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/mphinance/alpha-skills/mph-pinenpx skills add mphinance/alpha-skills --skill mph-pinegit clone --depth 1 https://github.com/mphinance/alpha-skillsWrote 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/mphinance/alpha-skills/mph-pine)<a href="https://agentmods.dev/skills/mphinance/alpha-skills/mph-pine"><img src="https://agentmods.dev/badge/skills/mphinance/alpha-skills/mph-pine.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 5.1 | $0.00059 | $0.02626 |
| Opus 5 | $0.00030 | $0.01313 |
| Sonnet 5 | $0.00012 | $0.00525 |
| Haiku 4.5 | $0.00006 | $0.00263 |
Grade A, and why
mph-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 6d 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 — 167 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Mph Pine
Build TradingView Pine Script v6 indicators that look and behave like the mphinance house stable (channels.pine, ghost_dashboard.pine, ghost_alpha.pine). Faithful math, clean v6, a synthwave dashboard, and a compressed AI-readable payload row so Gemini or Sam can read the chart.
When to invoke
Use when the user asks to build, port, or extend a TradingView indicator or strategy: "write a pine indicator", "tradingview indicator for X", "port this Python signal to Pine", "add alerts to my script", "/mph-pine". If the user names an existing engine (a Python scanner, a screener rule), treat that as the source of truth and port it faithfully before adding extras.
Flow
- Ground on v6 first. Pull current docs (the context7 / pine-script docs MCP, or tradingview.com/pine-script-docs) before writing. Do not trust v5 muscle memory. Confirm the version line is
//@version=6. - Find the source of truth. If porting, read the Python or existing Pine end to end and match field names, constants, and thresholds exactly. Cite the constants in a header comment. Only add new behavior after the faithful port is in place, and say plainly which parts are new.
- Scaffold in house style. Header comment block, palette consts, grouped inputs, calculations, draw, plots, alerts, dashboard. See the templates below.
- Run the v6 landmine checklist (below) against the finished file.
- Scan for em dashes. Search the file for U+2014 and U+2013, including code comments and string literals. Replace with a hyphen or comma. This is the single most common house-rule miss in generated code.
- Hand off for compile. There is no offline Pine compiler. Load the finished script onto the user's clipboard and tell them to paste it into TradingView's Pine Editor, Save, Add to chart, and report any red error. Fix reported errors and reload the clipboard.
- Save and offer to ship. Write to
docs/pine/<name>.pinein the relevant repo. Offer/ship. Never commit without being asked.
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.
- 6d ago First seen · 167 lines · 59 tokens per session scan A 8c84419f1e4a
mph-pine is a skill published in the GitHub repository mphinance/alpha-skills (19 stars, last pushed 8d ago), licensed MIT. It adds 59 tokens to every session and 2,626 once invoked, about $0.0003 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.