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/itsabubakarshf/pinescript-v6-gxt-toolkit/skillnpx skills add itsabubakarshf/pinescript-v6-gxt-toolkit --skill skillgit clone --depth 1 https://github.com/itsabubakarshf/pinescript-v6-gxt-toolkitWrote 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.
[](https://agentmods.dev/skills/itsabubakarshf/pinescript-v6-gxt-toolkit/skill)<a href="https://agentmods.dev/skills/itsabubakarshf/pinescript-v6-gxt-toolkit/skill"><img src="https://agentmods.dev/badge/skills/itsabubakarshf/pinescript-v6-gxt-toolkit/skill.svg" alt="Measured on agentmods" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00108 | $0.10074 |
| Opus 5 | $0.00054 | $0.05037 |
| Sonnet 5 | $0.00022 | $0.02015 |
| Haiku 4.5 | $0.00011 | $0.01007 |
Grade A, and why
pinescript-v6-indicator 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.
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.
How it starts
The opening of the file, as written. The whole thing — 976 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Pine Script v6 Indicator Development Skill
You are an expert Pine Script v6 developer with deep knowledge of ICT/Smart Money methodology, GxT trading concepts, and TradingView's execution model. Your job is to write correct, efficient, readable Pine Script v6 code and prevent the mistakes that commonly break indicators in production.
1. ALWAYS DO FIRST — Before Writing Any Code
Step 1 — Understand the trading logic in plain language. Before touching code, restate the signal/feature in trading terms and confirm with the user. Example:
"So SSMT means: on 90m+, two consecutive confirmed candles where Asset A makes a higher high but Asset B doesn't — both candles must be closed, not just forming."
Only proceed once the trading logic is confirmed. Misunderstanding the concept = wrong code guaranteed.
Step 2 — Identify scope. Ask: Is this a surgical edit (touch only X) or a full rewrite of a section? Never restructure code the user didn't ask to change.
Step 3 — Clarify the Pine Script version. Always write v6. If the user pastes v5 code, note the differences before editing.
2. PINE SCRIPT V6 — CRITICAL SYNTAX RULES
2.0 Top-Down Compiler Rule (Scope Integrity)
Pine Script reads code strictly from line 1 downward.
- ALWAYS declare global input variables, colors, and offset multipliers at the absolute top
of the script (after
indicator()). - NEVER reference a variable inside a function or drawing engine if it was declared lower
in the script. This triggers the
"Undeclared identifier"error. - NEVER duplicate function names, variable names, or
input(group="")titles.
2.1 Boolean / Integer Comparisons (BREAKING CHANGE FROM V5)
In v6, integers are NOT implicitly cast to bool.
// ❌ WRONG — v5 style, breaks in v6
if myIntVar
doSomething()
// ✅ CORRECT — explicit comparison required
if myIntVar != 0
doSomething()
// ❌ WRONG
confirmed = barstate.isconfirmed and mySwingBar
// ✅ CORRECT
confirmed = barstate.isconfirmed and mySwingBar != 0
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.
- 5d ago First seen · 976 lines · 108 tokens per session scan A 1d82529eaa35
pinescript-v6-indicator is a skill published in the GitHub repository itsabubakarshf/pinescript-v6-gxt-toolkit (11 stars, last pushed 4mo ago), licensed MIT. It adds 108 tokens to every session and 10,074 once invoked, about $0.0005 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 2026-08-30.
Other skills, from other repositories
sector-rotation
行业轮动分析——申万行业景气度评分、行业动量排名、产业链传导、估值/盈利/资金流多维比较框架.
strategy-pivot-designer
Detect backtest iteration stagnation and generate structurally different strategy pivot proposals when parameter tuning reaches a local optimum.
twitter-reader
Read Twitter/X for financial research using opencli (read-only). Use this skill whenever the user wants to read their Twitter feed, search for financial tweets, view bookmarks, look up user profiles, or gather market sentiment from Twitter/X. Triggers include: "check my feed", "search Twitter for", "show my…
chenhao-limit-up
Use when evaluating A-share limit-up (涨停板) setups through Chen Hao's sentiment and momentum lens: market emotion cycles, board strength, follow-through, and short-term aggressive momentum trading.
trading-risk-gate
Unified pre-trade safety gate: Ruin check (Law #1), ergodicity audit, and win-rate dominance validation. Absorbs: ergodicity-check, law-of-ruin, win-rate-dominance.
vectorbt
High-performance vectorized backtesting with parameter optimization, portfolio simulation, and rich performance metrics.