backtesting-arena

backtesting-arena is a skill for Claude Code, Codex from Schoasch/skill-backtesting-arena. It costs 0 tokens per session (5,282 once invoked), scanned A, original, MIT.

A skill that gives coding agents structured cryptocurrency market data, including cycle scores, indicators, and aggregated sentiment. Its analyses are backtested, versioned, and intended to be reproducible rather than financial advice.

In plain words
What is it for?
Use it to retrieve market-cycle readings for Bitcoin, Ethereum, or Solana, inspect their component indicators, and access crypto market signals.
Why use it?
It helps an agent use consistent market context with supporting evidence instead of relying on unsupported or hard-to-repeat claims.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: positional $N argument.

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/schoasch/skill-backtesting-arena/backtesting-arena
Any agent
npx skills add Schoasch/skill-backtesting-arena --skill backtesting-arena
Clone the repo
git clone --depth 1 https://github.com/Schoasch/skill-backtesting-arena

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 backtesting-arena

README.md
[![agentmods](https://agentmods.dev/badge/skills/schoasch/skill-backtesting-arena/backtesting-arena.svg)](https://agentmods.dev/skills/schoasch/skill-backtesting-arena/backtesting-arena)
Your own site
<a href="https://agentmods.dev/skills/schoasch/skill-backtesting-arena/backtesting-arena"><img src="https://agentmods.dev/badge/skills/schoasch/skill-backtesting-arena/backtesting-arena.svg" alt="Measured on agentmods" 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 5,282 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. 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 5.1 $0.00000 $0.05282
Opus 5 $0.00000 $0.02641
Sonnet 5 $0.00000 $0.01056
Haiku 4.5 $0.00000 $0.00528

Measured 5d ago against content hash 3112a594df9c, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

backtesting-arena scanned grade A with 1 finding 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 5d 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

curl https://tradingstrategies.work/api/arena-pulse/today
skills/backtesting-arena/SKILL.md · 202 lines

How it starts

The opening of the file, as written. The whole thing — 202 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Backtesting Arena Skill

Description: Battle-tested market intelligence — programmatic access to crypto market cycle scoring, on-chain indicators, and aggregated sentiment data. Every claim backtested, versioned, and explainable; evidence and base rates, never financial advice. Built for AI agents and LLMs that need structured, reproducible Bitcoin/crypto market context.

Canonical source: https://tradingstrategies.work/skill.md — this repo file is kept in sync. If you spot a drift, file an issue or refer to the live one.

Capabilities

  • Get the daily Arena Pulse heat score (0-100) — multi-dimensional aggregate from 8 indicators (Bullmarket gauge, Fear & Greed, MVRV Z-score, 200-WMA distance, Mayer Multiple, Altcoin Season, Funding rates, Hash Ribbons). Inspired by Fear & Greed but multidimensional.
  • Get the BTC cycle phase (accumulation / recovery / expansion / distribution / overheated) with all 10 component indicators (Pi-Cycle Top/Bottom, Mayer, Weekly RSI, MA200W, Halving position, Fear & Greed, BTC Dominance, Mining Difficulty, Macro Liquidity).
  • Get a per-coin cycle read for ETH or SOL — the transferable price-derived indicators (Mayer, Weekly RSI, 200-week-MA distance) with renormalized weights; BTC-native indicators are returned as not_applicable rather than faked.
  • Get reproducible BTC support/resistance key levels — swing-fractal clusters with touch-count, band and distance from spot (no eyeballing a fractal chart).
  • Read the alternative.me Fear & Greed Index via a DSGVO-compliant server-side proxy (your client never directly hits alternative.me).
  • Read the historical series of Arena Pulse and BTC cycle scores for trend analysis and regime detection.

Use Cases

  • Trading bots that need market regime context before placing orders
  • Research agents that compare current market state against historical analogues
  • Newsletter / content generators that need daily market sentiment data
  • Risk-management agents that throttle exposure based on cycle phase
  • Backtesting frameworks that want a reproducible "as-of-date" market context

Read the full file on GitHub · 202 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. 5d ago First seen · 202 lines · 0 tokens per session scan A 3112a594df9c

Subscribe to this mod's changes

backtesting-arena is a skill published in the GitHub repository Schoasch/skill-backtesting-arena (0 stars, last pushed 11d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 5,282 tokens. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.