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 xingwudao/open-xquant --skill create-rulegit 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-rule)<a href="https://agentmods.dev/skills/xingwudao/open-xquant/create-rule"><img src="https://agentmods.dev/badge/skills/xingwudao/open-xquant/create-rule.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 | $0.00034 | $0.00854 |
| Opus 5 | $0.00017 | $0.00427 |
| Sonnet 5 | $0.00007 | $0.00171 |
| Haiku 4.5 | $0.00003 | $0.00085 |
Grade A, and why
create-rule 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 7d 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 — 146 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Create Rule
You create bar-by-bar risk, hold, weight override, or exit logic.
Scope
Default built-in paths:
- source:
src/oxq/rules/{snake_name}.py - tests:
tests/rules/test_{snake_name}.py - package export:
src/oxq/rules/__init__.py - built-in registry:
src/oxq/core/registry.py
Phase 1: Read Existing Patterns
Read before editing:
src/oxq/core/types.pysrc/oxq/core/engine.pyrule handling instep()src/oxq/rules/constraint.pysrc/oxq/rules/order.py- one existing test in
tests/rules/ src/oxq/rules/__init__.py- the rule registration block in
src/oxq/core/registry.py
Important current engine behavior:
- pre-trade consumes
RuleResult.weights - pre-trade consumes
RuleResult.hold - post-trade consumes
RuleResult.target_positions RuleResult.constraintsexists in the type but is not currently applied byEngine.step()
Phase 2: Define Behavior
State before coding:
- pre-trade or post-trade
- trigger condition
- fields returned in
RuleResult - constructor parameters
- internal state, if any
- reset behavior, if any
- exact no-trigger result
Ask the user if risk thresholds or trigger semantics are ambiguous.
Phase 3: Test First
Write tests with hand-built portfolio and bar rows:
- protocol compliance with
Rule - trigger scenario
- no-trigger scenario returns empty
RuleResult() - correct
reasonwhen activated - no mutation of
Portfolio - stateful behavior if relevant
namevalue
Run the new test and confirm the missing implementation fails before coding.
uv run pytest tests/rules/test_{snake_name}.py -v
Phase 4: Implement
Skeleton:
"""Short description rule."""
from __future__ import annotations
from decimal import Decimal
import pandas as pd
from oxq.core.types import Portfolio, RuleResult
class ClassName:
"""Short behavior description."""
name = "ClassName"
def __init__(self, threshold: float) -> None:
self.threshold = threshold
def evaluate(
self,
symbol: str,
row: pd.Series,
portfolio: Portfolio,
prices: dict[str, Decimal] | None = None,
) -> RuleResult:
"""Return a RuleResult when the rule activates."""
...
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.
- 7d ago First seen · 146 lines · 34 tokens per session scan A 3156176e4880
create-rule is a skill published in the GitHub repository xingwudao/open-xquant (126 stars, last pushed 4d ago), licensed MIT. It adds 34 tokens to every session and 854 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
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.