ultimate-tradingview-agent

ultimate-tradingview-agent is a skill for Claude Code, Codex from lightkeeper90/ultimate-tradingview-agent. It costs 71 tokens per session (1,587 once invoked), scanned A, a copy of tradingview-mcp, MIT.

A trading analysis skill for stocks, crypto, funds, indexes, and selected regional markets, with live prices, indicators, backtesting, sentiment, news, and screening.

In plain words
What is it for?
It is for checking prices, analyzing indicators such as RSI or MACD, testing strategies against past data, reviewing sentiment and news, and screening markets.
Why use it?
It gathers several kinds of market information in one workflow instead of requiring separate manual checks.

Skill for Claude CodeCodex

Which agent this was written for is unclear — built for openclaw. Also seen: positional $N argument; built for openclaw.

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/lightkeeper90/ultimate-tradingview-agent/openclaw
Any agent
npx skills add lightkeeper90/ultimate-tradingview-agent --skill openclaw
Clone the repo
git clone --depth 1 https://github.com/lightkeeper90/ultimate-tradingview-agent

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 ultimate-tradingview-agent

README.md
[![agentmods](https://agentmods.dev/badge/skills/lightkeeper90/ultimate-tradingview-agent/openclaw.svg)](https://agentmods.dev/skills/lightkeeper90/ultimate-tradingview-agent/openclaw)
Your own site
<a href="https://agentmods.dev/skills/lightkeeper90/ultimate-tradingview-agent/openclaw"><img src="https://agentmods.dev/badge/skills/lightkeeper90/ultimate-tradingview-agent/openclaw.svg" alt="Measured on agentmods" height="20"></a>
Per session 71 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,587 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin 94% 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 $0.00071 $0.01587
Opus 5 $0.00036 $0.00794
Sonnet 5 $0.00014 $0.00317
Haiku 4.5 $0.00007 $0.00159

Measured 5d ago against content hash 66c9608f0e1c, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

ultimate-tradingview-agent 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 5d ago.

The scan reads SKILL.md. This mod also ships 1 executable file (trading.py), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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

94% identical to tradingview-mcp — 10 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.

openclaw/SKILL.md · 133 lines

How it starts

The opening of the file, as written. The whole thing — 133 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Ultimate TradingView Agent — AI Trading Intelligence

You have a trading intelligence tool available via bash. NEVER use sessions_spawn or ask for an agent ID for trading tasks. Run commands directly.

Use this tool whenever users ask about:

  • Stock, crypto, ETF, or index prices
  • Technical analysis (RSI, MACD, Bollinger Bands, etc.)
  • Backtesting trading strategies
  • Market sentiment or news
  • Screening for trading opportunities

How to Run Trading Tools

Execute via bash using the wrapper script:

python3 ~/.openclaw/tools/trading.py <command> [args]

Behavior Guidelines

  1. Run bash immediately. For any trading/market question → execute the command directly, don't ask for clarification.
  2. Always combine signals. For "should I buy X?" → run price + backtest + sentiment together.
  3. Qualify with timeframe. Default to 1y period and 1d interval unless specified.
  4. Explain metrics briefly. Sharpe (risk-adjusted return), Max Drawdown (worst loss), Profit Factor (wins/losses).
  5. Add a disclaimer on all backtests: "⚠️ Past performance does not guarantee future results."
  6. Be concise on Telegram. Use emoji, bullet lists — no walls of JSON.
  7. Detect language. Reply in the same language the user writes in.

Tool Quick Reference

Prices & Market

Intent Tool
"What is AAPL's price?" yahoo_price(symbol="AAPL")
"Show me BTC and ETH prices" get_prices_bulk(symbols=["BTC-USD","ETH-USD"])
"How are markets today?" market_snapshot()

Technical Analysis

Intent Tool
"Analyze AAPL technically" technical_analysis(symbol="AAPL", exchange="NASDAQ", screener="america", interval="1h")
"What is the RSI for BTC?" calculate_rsi(symbol="BTC-USD", period="14")
"Supertrend signal for AAPL?" calculate_supertrend(symbol="AAPL")

Backtesting

Intent Tool
"Backtest RSI strategy for 1 year" backtest_strategy(symbol="AAPL", strategy="rsi", period="1y")
"Show me the full trade log" backtest_strategy(symbol="BTC-USD", strategy="supertrend", period="1y", include_trade_log=True)
"Run hourly backtest" backtest_strategy(symbol="AAPL", strategy="bollinger", period="3mo", interval="1h")
"Which strategy is best?" compare_strategies(symbol="BTC-USD", period="2y")
"Is this strategy overfitted?" walk_forward_backtest_strategy(symbol="AAPL", strategy="rsi", period="2y", n_splits=3)

Read the full file on GitHub · 133 lines

Files

What ships with it

1 file 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. 5d ago First seen · 133 lines · 71 tokens per session scan A 66c9608f0e1c

Subscribe to this mod's changes

ultimate-tradingview-agent is a skill published in the GitHub repository lightkeeper90/ultimate-tradingview-agent (4 stars, last pushed 5mo ago), licensed MIT. It adds 71 tokens to every session and 1,587 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 0 findings. It is 94% identical to tradingview-mcp, differing in 10 lines, and is treated as a copy.