market-replay

market-replay is a skill for Claude Code, Codex from kayzaa/k.i.t.-bot. It costs 0 tokens per session (991 once invoked), scanned A, a copy of market-replay, MIT.

A historical market simulator that plays past price data at normal or accelerated speed. It lets you practise trades and test strategies with virtual orders instead of real money.

In plain words
What is it for?
Use it to replay charts, move through them bar by bar, place paper trades, track results, and review periods around news or economic events.
Why use it?
It provides a way to study past market conditions without risking capital or waiting for markets to unfold in real time.

Skill for Claude CodeCodex

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

Good fit Use it to replay charts, move through them bar by bar, place paper trades, track results, and review periods around news or economic events.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/kayzaa/k.i.t.-bot/market-replay
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 kayzaa/k.i.t.-bot --skill market-replay
Clone the repo
git clone --depth 1 https://github.com/kayzaa/k.i.t.-bot

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-replay

README.md
[![agentmods](https://agentmods.dev/badge/skills/kayzaa/k.i.t.-bot/market-replay/github.svg)](https://agentmods.dev/skills/kayzaa/k.i.t.-bot/market-replay)
Your own site
<a href="https://agentmods.dev/skills/kayzaa/k.i.t.-bot/market-replay"><img src="https://agentmods.dev/badge/skills/kayzaa/k.i.t.-bot/market-replay/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-replay

Your own site · 80×15
<a href="https://agentmods.dev/skills/kayzaa/k.i.t.-bot/market-replay"><img src="https://agentmods.dev/badge/skills/kayzaa/k.i.t.-bot/market-replay.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 0 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 991 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 100% 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 $0.00000 $0.00991
Opus 5 $0.00000 $0.00495
Sonnet 5 $0.00000 $0.00198
Haiku 4.5 $0.00000 $0.00099

Measured 8d ago against content hash bee202234562, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

market-replay 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 8d 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

100% identical to market-replay — 0 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.

src/skills/market-replay/SKILL.md · 137 lines

How it starts

The opening of the file, as written. The whole thing — 137 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Market Replay

Skill #92 - Historical market simulation for strategy testing

Overview

Replay historical market data in real-time or accelerated speed. Practice trading, test strategies, and learn from past market events without risking capital.

Inspired by TradingView's Replay feature.

Features

  • 9 Replay Speeds: 0.5x, 1x, 2x, 3x, 5x, 10x, 25x, 50x, 100x
  • Step Mode: Advance bar-by-bar for precise analysis
  • Multi-Chart Sync: Replay multiple timeframes together
  • Drawing Tools: Mark up charts during replay
  • Order Simulation: Place virtual trades during replay
  • Performance Tracking: P&L, win rate, stats from replay trades
  • Event Markers: Jump to news events, earnings, Fed meetings

Usage

# Start replay from specific date
kit skill replay --symbol BTCUSDT --date 2024-03-14 --speed 10x

# Step-by-step mode
kit skill replay --symbol EURUSD --date 2024-01-01 --mode step

# Replay with paper trading
kit skill replay --symbol AAPL --date 2024-11-05 --paper-trade

# Jump to event
kit skill replay --symbol SPY --event "2024-fed-rate-cut"

Configuration

market_replay:
  default_speed: 5x
  default_timeframe: 5m
  
  speeds:
    - 0.5x
    - 1x
    - 2x
    - 3x
    - 5x
    - 10x
    - 25x
    - 50x
    - 100x
  
  paper_trading:
    initial_balance: 100000
    commission: 0.001
    slippage: 0.0001
  
  saved_events:
    - name: "2024 Bitcoin Halving"
      date: "2024-04-20"
      symbol: "BTCUSDT"
    - name: "2024 US Election"
      date: "2024-11-05"
      symbols: ["SPY", "DXY", "XAUUSD"]
    - name: "2025 Fed Rate Cut"
      date: "2025-01-29"

Controls

Key Action
Space Play/Pause
Next bar (step mode)
Previous bar
+ Increase speed
- Decrease speed
B Place buy order
S Place sell order
X Close position
J Jump to date

Example Session

{
  "session": {
    "symbol": "BTCUSDT",
    "start_date": "2024-03-14",
    "end_date": "2024-03-14T23:59:59Z",
    "duration_real": "45m",
    "duration_simulated": "24h"
  },
  "paper_results": {
    "trades": 12,
    "winners": 8,
    "losers": 4,
    "win_rate": 66.67,
    "profit": 2340.50,
    "max_drawdown": 890.00,
    "sharpe": 1.42
  },
  "notes": [
    "BTC broke ATH at 73k",
    "Caught long at 71.2k, held through consolidation",
    "Missed short opportunity at rejection"
  ]
}

Read the full file on GitHub · 137 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. 8d ago First seen · 137 lines · 0 tokens per session scan A bee202234562

Subscribe to this mod's changes

market-replay is a skill published in the GitHub repository kayzaa/k.i.t.-bot (5 stars, last pushed 6mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 991 tokens. A static security scan graded it A with 0 findings. It is 100% identical to market-replay, differing in 0 lines, and is treated as a copy.