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/xingwudao/open-xquant/create-componentnpx skills add xingwudao/open-xquant --skill create-componentgit clone --depth 1 https://github.com/xingwudao/open-xquantWrote 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/xingwudao/open-xquant/create-component)<a href="https://agentmods.dev/skills/xingwudao/open-xquant/create-component"><img src="https://agentmods.dev/badge/skills/xingwudao/open-xquant/create-component.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 | $0.00032 | $0.00642 |
| Opus 5 | $0.00016 | $0.00321 |
| Sonnet 5 | $0.00006 | $0.00128 |
| Haiku 4.5 | $0.00003 | $0.00064 |
Grade A, and why
create-component 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 4d 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 — 82 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Component Creator
Use this skill when the user explicitly asks to modify open-xquant source code or add a built-in component to the framework.
For workspace-local custom components in a research task, use
author-component instead. That worker writes custom_components/,
component_manifest.json, and a refreshed component_catalog.json without
mutating the installed SDK bundle.
When this built-in/framework development path applies, decide whether a new component is actually needed, then route to the correct creation skill.
Do not write component code in this navigator skill.
Step 1: Classify The Request
Choose one component type:
- Indicator: numeric time-series computation from market or factor data
- Signal: boolean or categorical trading intent
- PortfolioOptimizer: target portfolio weights from signals or indicators
- Rule: bar-by-bar trading constraint, hold, or exit action
If the request could fit more than one type, ask the user to clarify. For example, "momentum" can be an Indicator, while "buy when momentum is positive" is a Signal.
For ROC timing strategies, prefer the existing split:
ROCis the numeric Indicator.ROCTimingis the Signal that emitsBUY,SELL, orHOLD.SignalToPositionis the PortfolioOptimizer that turns those labels into target weights whileHOLDmaintains the prior target position.
For other categorical timing signals, keep the same boundary: the Signal emits
labels, the spec declares output_domain, and SignalToPosition maps labels
to target weights. Do not route that behavior to an Indicator only to make a
spec compile.
Step 2: Check Existing Registry
uv run python - <<'PY'
import oxq
print("Indicators:", sorted(oxq.list_indicators()))
print("Signals:", sorted(oxq.list_signals()))
print("Portfolios:", sorted(oxq.list_portfolio_optimizers()))
print("Rules:", sorted(oxq.list_rules()))
PY
Search for exact and near matches. If a component already exists, report the existing name and stop unless the user explicitly needs different behavior.
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.
- 4d ago First seen · 82 lines · 32 tokens per session scan A 8e53956c68f8
create-component is a skill published in the GitHub repository xingwudao/open-xquant (124 stars, last pushed 7d ago), licensed MIT. It adds 32 tokens to every session and 642 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 2026-08-30.
Other skills, from other repositories
convex-add
Add a capability to the CURRENT Convex app — consults the served Convex capability catalog for always-current procedures (billing, crons, auth, agent, search, …); falls back to built-in hosting or @convex-dev component search. TRIGGER when the user runs /add, or asks to add hosting/publishing or any backend capability…
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
Use when evaluating A-share limit-up (涨停板) setups through Chen Hao's sentiment and momentum lens: market emotion cycles, board strength, follow-through, and short-term aggressive momentum trading.
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.
cwv-optimizer
Diagnose and fix Core Web Vitals issues on AEM Edge Delivery Services pages. Goes deeper than generic CWV advice by understanding EDS-specific performance patterns including the 100KB LCP budget, E-L-D loading phases, block rendering behavior, and third-party script impact. Produces specific fixes for LCP, CLS, and…
multi-expert-analyzer
针对通用问题进行多领域专家联合分析, 综合稿产生前必经 fact-checker 与 red-team 两道独立校验。适用场景: 用户提出跨领域或不确定领域的复杂问题, 需要从多个专家角度分别搜证并相互校验后综合成文, 例如该不该买房、该不该跳槽、是否进入某个赛道等。触发关键词: 多角度分析、专家分析、综合分析、多视角、跨领域分析、从不同角度看、深度分析。问题只属于单一明确领域时, 优先使用该领域的专门 skill, 例如纯财务用 finance-core-analysis、纯技术用 software-architect。输出 (全部 markdown 保存到当前项目 markdown/ 目录): (1) 每位专家的中间分析稿…