evaluate-factor

evaluate-factor is a skill for Claude Code, Codex from xingwudao/open-xquant. It costs 28 tokens per session (333 once invoked), scanned A, original, MIT.

A routing guide for evaluating whether a factor predicts future returns. A factor is a measurable property of market data used to rank assets or decide when to trade.

In plain words
What is it for?
Use it to choose between cross-sectional evaluation across many assets and time-series evaluation for one asset or a small rotation set, with properly aligned forward returns.
Why use it?
It avoids using the wrong statistical test for the question, such as comparing many stocks when the task is timing one asset.

Skill for Claude CodeCodex

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.

agentmods
npx agentmods add skills/xingwudao/open-xquant/evaluate-factor
Any agent
npx skills add xingwudao/open-xquant --skill evaluate-factor
Clone the repo
git clone --depth 1 https://github.com/xingwudao/open-xquant

Made for: Claude Code, Codex.

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 evaluate-factor

README.md
[![agentmods](https://agentmods.dev/badge/skills/xingwudao/open-xquant/evaluate-factor.svg)](https://agentmods.dev/skills/xingwudao/open-xquant/evaluate-factor)
Your own site
<a href="https://agentmods.dev/skills/xingwudao/open-xquant/evaluate-factor"><img src="https://agentmods.dev/badge/skills/xingwudao/open-xquant/evaluate-factor.svg" alt="Measured on agentmods" height="20"></a>
Per session 28 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 333 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00028 $0.00333
Opus 5 $0.00014 $0.00167
Sonnet 5 $0.00006 $0.00067
Haiku 4.5 $0.00003 $0.00033

Measured 5d ago against content hash 9320567db0c4, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

evaluate-factor 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 5d 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.

agent/skills/evaluate-factor/SKILL.md · 54 lines

What it actually says

Factor Evaluator

You decide which factor evaluation workflow to use.

Ask First

Confirm:

  • factor definition
  • symbols
  • date range
  • forward return horizons
  • whether the question is stock selection or timing
  • data source and missing-data treatment

Route

Use agent/skills/evaluate-cross-sectional/SKILL.md when:

  • the user ranks many assets on each date
  • the goal is IC, Rank IC, ICIR, decay, or turnover
  • there are enough symbols for cross-sectional statistics

Use agent/skills/evaluate-time-series/SKILL.md when:

  • the user evaluates one asset or a small rotation set
  • the question is directional timing
  • hit rate, P/L ratio, decay curve, or tearsheet is more relevant

Rule of thumb:

  • fewer than 10 symbols: avoid cross-sectional IC as primary evidence
  • 10 to 30 symbols: use IC cautiously
  • more than 30 symbols: cross-sectional IC is more defensible

Data Requirements

Build factor values and forward returns with aligned indexes. Do not let same-day execution leak into forward returns. For formal reports, state the horizon, date alignment, and excluded rows.

Red Lines

  • Do not evaluate a factor without forward-return alignment.
  • Do not run only one horizon when the user is making a research claim.
  • Do not hide low sample size or high turnover.
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. 5d ago First seen · 54 lines · 28 tokens per session scan A 9320567db0c4

Subscribe to this mod's changes

evaluate-factor is a skill published in the GitHub repository xingwudao/open-xquant (126 stars, last pushed 2d ago), licensed MIT. It adds 28 tokens to every session and 333 once invoked, about $0.0001 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 2026-08-30.