tradingview-mcp-server: Command for Claude Code

.claude/commands/smart-screen.md

smart-screen is a command for Claude Code from fiale-plus/tradingview-mcp-server. It costs 18 tokens per session (1,182 once invoked), scanned A, original, MIT.

A command that first judges the condition of the US stock market and then chooses a stock-screening strategy. Stock screening means filtering a large set of stocks using selected measures.

In plain words
What is it for?
Use it to assess the S&P 500, Nasdaq, Russell 2000, and Dow Jones, then run a suitable quality, growth, momentum, or value screen.
Why use it?
The most useful screening approach can change between a rising market, a correction, and a decline. This command connects the market context to the screening method.

Command for Claude Code

Written for Claude Code: installed under .claude/.

This is fiale-plus/tradingview-mcp-server's own configuration. It tells Claude Code how to work on tradingview-mcp-server 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 tradingview-mcp-server configures →

Reuse

Borrowing it

Nothing to install: this file belongs to fiale-plus/tradingview-mcp-server. 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/fiale-plus/tradingview-mcp-server/main/.claude/commands/smart-screen.md
Clone the repo
git clone --depth 1 https://github.com/fiale-plus/tradingview-mcp-server

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 smart-screen

README.md
[![agentmods](https://agentmods.dev/badge/commands/fiale-plus/tradingview-mcp-server/smart-screen/github.svg)](https://agentmods.dev/commands/fiale-plus/tradingview-mcp-server/smart-screen)
Your own site
<a href="https://agentmods.dev/commands/fiale-plus/tradingview-mcp-server/smart-screen"><img src="https://agentmods.dev/badge/commands/fiale-plus/tradingview-mcp-server/smart-screen/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 smart-screen

Your own site · 80×15
<a href="https://agentmods.dev/commands/fiale-plus/tradingview-mcp-server/smart-screen"><img src="https://agentmods.dev/badge/commands/fiale-plus/tradingview-mcp-server/smart-screen.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 18 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,182 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 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 $0.00018 $0.01182
Opus 5.5 $0.00007 $0.00473
Sonnet 5.5 $0.00004 $0.00236
Haiku 4.5 $0.00002 $0.00118

Measured 2mo ago against content hash 0093436d74c0, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

smart-screen 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 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.

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/commands/smart-screen.md · 77 lines

How it starts

The opening of the file, as written. The whole thing — 77 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Smart Screen

Automatically determines the current market regime by analyzing major US indexes, selects the most appropriate screening strategy, runs it, and displays the top results.

Steps:

  1. Fetch market regime data using mcp__tradingview__lookup_symbols

    • symbols: ["TVC:SPX", "TVC:IXIC", "TVC:RUT", "TVC:DJI"]
    • columns: ["name", "close", "all_time_high", "price_52_week_high", "price_52_week_low", "SMA200", "RSI", "Perf.1M"]
  2. Calculate regime indicators for SPX

    • ATH Drawdown = ((close - all_time_high) / all_time_high) * 100
    • Is SPX above its SMA200? (close > SMA200)
    • SPX 1M performance
  3. Determine market regime (based on SPX primarily):

    • Bull Market: SPX within 10% of ATH (drawdown > -10%) AND above SMA200
      • Recommended strategy: quality_growth_screener (if RSI < 65) or momentum_stocks (if RSI >= 65)
      • Rationale: Strong uptrend favors high-quality compounders and momentum
    • Correction: SPX 10-20% below ATH (drawdown between -20% and -10%) OR below SMA200
      • Recommended strategy: quality_stocks (if drawdown > -15%) or value_stocks (if drawdown <= -15%)
      • Rationale: Pullbacks favor defensive quality; deeper corrections favor value hunting
    • Bear Market: SPX more than 20% below ATH (drawdown < -20%)
      • Recommended strategy: value_stocks (if RSI > 35) or dividend_stocks (if RSI <= 35)
      • Rationale: Severe downturns favor deep value and income-producing assets
  4. Announce the regime and recommended strategy Display prominently:

    Current Market Regime: [Bull Market / Correction / Bear Market]
    SPX: [price] | ATH Drawdown: [X.X%] | vs SMA200: [above/below]
    Recommended Strategy: [preset_name]
    

    Follow with 2-3 sentences explaining the rationale for this strategy given current conditions. Also show a compact table of all 4 indexes:

    | Index | Price    | ATH Drawdown | vs SMA200 | RSI | 1M%   |
    |-------|----------|--------------|-----------|-----|-------|
    | SPX   | 5,732    | -2.1%        | +8.3%     | 62  | +3.2% |
    | DJI   | 42,150   | -1.8%        | +6.1%     | 60  | +2.8% |
    | IXIC  | 18,650   | -3.4%        | +9.7%     | 64  | +4.1% |
    | RUT   | 2,180    | -8.2%        | -1.2%     | 48  | +0.9% |
    

Read the full file on GitHub · 77 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. 2mo ago First seen · 77 lines · 18 tokens per session scan A 0093436d74c0

Subscribe to this mod's changes

smart-screen is a command published in the GitHub repository fiale-plus/tradingview-mcp-server (52 stars, last pushed 18d ago), licensed MIT. It adds 18 tokens to every session and 1,182 once invoked, about $0.0001 per session on Opus 5.5. 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 2026-08-30.

Related

smart-screen compared with commands from other repositories

smart-screen next to 6 commands from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
smart-screenfiale-plus/tradingview-mcp-serverCommand5218d agoMITA18Claude Code
merit-reconcileElnora-AI/elnora-merit-aktivaCommand104d agoApache-2.0A20Claude Code
merit-customersElnora-AI/elnora-merit-aktivaCommand104d agoApache-2.0A17Claude Code
fieldscoltonbearden/carrelCommand23d agoMITA36Claude Code
tnl-asset-exposurebekirdag/tnl-intelligenceCommand28d agoMITA14Claude Code, Cursor
checklistgithub/spec-kitCommand148kyesterdayMITA13Claude Code
clarifygithub/spec-kitCommand148kyesterdayMITA27Claude Code