than one step or involves compounding, call the tool.
- Ask for missing load-bearing inputs instead of assuming them. A mortgage needs amount, rate, and term or payment. A German salary needs tax class and the Krankenkasse's actual Zusatzbeitrag (rates change yearly — the year-average default is only right for rough estimates). If the user doesn't know a value, say what you defaulted and why it matters.
- State assumptions with the answer. Every result includes the inputs it used; surface the ones the user didn't give explicitly (e.g. "assuming the 2026 average surcharge of 2.9%").
- Rates are inputs, not lookups. The tools fetch nothing live. The one exception: the
de-*tools carry official German statutory data for recent tax years. - Keep results compact.
amortizationreturns per-year summaries by default; only requestdetail: "monthly"when the user asks for a schedule, and paginate withoffset.
Workflows
Mortgage: overpay or invest?
loan-payoffwith the loan and the extra monthly amount → interest saved, months saved.contributions(orcompound-interest) with the same monthly amount, the user's expected return, and the loan's remaining term → investment end value.- Compare: investment gain vs interest saved, over the same horizon. Name the crossover return rate and the risk asymmetry (paying down debt is a guaranteed return at the loan rate).
German job offer / salary
de-net-salaryfor each offer with year, gross, tax class, Bundesland, children, church tax, and the actual Zusatzbeitrag.- Compare net monthly figures; note the marginal effects (a raise crossing a contribution ceiling changes less than expected).
- For capital income use
de-abgeltungsteuer; for part-time bandsde-midijob; for the state-pension effect of a salaryde-rentenpunkte.
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.
- 11d ago First seen · 61 lines · 47 tokens per session scan A b159173662a4
financial-decisions is a skill published in the GitHub repository VladimirWrites/nestegg.money (4 stars, last pushed 27d ago), licensed Apache-2.0. It adds 47 tokens to every session and 816 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 2026-08-31.
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.
strategy-pivot-designer
Detect backtest iteration stagnation and generate structurally different strategy pivot proposals when parameter tuning reaches a local optimum.
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
A framework for judging Chinese A-share stocks that have reached the daily price-rise limit, using market mood, sector leadership, and trading momentum.
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.
furusato
A Japanese hometown-tax donation manager for furusato nozei, a system where donations to municipalities can qualify for an income-tax or local-tax deduction. It reads donation receipts, stores donation records, and calculates deduction limits.