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 BlueWaterCorp/RiskModels_API --skill cost-of-capitalgit clone --depth 1 https://github.com/BlueWaterCorp/RiskModels_APIWrote 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/bluewatercorp/riskmodels_api/cost-of-capital)<a href="https://agentmods.dev/skills/bluewatercorp/riskmodels_api/cost-of-capital"><img src="https://agentmods.dev/badge/skills/bluewatercorp/riskmodels_api/cost-of-capital/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/bluewatercorp/riskmodels_api/cost-of-capital"><img src="https://agentmods.dev/badge/skills/bluewatercorp/riskmodels_api/cost-of-capital.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 | $0.00095 | $0.00958 |
| Opus 5.5 | $0.00038 | $0.00383 |
| Sonnet 5.5 | $0.00019 | $0.00192 |
| Haiku 4.5 | $0.00010 | $0.00096 |
Grade A, and why
cost-of-capital 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 26d 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 — 67 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Cost of capital (CAPM mode)
Report a name's cost of capital from its PIT fundamentals. Cost of equity is CAPM: risk-free rate at the chosen tenor plus the reported valuation beta times the equity-risk-premium request assumption. WACC uses book-value weights. This skill wraps the hosted RiskModels MCP and reports its outputs — it computes nothing itself.
What to call
riskmodels_get_fundamentals— the cost-of-capital layer rides on this tool. Relevant params:erp— the equity risk premium request assumption. If the user did not give one, ask for it or report across the grid; state the ERP used in every answer.rf_tenor— Treasury constant-maturity tenor for the risk-free rate (3m|1y|2y|5y|10y|30y, default10y, the long-duration valuation convention).tax_rate— applied to the WACC debt shield (default 0.21).grid=truewitherp_grid/rf_tenor_grid— returns the sensitivity table ofcost_of_equity, strictwacc, parallelwacc_imputed, andeconomic_profitacross every ERP × tenor cell, instead of a single scalar. Prefer the grid when the user has not fixed an ERP.
Reading the response
cost_of_equity=rf_rate+beta_market×erp(CAPM). Because the valuation beta can be low or negative for defensive names,cost_of_equitycan fall below the risk-free rate — state it plainly rather than "correcting" it.cost_of_debt/waccare strict reported-data fields. If positive trusted SEC debt lacks usable TTM interest expense, both remain null — never read null as 0%.cost_of_debt_imputed/wacc_imputedare separate proxy fields. Use them only whencost_of_debt_imputation.status == "used", label them PIT-lagged high-quality-market proxy, and report the provenance. The stored spread is monthlyHQMCB10YR - GS10, then added to the separate period-end 10-year Treasury rate. The reference month becomes eligible on day 10 of the following month. It covers the A/AA/AAA high-quality market; it is not an issuer rating or issuer bond yield.- Both WACC fields use book-value weights (balance-sheet equity and debt). The textbook convention is market-value weights; say so, and note the user can reweight if they have market caps.
economic_profitscales with book equity; pair it withroe_ttm − cost_of_equity(the equity-charge spread). It is not NOPAT minus WACC times invested capital.- A short
rf_tenor(3m/1y) should be paired with a bill-basis ERP, or cost of capital is understated. Surface the tenor you used.
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.
- 26d ago Changed · +7 lines · +12 tokens per session f409078692e4
- 2mo ago First seen · 60 lines · 83 tokens per session scan A e9cdc3f9082f
cost-of-capital is a skill published in the GitHub repository BlueWaterCorp/RiskModels_API (0 stars, last pushed yesterday), licensed Apache-2.0. It adds 95 tokens to every session and 958 once invoked, about $0.0004 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 2026-09-04.
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 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…
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…
airdrop-hunting-guide
Guide to finding and qualifying for crypto airdrops — eligibility criteria, farming strategies, on-chain activity requirements, Sybil detection avoidance, and tracking tools. Use when helping users understand airdrops, check eligibility, or plan participation strategies.
recipe-daily-pnl-report
Generate a daily profit and loss summary from trades and balances.