tradingview-opencode-agent

A dispatcher for a TradingView Desktop AI assistant connected through MCP, a standard way for agents to use external tools. It routes requests to specialised skills for charts, Pine Script, replay practice, symbol scans, or strategy reports.

In plain words
What is it for?
Use it to analyse charts, develop or test Pine Script, practise trades in replay, scan multiple symbols, or report strategy performance.
Why use it?
It directs different TradingView tasks to the relevant workflow instead of treating every request as the same kind of analysis.

Skill for Claude CodeCodex

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

Made for: Claude Code, Codex.

Per session 44 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 918 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. 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 $0.00044 $0.00918
Opus 5 $0.00022 $0.00459
Sonnet 5 $0.00009 $0.00184
Haiku 4.5 $0.00004 $0.00092

Measured yesterday against content hash 27cdf47a4f86, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

tradingview-opencode-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 yesterday.

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.

opencode-skills/SKILL.md · 99 lines

How it starts

The opening of the file, as written. The whole thing — 99 lines — stays where its author put it; the contents beside it link to each section on GitHub.

TradingView OpenCode Agent — Dispatcher

Este es el skill orquestador que enruta a las sub-skills especializadas de TradingView.

Sub-Skills Disponibles

Sub-Skill Trigger Descripción
chart-analysis "analyze chart", "technical analysis", "review my chart" Análisis técnico completo: setup de gráfico, indicadores, navegación, anotaciones, screenshot
pine-develop "write Pine Script", "develop indicator", "create strategy" Desarrollo Pine Script: write → compile → fix errors → iterate
replay-practice "replay", "practice trading", "backtest manually" Modo replay: step bars, tomar trades, trackear P&L
multi-symbol-scan "scan symbols", "compare instruments", "multi-symbol", "screen" Análisis multi-símbolo: batch screenshots, indicadores, watchlist
strategy-report "strategy report", "backtest results", "performance report" Métricas de estrategia: trades, equity, win rate, recomendaciones

Cómo Usar

Cuando el usuario pide algo relacionado con TradingView:

  1. Identifica la sub-skill correcta según los triggers de arriba
  2. Carga la sub-skill desde el directorio de skills
  3. Sigue el workflow de la sub-skill precisamente
  4. Reporta los resultados al usuario

Quick Decision Tree

El usuario dice... Sub-Skill
"¿Qué hay en mi gráfico?" / "Analiza ES1!" chart-analysis
"Escribe un indicador para..." pine-develop
"Practicar trading del 1 de marzo" replay-practice
"Escanea ES, NQ, YM para setups" multi-symbol-scan
"Muéstrame el rendimiento de la estrategia" strategy-report

Conexión MCP

Path: ./src/server.js

Antes de cualquier sub-skill, verificar que TradingView esté conectado:

tv_health_check

Si falla, usar tv_launch para iniciar TradingView con debug port.

Estructura del Repositorio

opencode-skills/
├── SKILL.md                    # Este archivo (dispatcher)
├── chart-analysis/
│   └── SKILL.md
├── pine-develop/
│   └── SKILL.md
├── replay-practice/
│   └── SKILL.md
├── multi-symbol-scan/
│   └── SKILL.md
├── strategy-report/
│   └── SKILL.md
└── docs/
    ├── INSTALL.md
    ├── MCP.md
    └── TROUBLESHOOTING.md

Read the full file on GitHub · 99 lines

Files

What ships with it

8 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. yesterday First seen · 99 lines · 44 tokens per session scan A 27cdf47a4f86

Subscribe to this mod's changes

tradingview-opencode-agent is a skill published in the GitHub repository jadatorin/tradingview-opencode-agent (2 stars, last pushed 1mo ago), licensed MIT. It adds 44 tokens to every session and 918 once invoked, about $0.0002 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.