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 agentmods add skills/proxy2021/enso/alpharank_validationnpx skills add Proxy2021/Enso --skill alpharank_validationgit clone --depth 1 https://github.com/Proxy2021/EnsoWhat 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 | $0.00041 | $0.00859 |
| Opus 5 | $0.00020 | $0.00430 |
| Sonnet 5 | $0.00008 | $0.00172 |
| Haiku 4.5 | $0.00004 | $0.00086 |
Grade A, and why
alpharank_validation 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 2d 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 — 51 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AlphaRank validation dashboard: model scorecard with IC/ICIR/PBO/DSR gates, feature importance analysis, overfitting diagnostics, validation checklist tracker, and model comparison
Tool Reference
enso_alpharank_validation_scorecard (primary)
Display AlphaRank model validation scorecard with key metrics (IC, ICIR, PBO, DSR, Sharpe, drawdown) and pass/fail gates for each model horizon M1-M12. Accepts metrics as JSON input or reads from a results file. Use when the user says: 'show validation scorecard', 'model metrics', 'how are my models doing', 'validation dashboard', 'AlphaRank scorecard'.
Parameters:
metrics(string): JSON string of model metrics. Each model should have: name, trainIC, testIC, icir, pbo, dsr, sharpe, annualReturn, maxDrawdown. If omitted, reads from state or uses sample data.filePath(string): Path to a JSON results file containing model metrics. Optional.
enso_alpharank_validation_features
View feature importance analysis for AlphaRank models: top features by SHAP/MDI importance, category breakdown, stability scores, and keep/cut recommendations. Accept feature data as JSON input. Use when the user says: 'show feature importance', 'which features matter', 'feature analysis', 'SHAP values'.
Parameters:
features(string): JSON string of feature importance data. Each feature should have: name, importance, category, stability, recommendation. If omitted, uses sample data.model(string): Model name to show features for (e.g. 'M1', 'M6'). Defaults to best model.topN(number): Number of top features to display (default: 20)
enso_alpharank_validation_diagnose
Run overfitting diagnostic analysis: train vs test comparison, IC decay curve, rolling IC, degrees of freedom, and LLM-powered recommendation engine. Use when the user says: 'diagnose overfitting', 'why is my model overfitting', 'overfitting analysis', 'train vs test gap'.
Parameters:
diagnostics(string): JSON string of diagnostic data including train/test metrics over time. If omitted, uses sample data.model(string): Model name to diagnose (e.g. 'M1', 'M6'). Defaults to worst performing model.
What ships with it
8 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 2d ago First seen · 51 lines · 41 tokens per session scan A 882c913069b9
alpharank_validation is a skill published in the GitHub repository Proxy2021/Enso (5 stars, last pushed 3mo ago), licensed MIT. It adds 41 tokens to every session and 859 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
edgefinder
Use EdgeFinder for NFL, NBA, and MLB sports betting analysis, schedules, standings, odds, and Polymarket portfolio analysis.
officecli-financial-model
Use this skill when the user wants to build a financial model — 3-statement model, DCF valuation, LBO, SaaS unit economics, sensitivity / scenario analysis, debt schedule, or fundraising projections — in Excel. Trigger on: 'financial model', '3-statement model', 'P&L + BS + CF', 'DCF', 'WACC', 'NPV', 'terminal value'…
1m-trade
Integrated on-chain operations hub: integrates BlockBeats market intelligence, Hyperliquid DEX trading via hl1m, wallet creation and management at https://www.1m-trade.com, and supports local initialization using hl1m init-wallet (wallet address + proxy private key, never use the main wallet private key). Supports…
0xarchive
Query historical crypto market data from 0xArchive across Hyperliquid, Lighter.xyz, and HIP-3. Covers orderbooks, trades, candles, funding rates, open interest, liquidations, and data quality. Use when the user asks about crypto market data, orderbooks, trades, funding rates, or historical prices on Hyperliquid…
a-stock-orchestrator
A股投研指挥官 - 编排调度多个股票分析Skill，串联成完整投研流水线。支持四种模式：板块扫描、板块分析、个股深度分析、持仓体检。最终输出结构化投资简报并自动存档飞书。.
1m-trade-dex
Hyperliquid DEX/Perps entrypoint via hl1m: market queries, order placement. Wallet creation/management at https://www.1m-trade.com; local hl1m init-wallet with address + proxy (API) private key — never the main wallet key. No in-skill private-key messaging.