agent-trading-arena: Skill for Claude Code

.claude/skills/trading-wisdom/SKILL.md

trading-wisdom is a skill for Claude Code from 0xhubed/agent-trading-arena. It costs 26 tokens per session (8,400 once invoked), scanned A, original, MIT.

A collection of trading lessons drawn from results in an agent competition.

In plain words
What is it for?
It is used to inform trading decisions with observed patterns about market conditions, position direction, trade frequency, and self-review.
Why use it?
It helps trading systems account for recurring mistakes such as misreading the market direction, overtrading, and acting when staying out would be safer.

Skill for Claude Code

Written for Claude Code: installed under .claude/. Also seen: positional $N argument.

This is 0xhubed/agent-trading-arena's own configuration. It tells Claude Code how to work on agent-trading-arena itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything agent-trading-arena configures →

Reuse

Borrowing it

Nothing to install: this file belongs to 0xhubed/agent-trading-arena. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/0xhubed/agent-trading-arena/main/.claude/skills/trading-wisdom/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/0xhubed/agent-trading-arena

Made for: Claude Code.

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 trading-wisdom

README.md
[![agentmods](https://agentmods.dev/badge/skills/0xhubed/agent-trading-arena/trading-wisdom/github.svg)](https://agentmods.dev/skills/0xhubed/agent-trading-arena/trading-wisdom)
Your own site
<a href="https://agentmods.dev/skills/0xhubed/agent-trading-arena/trading-wisdom"><img src="https://agentmods.dev/badge/skills/0xhubed/agent-trading-arena/trading-wisdom/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 trading-wisdom

Your own site · 80×15
<a href="https://agentmods.dev/skills/0xhubed/agent-trading-arena/trading-wisdom"><img src="https://agentmods.dev/badge/skills/0xhubed/agent-trading-arena/trading-wisdom.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 26 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 8,400 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. Third-party audits
  • Socket pass 22 Apr 2026
  • Snyk pass 22 Apr 2026
How audits are shown
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 $0.00026 $0.08400
Opus 5 $0.00013 $0.04200
Sonnet 5 $0.00005 $0.01680
Haiku 4.5 $0.00003 $0.00840

Measured 11d ago against content hash 1fe4c5cd4023, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

trading-wisdom 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 11d 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.

.claude/skills/trading-wisdom/SKILL.md · 413 lines

How it starts

The opening of the file, as written. The whole thing — 413 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Trading Wisdom

Last updated: 2026-03-09 20:08 UTC Active patterns: 232 Total samples: 22482 Confidence threshold: 60%

Key Learnings

  1. Market was uniformly bullish (BNB +3.31%, BTC +2.68%, ETH +3.90%, SOL +5.07%, DOGE +2.46%) — the 7th consecutive window where regime misidentification was the primary loss driver.
  2. Only 1 of 6 active agents was profitable (journal_aware +$55.48). The other 5 active agents lost a combined -$571.18, suggesting widespread SHORT bias despite uniformly positive market.
  3. gptoss_skill_aware was the worst performer (-$340.51 on 31 trades), consistent with the persistent pattern of sophisticated validation frameworks providing false confidence on wrong-direction trades.
  4. Self-reflective position management (journal_aware) continues to be the most reliable edge among active agents, now profitable in multiple bullish windows.
  5. Zero trading (ta_bot, index_fund) outperformed 5 of 6 active agents, reinforcing that inaction beats wrong-direction action.
  6. SOL was the best performer (+5.07%) — highest-beta assets continue to show the largest moves, making them both the best LONG targets and the worst SHORT targets.
  7. Trade frequency amplifies losses when directional bias is wrong: skill_aware's 31 trades at -$10.98/trade vs contrarian's 6 trades at -$3.79/trade.

Winning Strategies

skill_aware_oss: High-frequency SHORT-biased tradi...

  • Confidence: 95%
  • Total samples: 200
  • Times confirmed: 1
  • First seen: 2026-02-01
  • Details: skill_aware_oss: High-frequency SHORT-biased trading (200 trades/24h) with multi-timeframe bearish alignment validation, 2% equity risk sizing, and disciplined profit-taking. Achieved +$2911.52 in uniformly bearish market (-6% to -11% across all assets).

Combining technical validation ('risk calculator s...

  • Confidence: 92%
  • Total samples: 200
  • Times confirmed: 1
  • First seen: 2026-02-01
  • Details: Combining technical validation ('risk calculator shows 2:1 reward', 'validation permits trade') with trend alignment across 15m/1h/4h timeframes for SHORT entries in bearish markets. skill_aware_oss used this consistently with high confidence (0.78-0.92).

Read the full file on GitHub · 413 lines

Files

What ships with it

2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 11d ago First seen · 413 lines · 26 tokens per session scan A 1fe4c5cd4023

Subscribe to this mod's changes

trading-wisdom is a skill published in the GitHub repository 0xhubed/agent-trading-arena (8 stars, last pushed 4mo ago), licensed MIT. It adds 26 tokens to every session and 8,400 once invoked, about $0.0001 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 2026-08-31.

Related

Other skills, from other repositories

sector-rotation

An analysis framework for comparing industries in the Chinese A-share stock market, using business conditions, price momentum, valuation, and money flows. It produces rankings and higher- or lower-allocation suggestions.

HKUDS/Vibe-Trading · 39 tokens

strategy-pivot-designer

Detect backtest iteration stagnation and generate structurally different strategy pivot proposals when parameter tuning reaches a local optimum.

tradermonty/claude-trading-skills · 28 tokens

twitter-reader

Read Twitter/X for financial research using opencli (read-only). Use this skill whenever the user wants to read their Twitter feed, search for financial tweets, view bookmarks, look up user profiles, or gather market sentiment from Twitter/X. Triggers include: "check my feed", "search Twitter for", "show my…

himself65/finance-skills · 161 tokens

chenhao-limit-up

A framework for judging Chinese A-share stocks that have reached the daily price-rise limit, using market mood, sector leadership, and trading momentum.

questflowai/investorskills · 44 tokens

trading-risk-gate

Unified pre-trade safety gate: Ruin check (Law #1), ergodicity audit, and win-rate dominance validation. Absorbs: ergodicity-check, law-of-ruin, win-rate-dominance.

winstonkoh87/Athena-Public · 53 tokens

furusato

A Japanese hometown-tax donation manager for furusato nozei, a system where donations to municipalities can qualify for an income-tax or local-tax deduction. It reads donation receipts, stores donation records, and calculates deduction limits.

kazukinagata/shinkoku · 102 tokens