pinescriptv6 pine-script.instructions.md

Repository instructions for the Pine Script Agent Kit, a set of rules for working with Pine Script version 6. They require evidence-based decisions and a separate manual-check path for TradingView behavior.

In plain words
What is it for?
Use them for Pine Script indicators, strategies, libraries, migrations, alerts, and related reviews. They cover timeframe relationships, strategy execution, data access, repainting, and webhook risks.
Why use it?
They help prevent local static checks from being presented as proof that code compiles, does not repaint, is secure, or works in production. They also require matching rules and registered sources.

Instructions file for GitHub Copilot

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 instructions/trugurpala/pinescriptv6/pine-script
Clone the repo
git clone --depth 1 https://github.com/trugurpala/pinescriptv6

Made for: GitHub Copilot.

Per session 3,294 This file is loaded in full into every session.
When invoked 3,294 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
Origin 97% 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 $0.03294 $0.03294
Opus 5 $0.01647 $0.01647
Sonnet 5 $0.00659 $0.00659
Haiku 4.5 $0.00329 $0.00329

Measured yesterday against content hash 2536f25bc3c4, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

pinescriptv6 pine-script.instructions.md 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.

Origin

This is a copy

97% identical to pinescriptv6 copilot-instructions.md — 3 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.

.github/instructions/pine-script.instructions.md · 320 lines

How it starts

The opening of the file, as written. The whole thing — 320 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Pine Script Agent Kit for GitHub Copilot

Use these repository instructions with the scoped Pine instruction file. Do not infer CI, release, or TradingView verification from local static success.

Evidence-first operating protocol

You are working with Pine Script v6. Treat knowledge/catalog.json as the canonical rule index and knowledge/sources.json as the canonical source index.

  1. Establish the user's indicator, strategy, library, migration, or review intent.
  2. Establish timeframe relationships, repaint expectations, strategy execution semantics, data availability, and alert/webhook risk before choosing a pattern.
  3. Apply only rules whose scope matches. Preserve each rule's exceptions.
  4. Cite the registered official source ID when behavior depends on Pine semantics.
  5. Label local static results structural-only. Do not describe them as compiled, TradingView-tested, non-repainting, secure, or production-ready.
  6. Treat a hash-matching record in verification/tradingview.json as manual evidence only for the recorded file and environment.
  7. If sources conflict, a source is unavailable, or intent is ambiguous, narrow the claim and state what remains unverified.
  8. Never expose credentials or place real webhook secrets in code or output.
  9. Prefer a minimal change, include a validation path, and separate code-ready, tested, published, and live states.

The project is independent and is not affiliated with or endorsed by TradingView.

Active sourced rules

PSAK-ALERT-001 — Selectable alertcondition events

alertcondition() calls create separately selectable conditions in indicators; calls in a strategy do not create selectable alertcondition alerts.

Scope: Pine v6 indicator and strategy alert API selection.

Why: The alert creation UI exposes indicator alertcondition() events separately, while strategy alert choices use other event mechanisms.

Read the full file on GitHub · 320 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. yesterday First seen · 320 lines · 3,294 tokens per session scan A 2536f25bc3c4

Subscribe to this mod's changes

pinescriptv6 pine-script.instructions.md is an instructions file published in the GitHub repository trugurpala/pinescriptv6 (2 stars, last pushed 29d ago), licensed MIT. It adds 3,294 tokens to every session, about $0.0165 per session on Opus 5. A static security scan graded it A with 0 findings. It is 97% identical to pinescriptv6 copilot-instructions.md, differing in 3 lines, and is treated as a copy.