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 Schoasch/skill-backtesting-arena --skill backtesting-arenagit clone --depth 1 https://github.com/Schoasch/skill-backtesting-arenaWrote 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/schoasch/skill-backtesting-arena/backtesting-arena)<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/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.
<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="Reviewed on agentmods" width="80" 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 | $0.00000 | $0.05282 |
| Opus 5.5 | $0.00000 | $0.02113 |
| Sonnet 5.5 | $0.00000 | $0.01056 |
| Haiku 4.5 | $0.00000 | $0.00528 |
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 2mo 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 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_applicablerather 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
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.
- 2mo ago First seen · 202 lines · 0 tokens per session scan A 3112a594df9c
backtesting-arena is a skill published in the GitHub repository Schoasch/skill-backtesting-arena (0 stars, last pushed 8d 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.
backtesting-arena compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| backtesting-arenaSchoasch/skill-backtesting-arena | Skill | 0 | 8d ago | MIT | A | 0 | Claude Code, Codex |
| agentic-streetLeoYeAI/openclaw-master-skills | Skill | 2.2k | 6d ago | MIT | A | 91 | Claude Code, Codex |
| token-pickaeonfun/aeon | Skill | 788 | yesterday | MIT | A | 25 | Claude Code, Codex |
| bridgealsk1992/CloddsBot | Skill | 3.1k | 1mo ago | MIT | A | 13 | Claude Code, Codex |
| hyperliquidalsk1992/CloddsBot | Skill | 3.1k | 1mo ago | MIT | A | 19 | Claude Code, Codex |
| marginfialsk1992/CloddsBot | Skill | 3.1k | 1mo ago | MIT | A | 11 | Claude Code, Codex |
| airdrop-hunting-guidenirholas/three.ws | Skill | 269 | yesterday | Apache-2.0 | A | 54 | Claude Code, Codex |