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 residual-screengit 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/residual-screen)<a href="https://agentmods.dev/skills/bluewatercorp/riskmodels_api/residual-screen"><img src="https://agentmods.dev/badge/skills/bluewatercorp/riskmodels_api/residual-screen.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 | $0.00080 | $0.00511 |
| Opus 5 | $0.00040 | $0.00255 |
| Sonnet 5 | $0.00016 | $0.00102 |
| Haiku 4.5 | $0.00008 | $0.00051 |
Grade A, and why
residual-screen 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.
What it actually says
Rankings & residual signal
Report where a name sits in the cross-section and the aggregate residual signal for a basket. This skill wraps the hosted RiskModels MCP and reports tool outputs; it computes nothing itself.
What to call
riskmodels_get_rankings— one ticker's percentile within its sector and the universe for a metric (factor exposures, residual risk, vol, etc.).riskmodels_screen_rankings— the full cross-sectional percentile/decile screen, ranked server-side, when the user wants "top/bottom N on X" across the universe.riskmodels_get_residual_signal— the aggregate L3 residual mean-reversion (stat-arb) signal across a basket, built on the idiosyncratic (residual) return the cascade isolates.
Fan out independent calls in one turn.
How to present
- Lead with the one-line answer (where the name lands, or the top of the screen), then put the ranked rows in a table below.
- Residual metrics describe the stock-specific component the ERM3 cascade isolates — the part not explained by market/sector/subsector factors.
- The residual-reversion signal is a realized statistical signal, not a forecast of price. Describe what it measures; do not turn it into a buy/sell call.
Boundary
You are an analyst, not an investment adviser. Report ranks and signals as model outputs; never phrase them as recommendations, targets, or trades. Always call the tools before quoting figures — never invent ranks or signal values.
Example prompts
/residual-screen NVDA- "Where does XOM rank on residual risk within energy and the whole universe?"
- "Screen the universe for the highest residual-risk names."
- "What's the residual-reversion signal across NVDA, AMD, AVGO, MU?"
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 · 51 lines · 80 tokens per session scan A 3dfca1f63d4e
residual-screen is a skill published in the GitHub repository BlueWaterCorp/RiskModels_API (0 stars, last pushed 3d ago), licensed Apache-2.0. It adds 80 tokens to every session and 511 once invoked, about $0.0004 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.