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 risk-decomposegit 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/risk-decompose)<a href="https://agentmods.dev/skills/bluewatercorp/riskmodels_api/risk-decompose"><img src="https://agentmods.dev/badge/skills/bluewatercorp/riskmodels_api/risk-decompose.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 | $0.00093 | $0.00717 |
| Opus 5 | $0.00046 | $0.00358 |
| Sonnet 5 | $0.00019 | $0.00143 |
| Haiku 4.5 | $0.00009 | $0.00072 |
Grade A, and why
risk-decompose 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 3d 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 — 59 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Risk decomposition (ERM3 L1/L2/L3)
Decompose the risk of a single US equity into a nested cascade and report the ETF hedge ratios it implies. This skill is a thin wrapper over the hosted RiskModels MCP — it calls live tools and reports their outputs. It computes nothing itself.
What to call
Resolve the symbol first if the user gave a company name (riskmodels_search_tickers),
then:
riskmodels_get_hedge_levels— the L1/L2/L3 hedge snapshots side by side (hedge ratios + explained-risk fractions + the ETF legs at each depth). Best for "how does the decomposition deepen from market-only to subsector?"riskmodels_decompose— the L3 four-bet decomposition (market / sector / subsector / residual) for one name. Best for "what is driving this stock's risk?"get_metrics— the latest snapshot (hedge ratios, ER fractions, vol, close) when the user just wants the current numbers.
Fan out independent calls in one turn.
How to read the outputs
- Explained risk (
*_er) are variance fractions that sum to ~1.0 at L3 (l3_mkt_er + l3_sec_er + l3_sub_er + l3_res_er). Use these — not hedge-ratio signs — to say where variance lives. A high residual ER (>0.5) means much of the risk is stock-specific and not hedgeable with sector/market ETFs. - Hedge ratios (
*_hr) are model outputs: dollars of an ETF leg that mechanically neutralize $1 of a given layer of risk. Report them as math, e.g. "$0.62 of SPY per $1 of position neutralizes the market leg." - A negative L3 market hedge ratio is not "negative market exposure." At L2/L3 the
sector and subsector ETF legs already carry market beta; the SPY leg often offsets
beta embedded in those legs (orthogonalization), not a separate short-macro story.
Never infer market stance from the sign of
l3_market_hr— readl3_mkt_er.
Boundary
You are an analyst, not an investment adviser. Report the decomposition and what each hedge leg would mechanically neutralize; never recommend a trade, rebalance, or assess whether the position is suitable. Always call the tools before stating any number — never invent figures.
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.
- 3d ago First seen · 59 lines · 93 tokens per session scan A 67edfd87833a
risk-decompose is a skill published in the GitHub repository BlueWaterCorp/RiskModels_API (0 stars, last pushed 3d ago), licensed Apache-2.0. It adds 93 tokens to every session and 717 once invoked, about $0.0005 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 2026-09-04.
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 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.
vectorbt
High-performance vectorized backtesting with parameter optimization, portfolio simulation, and rich performance metrics.