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 skills add mphinance/alpha-skills --skill broker-mcp-selectorgit 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/broker-mcp-selector)<a href="https://agentmods.dev/skills/mphinance/alpha-skills/broker-mcp-selector"><img src="https://agentmods.dev/badge/skills/mphinance/alpha-skills/broker-mcp-selector/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/mphinance/alpha-skills/broker-mcp-selector"><img src="https://agentmods.dev/badge/skills/mphinance/alpha-skills/broker-mcp-selector.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00120 | $0.02063 |
| Opus 5 | $0.00060 | $0.01032 |
| Sonnet 5 | $0.00024 | $0.00413 |
| Haiku 4.5 | $0.00012 | $0.00206 |
Grade A, and why
broker-mcp-selector 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 12d 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 — 146 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Broker MCP Selector
Overview
The rest of the Alpha Skills suite is the brain — it screens, scores, detects regimes, and produces a trade plan. This skill is the hands: it answers the next question, "where do I actually place this order, and is it safe to let an agent do it?"
It selects a broker MCP server for execution based on what the user trades, where they are, and how much autonomy they're comfortable giving an agent — then walks them through connecting it with safe defaults.
The authoritative, continuously re-verified data behind this skill lives in
awesome-broker-mcp — a directory
where every entry was opened and read at the source (the broker's own docs or the server's
own repo). A condensed snapshot ships in references/brokers.md; always prefer the live
list for the final decision, because this space moves fast and a stale entry is how
someone wires an agent to the wrong thing.
When to Use
Invoke this skill when the user wants to:
- "Actually place the trade" / "submit this order" / "execute this"
- "Connect my agent to my brokerage" / "wire up execution"
- "Which broker can Claude trade through?" / "does have an MCP server?"
- "Set up an auto-trader" / "automate my strategy" (pair with
ghost-auto-trader) - "Is it safe to let an AI place orders on my account?"
- Move from a plan produced by any screener/analysis skill to a live or paper order
- Choose between broker MCP servers, or check if one is read-only vs. trade-capable
The two questions that decide almost everything
Before recommending anything, establish these — they collapse the whole option space:
- Who wrote the server, and can it actually place an order?
✅ Trades— places a real order on its own tool call.📝 Draft only— builds the order; the human submits it in the broker's UI. The server physically cannot submit (e.g. Interactive Brokers).👁️ Read-only— cannot place an order. Often official and deliberate. Most people wiring up an LLM for analysis want exactly this.- "Has an MCP server" ≠ "can trade." Some official servers are docs-only or read-only; some community repos claim MCP but never register a trading tool. Verify the tool surface, not the marketing.
What ships with it
2 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.
- 12d ago First seen · 146 lines · 120 tokens per session scan A 3d41a3a32e3c
broker-mcp-selector is a skill published in the GitHub repository mphinance/alpha-skills (22 stars, last pushed 14d ago), licensed MIT. It adds 120 tokens to every session and 2,063 once invoked, about $0.0006 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
An analysis framework for comparing industries in the Chinese A-share stock market, using business conditions, price momentum, valuation, and money flows. It produces rankings and higher- or lower-allocation suggestions.
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
A framework for judging Chinese A-share stocks that have reached the daily price-rise limit, using market mood, sector leadership, and trading momentum.
furusato
A Japanese hometown-tax donation manager for furusato nozei, a system where donations to municipalities can qualify for an income-tax or local-tax deduction. It reads donation receipts, stores donation records, and calculates deduction limits.
reading-receipt
An image-reading workflow for extracting structured information from receipts, invoices, and hometown-tax donation certificates. It can first extract text from PDFs and otherwise read their images.