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 agentmods add skills/jadatorin/tradingview-opencode-agent/pine-developnpx skills add jadatorin/tradingview-opencode-agent --skill pine-developgit clone --depth 1 https://github.com/jadatorin/tradingview-opencode-agentWhat 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 | $0.00032 | $0.00715 |
| Opus 5 | $0.00016 | $0.00358 |
| Sonnet 5 | $0.00006 | $0.00143 |
| Haiku 4.5 | $0.00003 | $0.00072 |
Grade A, and why
pine-develop 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.
Copies of this mod
2 near-identical copies found in the catalogue:
- pine-develop — 91% identical, 16 lines differ
- pine-develop — 91% identical, 16 lines differ
How it starts
The opening of the file, as written. The whole thing — 93 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Pine Script Development Loop
You are developing a Pine Script indicator or strategy in TradingView. Follow this loop precisely.
Step 1: Understand the Goal
If not already clear, ask the user:
- What type? (indicator, strategy, library)
- What does it do? (entry/exit logic, overlay, oscillator, etc.)
- Overlay or separate pane?
- Any specific inputs or visual elements?
Step 2: Pull Current Source (if modifying)
If modifying an existing script:
node scripts/pine_pull.js
Then read scripts/current.pine to understand what's there.
If creating new: start from scratch.
Step 3: Write the Pine Script
Write the complete script to scripts/current.pine. Every script MUST include:
//@version=6header- Proper
indicator()orstrategy()declaration - All user inputs with
input.*()functions and groups - Clear comments for each logical section
For strategies, include:
strategy.entry()andstrategy.exit()calls- Position sizing via
strategy()declaration - Default commission and slippage settings
Step 4: Push and Compile
node scripts/pine_push.js
This injects the code into TradingView's Pine Editor, clicks compile, and reports any errors.
Step 5: Fix Errors
If errors are reported:
- Read the error messages (line number + description)
- Edit
scripts/current.pinelocally — fix the specific lines - Push again:
node scripts/pine_push.js - Repeat until 0 errors
Common Pine Script errors:
- "Mismatched input" — usually indentation (Pine uses 4-space indentation, not braces)
- "Could not find function or function reference" — typo in function name or wrong version
- "Undeclared identifier" — variable used before declaration
- "Cannot call X with argument type Y" — wrong parameter type
Step 6: Verify on Chart
After clean compilation:
capture_screenshot— take a screenshot to verify it looks rightdata_get_strategy_results— if it's a strategy, check performance- Show the user the results
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.
- yesterday First seen · 93 lines · 0 tokens per session scan A 31702197d7ec
pine-develop is a skill published in the GitHub repository jadatorin/tradingview-opencode-agent (2 stars, last pushed 1mo ago), licensed MIT. It adds 32 tokens to every session and 715 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.
Other skills, from other repositories
browser-automation
Use browser automation to inspect or interact with websites, test rendered interfaces, capture screenshots, and diagnose console or network behavior.
ninja-patterns
NinjaTrader 8 NinjaScript indicator scaffold and patterns. Provides C# structure guidance and triggers doc-researcher for API verification. Use when developing NinjaTrader indicators.
tradovate-patterns
Tradovate JavaScript indicator scaffold and patterns. Provides class structure and export guidance. Use when developing Tradovate indicators.
pine-patterns
Pine Script v5/v6 indicator scaffold and patterns. Provides structure guidance and triggers doc-researcher for current syntax verification. Use when developing TradingView indicators.
a11y-debugging
Uses Chrome DevTools MCP for accessibility (a11y) debugging and auditing based on web.dev guidelines. Use when testing semantic HTML, ARIA labels, focus states, keyboard navigation, tap targets, and color contrast.
autopilot
Full autonomous execution from idea to working code.