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/paulieb89/pinescript-mcp/pinenpx skills add paulieb89/pinescript-mcp --skill pinegit clone --depth 1 https://github.com/paulieb89/pinescript-mcpWhat 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 | $0.00216 | $0.02115 |
| Opus 5 | $0.00108 | $0.01058 |
| Sonnet 5 | $0.00043 | $0.00423 |
| Haiku 4.5 | $0.00022 | $0.00212 |
Grade A, and why
pine 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 3d 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 — 127 lines — stays where its author put it; the contents beside it link to each section on GitHub.
pine — Pine Script v6 authoring
You are writing Pine Script v6 for TradingView. Your single most important job is to never emit a function call you have not validated against the v6 allowlist. Pine Script's compiler is unforgiving and TradingView users iterate by copy-paste, so a hallucinated ta.adx() or a stray study() wastes their time. This skill exists to prevent that.
Follow the seven-step authoring loop below on every invocation. Do not skip steps. Do not reorder them.
Authoring loop
1. Clarify intent — at most one question, only if essential
If the user's request is missing a load-bearing detail, ask exactly one focused question. Otherwise proceed.
Load-bearing details (ask only if absent and not inferable):
- Overlay on price chart, or separate pane? (indicator only)
- Indicator or strategy? (i.e. plotting signals vs placing simulated orders)
- Specific inputs/parameters the user wants exposed (lengths, sources, thresholds)
Do not ask about colour schemes, label text, code style, or anything cosmetic. Make a reasonable default and proceed.
2. Route via the manifest
Read the docs://manifest MCP resource first. It is the routing index for the Pine v6 doc corpus. Identify the doc paths most relevant to the functions and concepts the script will need (e.g. reference/functions/ta.md, concepts/strategies.md, concepts/timeframes.md).
For exact API terms (ta.rsi, request.security, repainting), call resolve_topic to jump directly to the right doc.
3. Read the relevant doc sections
Prefer get_section over get_doc. Large doc files (ta.md, strategy.md, drawing.md) blow context if read whole. Use list_sections to enumerate ## headers, then get_section for just the section you need.
For each function the script will call, you must have seen its actual signature, parameter order, and return type — not your memory of it. Pine v6 renamed and re-tupled enough functions that memory is unreliable.
4. Draft the code
What ships with it
3 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.
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.
- 3d ago First seen · 127 lines · 216 tokens per session scan A accbff47a394
pine is a skill published in the GitHub repository paulieb89/pinescript-mcp (9 stars, last pushed 7d ago), licensed MIT. It adds 216 tokens to every session and 2,115 once invoked, about $0.0011 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
property-report
UK property analysis: comparable sales, EPC ratings, rental yields, stamp duty, market context. Use to analyse a property, value a house, check what a place is worth, compare area prices, assess rental yield, or pull a property report. Trigger on any request involving a specific UK address or postcode where the user…
property-search
UK property deal sourcing and investment screening. Use when the user wants to FIND properties matching criteria — budget, area, yield target, property type. Triggers on searching and browsing intent: "find me", "source deals", "what's available in", "looking for BTLs", "search for properties under £X", "show me flats…
high-risk
High-risk overlay for Bitkub swing trading. Up to 3% risk per trade, BTC + ETH + top-10 altcoins allowed, no minimum cash reserve floor, shorter entry timeframe. Use when asked to trade aggressively, maximize returns, or "high risk". Applies looser filters on top of the playbook — read this first, then follow the…
playbook
Playbook for swing-trading the long side on Bitkub (THB pairs) using the gokub-mcp tools. Use when asked to find a trade, screen coins, evaluate an entry, size a position, place/manage an order, or review trading performance on Bitkub. Encodes the risk rules, the screen→regime→signal→size→validate→place→manage→log…
low-risk
Low-risk overlay for Bitkub swing trading. BTC-only, 1% risk per trade, cash reserve enforced. Use when asked to trade safely, trade conservatively, or "low risk". Applies stricter filters on top of the playbook flow — read this first, then follow the playbook.
vibe-trading
Professional finance research toolkit — backtesting (10 engines + benchmark comparison panel), factor analysis, Alpha Zoo (462 pre-built alphas across qlib158/alpha101/gtja191/academic/fundamental), options pricing, 90 finance skills, 30 multi-agent swarm teams, Trade Journal analyzer, and Shadow Account (extract →…