execution-model

execution-model is a skill for Claude Code, Codex from HKUDS/Vibe-Trading. It costs 41 tokens per session (3,229 once invoked), scanned A, original, MIT.

A set of backtest-only models for estimating trading costs, including slippage, market impact, and delayed execution. Slippage is the difference between the expected price and the simulated fill price; market impact is the price movement caused by a large order.

In plain words
What is it for?
Use it to make historical trading simulations more realistic with fixed, linear, or square-root impact models and delayed fills. It does not place live orders.
Why use it?
A backtest that assumes every order fills instantly at the displayed price can look better than real trading. These models add assumptions for spreads, order size, price impact, and signal-to-fill delay.

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/hkuds/vibe-trading/execution-model
Any agent
npx skills add HKUDS/Vibe-Trading --skill execution-model
Clone the repo
git clone --depth 1 https://github.com/HKUDS/Vibe-Trading

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 execution-model

README.md
[![agentmods](https://agentmods.dev/badge/skills/hkuds/vibe-trading/execution-model.svg)](https://agentmods.dev/skills/hkuds/vibe-trading/execution-model)
Your own site
<a href="https://agentmods.dev/skills/hkuds/vibe-trading/execution-model"><img src="https://agentmods.dev/badge/skills/hkuds/vibe-trading/execution-model.svg" alt="Measured on agentmods" height="20"></a>
Per session 41 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,229 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 $0.00041 $0.03229
Opus 5 $0.00020 $0.01614
Sonnet 5 $0.00008 $0.00646
Haiku 4.5 $0.00004 $0.00323

Measured 4d ago against content hash da126eefad69, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

execution-model 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.

agent/src/skills/execution-model/SKILL.md · 336 lines

How it starts

The opening of the file, as written. The whole thing — 336 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Trade Execution Modeling

Overview

Provide more realistic execution assumptions for backtests, including slippage models, market-impact estimation, and execution-algorithm principles. This skill is for backtest simulation only and does not involve live order execution.

Slippage Models

Why Slippage Models Are Needed

Idealized backtest: filled at the close, zero slippage
Real world:
1. The order book has a bid-ask spread
2. Large orders push prices (market impact)
3. Execution is delayed (there is latency from signal to fill)

No slippage model -> overly optimistic backtest -> losses in live trading

Do not retype these models. All four are implemented and tested in src/quantlib/impact.py; import them. The tested versions validate their inputs — a zero ADV raises instead of dividing by zero, and a negative delay_bars raises instead of silently introducing look-ahead bias.

from src.quantlib.impact import fixed_slippage, linear_impact, sqrt_impact, delayed_execution

1. Fixed Slippage Model

fixed_slippage(price=100.0, direction=1, bps=5.0)   # 100.05  (buy pays up)
fixed_slippage(price=100.0, direction=-1, bps=5.0)  #  99.95  (sell receives less)

direction is 1 to buy or -1 to sell, and must be exactly one of those — it multiplies the impact, so an unchecked 2 would silently double the modelled cost. bps defaults to DEFAULT_SLIPPAGE_BPS (5.0).

Reference fixed-slippage assumptions by market:

Market Instrument Suggested Slippage (bps) Notes
China A-share large cap CSI 300 constituents 3-5 Good liquidity
China A-share small cap CSI 1000 constituents 5-10 Average liquidity
China micro-cap market cap < 5 billion RMB 10-30 Poor liquidity
US large cap AAPL / MSFT 1-3 Excellent liquidity
Hong Kong stocks Hang Seng constituents 5-10 Less liquid than A / US
BTC spot BTC-USDT 2-5 Good OKX liquidity
ETH spot ETH-USDT 3-8 Slightly worse than BTC
Small altcoins other -USDT pairs 10-50 Liquidity varies widely

Read the full file on GitHub · 336 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. 4d ago First seen · 336 lines · 41 tokens per session scan A da126eefad69

Subscribe to this mod's changes

execution-model is a skill published in the GitHub repository HKUDS/Vibe-Trading (32,384 stars, last pushed 2d ago), licensed MIT. It adds 41 tokens to every session and 3,229 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.

Related

Other skills, from other repositories

backtest-interpretation

Interpret backtest output from the historicalpriceanalyzer tool — four built-in strategies (SMA crossover, RSI reversal, breakout, mean reversion) over Indian stocks, with Sharpe, max drawdown, win rate, and avg trade. Use when the user asks about "backtest", "how would strategy X have performed", "test this on…

Sundeepg98/kite-mcp-server · 103 tokens

sector-rotation

Analyze sector exposure in an Indian equity portfolio — which sectors the user is overweight/underweight vs NIFTY benchmarks, how yesterday's FII/DII flows align with current holdings, and what the concentration numbers actually say. Use when the user asks about "sector exposure", "sector rotation", "am I too…

Sundeepg98/kite-mcp-server · 100 tokens

tax-harvest

Walk an Indian retail trader through tax-loss harvesting on their Zerodha equity holdings — identify STCG/LTCG positions with losses, estimate tax savings under Indian capital-gains rules, and plan the sell-and-rebuy sequence while avoiding wash-sale equivalents. Use when the user asks about "tax harvesting", "tax…

Sundeepg98/kite-mcp-server · 109 tokens

eod-review

End-of-day trading review for an Indian retail trader on Zerodha Kite — day P&L, positions still open, orders placed today, alert activity, MIS square-off warnings, and action items for tomorrow. Use when the user says "EOD review", "end of day summary", "how did today go", "close the books", "wrap up trading day", or…

Sundeepg98/kite-mcp-server · 87 tokens

morning-brief

Generate a daily pre-market briefing for an Indian retail trader using Zerodha Kite holdings, positions, indices, alerts, and margin. Use when the user asks for a "morning brief", "pre-market check", "what should I watch today", "pre-open check", or similar phrasing about Indian stock market start-of-day status.

Sundeepg98/kite-mcp-server · 73 tokens

trade-check

Run a pre-flight check before placing an equity order on Zerodha Kite — current price, margin required, portfolio concentration impact, existing exposure, and stop-loss suggestion. Use when the user says "should I buy X", "pre-trade check on Y", "can I afford Z quantity of ABC", "check before I place order", or asks…

Sundeepg98/kite-mcp-server · 84 tokens