market-microstructure

market-microstructure is a skill for Claude Code, Codex from skloxo/TideTrading. It costs 55 tokens per session (3,156 once invoked), scanned A, a copy of market-microstructure, MIT.

A framework for studying how orders and trades affect prices in a market. It covers bid-ask spreads, liquidity, order-flow behaviour and the limit order book, which lists available buy and sell orders.

In plain words
What is it for?
Use it to estimate transaction costs, analyse order books and spreads, design large-order execution methods such as TWAP or VWAP, detect toxic order flow, and study Chinese A-share auctions and block trades.
Why use it?
Trading costs and price impact are often larger than a simple fee estimate suggests, especially for large orders or thin markets. This helps measure those costs and identify liquidity and informed-trading risks.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it to estimate transaction costs, analyse order books and spreads, design large-order execution methods such as TWAP or VWAP, detect toxic order flow, and study Chinese A-share auctions and block trades.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/skloxo/tidetrading/market-microstructure
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.

Any agent
npx skills add skloxo/TideTrading --skill market-microstructure
Clone the repo
git clone --depth 1 https://github.com/skloxo/TideTrading

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 market-microstructure

README.md
[![agentmods](https://agentmods.dev/badge/skills/skloxo/tidetrading/market-microstructure/github.svg)](https://agentmods.dev/skills/skloxo/tidetrading/market-microstructure)
Your own site
<a href="https://agentmods.dev/skills/skloxo/tidetrading/market-microstructure"><img src="https://agentmods.dev/badge/skills/skloxo/tidetrading/market-microstructure/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for market-microstructure

Your own site · 80×15
<a href="https://agentmods.dev/skills/skloxo/tidetrading/market-microstructure"><img src="https://agentmods.dev/badge/skills/skloxo/tidetrading/market-microstructure.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 55 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,156 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin 94% copy Near-identical to another mod 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 5.1 $0.00055 $0.03156
Opus 5 $0.00028 $0.01578
Sonnet 5 $0.00011 $0.00631
Haiku 4.5 $0.00006 $0.00316

Measured 9d ago against content hash 59fab51b6bea, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

market-microstructure 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 9d 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.

Origin

This is a copy

94% identical to market-microstructure — 10 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

agent/src/skills/market-microstructure/SKILL.md · 300 lines

How it starts

The opening of the file, as written. The whole thing — 300 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Market Microstructure

Overview

Study the micro-level mechanisms of price formation: who is trading, how they are trading, and how trades affect prices. For quantitative strategies, this matters because it improves transaction-cost estimation, identifies informed trading, and optimizes execution.

Applicable scenarios:

  • Precise estimation of strategy trading costs (instead of simply assuming a flat 0.1% fee)
  • Designing large-order execution strategies (TWAP / VWAP / IS)
  • Detecting order-flow toxicity (avoid time windows dominated by informed traders)
  • Quantifying liquidity risk (flash-crash warning)
  • Capturing China A-share-specific microstructure features (call auction / closing auction / block trades)

Core Concepts

Bid-Ask Spread

Three measurements:

Metric Formula Meaning
Quoted spread Ask - Bid Best spread shown in the limit order book
Effective spread `2 × trade price - mid price
Realized spread 2 × direction × (trade price - mid price 5min later) True market-maker profit
China A-share example:
  Instrument: 600519.SH Kweichow Moutai
  Best bid: 1680.00  Best ask: 1680.50
  Quoted spread: 0.50 RMB = 0.03%

  Instrument: 000001.SZ Ping An Bank
  Best bid: 11.05  Best ask: 11.06
  Quoted spread: 0.01 RMB = 0.09%

Spread decomposition (Roll):
  Spread = adverse-selection cost + inventory cost + order-processing cost
  In China A-shares: adverse selection accounts for 60-70% (mixture of retail and informed traders)

Spread drivers:
  - Larger market cap -> smaller spread (Moutai 0.03% vs small-cap 0.5%)
  - Higher volatility -> wider spread (market-maker risk premium)
  - Higher volume -> narrower spread (greater competition)
  - Higher information asymmetry -> wider spread (adverse selection)

Order-Flow Toxicity Metrics

VPIN (Volume-Synchronized Probability of Informed Trading):

Principle: replace clock time with volume time to measure the probability of informed trading

Calculation steps:
  1. Bucket trades by fixed volume (Volume Bucket)
     Bucket size V = average daily volume / 50 (about 5-10 minutes per bucket)

  2. Classify buy and sell volume in each bucket (Bulk Volume Classification):
     buy_volume = V × Φ(ΔP / σ)  (standard normal CDF)
     sell_volume = V - buy_volume

  3. Compute order-flow imbalance:
     OI_i = |buy_volume_i - sell_volume_i|

  4. VPIN = Σ(OI_i) / (n × V)  (n=50-bucket rolling window)

Interpretation:
  VPIN < 0.3 -> normal, low informed-trading share
  VPIN 0.3-0.5 -> caution, informed trading rising
  VPIN > 0.5 -> dangerous, high probability that major information is about to be released

China A-share usage:
  A sudden VPIN spike in a stock may foreshadow:
  - insider trading ahead of a major announcement
  - institutional position building / distribution
  Before the 2015 China A-share flash crashes, VPIN stayed above 0.6 for a prolonged period

Read the full file on GitHub · 300 lines

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. 9d ago First seen · 300 lines · 55 tokens per session scan A 59fab51b6bea

Subscribe to this mod's changes

market-microstructure is a skill published in the GitHub repository skloxo/TideTrading (10 stars, last pushed 2d ago), licensed MIT. It adds 55 tokens to every session and 3,156 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. It is 94% identical to market-microstructure, differing in 10 lines, and is treated as a copy.

Related

Other skills, from other repositories

daily-deep-brief

A scheduled, pre-market investment briefing for Hong Kong and United States stocks. A deterministic preparation step gathers data and an agent adds judgment, while a later step validates and publishes the result.

KCNyu/clawock · 163 tokens

hk-stock-analysis

A workspace-aware analysis workflow for Hong Kong-listed stocks. It retrieves prices, technical indicators, market comparisons, and news through a local data pipeline, then adds Hong Kong-specific investment context.

KCNyu/clawock · 126 tokens

us-stock-analysis

Workspace-aware US stock analysis for kcn. Routes through clawock analyze-us / clawock us-quotes instead of generic web search, then layers fundamental/technical/news analysis on top. Use when user asks to analyze a US ticker (e.g. "analyze AAPL", "look at RKLB", "compare TSLA vs NVDA"), check earnings, run…

KCNyu/clawock · 97 tokens

invest-analyst

A framework for producing professional investment research, including company reports, industry studies, event analysis, analyst-expectation reviews, comparisons, and market summaries. It connects several investment research workflows into one process.

taxueseek/fund-investment-guide · 193 tokens

invest-fund

A Chinese-language guide for analysing investment funds, with different workflows for comparing funds, reviewing ETFs, examining new funds, and studying industry funds.

taxueseek/fund-investment-guide · 142 tokens

invest-cli

An investment-analysis command-line tool that fetches data for Chinese stocks and funds, US stocks, and stock screening, then applies matching analysis frameworks. A command-line tool is a program operated from a terminal.

taxueseek/fund-investment-guide · 107 tokens