risk-decompose

risk-decompose is a skill for Claude Code from BlueWaterCorp/RiskModels_API. It costs 93 tokens per session (717 once invoked), scanned A, original, Apache-2.0.

A tool for breaking down a US stock’s risk into market, sector, subsector, and stock-specific parts, using related ETFs as comparison or hedge instruments.

In plain words
What is it for?
Use it to investigate a stock’s risk sources, measure how much is stock-specific, and review the ETF hedge ratios implied by each level.
Why use it?
It helps explain what is driving a stock’s volatility instead of treating all risk as one number.

Skill for Claude Code

Written for Claude Code: argument-hint in frontmatter. Also seen: positional $N argument.

Part of the riskmodels plugin — 5 skills, 5 commands, 1 agent shipped together

Good fit Use it to investigate a stock’s risk sources, measure how much is stock-specific, and review the ETF hedge ratios implied by each level.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/bluewatercorp/riskmodels_api/risk-decompose
Install

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.

Any agent
npx skills add BlueWaterCorp/RiskModels_API --skill risk-decompose
Clone the repo
git clone --depth 1 https://github.com/BlueWaterCorp/RiskModels_API

Made for: Claude Code.

Or install riskmodels, the plugin that ships this one along with the rest of its 5 skills, 5 commands, 1 agent.

Wrote 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.

agentmods badge for risk-decompose

README.md
[![agentmods](https://agentmods.dev/badge/skills/bluewatercorp/riskmodels_api/risk-decompose.svg)](https://agentmods.dev/skills/bluewatercorp/riskmodels_api/risk-decompose)
Your own site
<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>
Per session 93 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 717 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce 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

Measured 3d ago against content hash 67edfd87833a, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

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.

claude-plugin/plugins/riskmodels/skills/risk-decompose/SKILL.md · 59 lines

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 — read l3_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.

Read the full file on GitHub · 59 lines

Changes

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.

  1. 3d ago First seen · 59 lines · 93 tokens per session scan A 67edfd87833a

Subscribe to this mod's changes

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.

Related

Other skills, from other repositories