quantdata-plugin

# Quant Data — market-statistics skills for AI agents

Measured market statistics for index futures and equities, packaged so an AI agent can use
them and — more importantly — report them honestly. Installs natively into **Claude Code**
(plugin), **Codex CLI** (plugin marketplace) and **Gemini CLI** (extension), all from this
one repository.

| Skill | What the agent gains | Key needed |
|---|---|---|
| `quantdata-daily-bias` | Day-type probabilities for the current session and the measured verdicts on famous price-action claims | Yes |
| `quantdata-weis-wave` | Volume-price wave structure and five Weis events, each with its measured win rate | Yes |
| `quantdata-max-pain` | Options max pain, open-interest walls, put/call ratio, estimated dealer gamma exposure | Optional — free public pages with no key; JSON endpoints for any optionable US stock or ETF with one |

The honest summary of what you get: measured edges of 52–56%, published together with the
places the models fail. There is a section below on exactly that, and it is not buried.

---

## Install

### Claude Code

```bash
/plugin marketplace add celineycn/quantdata-plugin
/plugin install quantdata@quantdata
```

### Codex CLI

The same repository doubles as a Codex plugin marketplace:

```bash
codex plugin marketplace add celineycn/quantdata-plugin
codex plugin add quantdata@quantdata
```

### Any other MCP client (Claude Desktop, ChatGPT, Cursor, VS Code, Zed)

The same four endpoints are a **remote MCP server**. Nothing to install — point the client at:

```
https://api.quantdata.uk/mcp
```

Streamable HTTP, and **no authentication to try it**: it answers on the daily keyless allowance
and returns the same complete responses a subscriber gets. Send `X-API-Key: qd_...` as a header
to lift the limit. A stdio bridge ships in `quantdata/mcp/` for clients that can only launch a
local command; it forwards to the same URL.

Details: [`quantdata/mcp/README.md`](quantdata/mcp/README.md).

### Gemini CLI

The repository is also a Gemini CLI extension. `GEMINI.md` carries the three skill bodies
merged into one context file:

```bash
gemini extensions install https://github.com/celineycn/quantdata-plugin
```

### Then

Start a new session. You do not invoke a skill by name — just ask:

> What kind of day is NVDA having?

> Is the pullback in ES=F happening on low volume?

> Where is max pain for TSLA this Friday?

> Which way is dealer gamma leaning on NVDA?

To check it loaded, ask: *"Which Quant Data skills do you have?"*

### Without the plugin system

A skill is just a folder with a `SKILL.md` in it, so you can also copy them by hand:

```bash
mkdir -p ~/.claude/skills
cp -R quantdata/skills/* ~/.claude/skills/
```

Or project-scoped, committed alongside your code, in `.claude/skills/`.

---

## Try it before paying anything

The free tier is the Max Pain and GEX pages. No key, no account, no card:

```
https://quantdata.uk/max-pain/nvda
https://quantdata.uk/gex/nvda
```

Max pain (the option strike at which option buyers lose the most in aggregate at expiration),
put/call ratio and open interest by expiration, one page per US individual stock, rebuilt
nightly — and a separate GEX page per ticker with net gamma exposure and the zero gamma (flip)
level. Lowercase tickers. `https://quantdata.uk/max-pain` and `https://quantdata.uk/gex` are
the coverage lists.

To check the research before paying for it, read
**<https://quantdata.uk/methodology>** — an ordinary web page, free, no key. It publishes the
fact-check of the trading literature's famous probability claims against 3,946 S&P 500 futures
trading days (2010–2026). The claim that one of the session's extremes forms within the first
90 minutes is usually taught as 90%; the measured figure is 81.2%. The pattern holds across
every claim tested — directionally right, inflated by roughly 7–10 percentage points.

Start there. If the numbers are not the size you expected from an honest test, do not buy.

---

## The paid endpoints

**Every endpoint below answers 10 calls a day with no key at all** — the same complete
response a subscriber gets, not a trimmed sample. Install the plugin, ask a question, and you
will get a real answer before anyone asks you for a card. A key removes the daily limit.

One plan: **$39/month, first 3 days free.** Checkout is self-serve at
<https://quantdata.uk/pricing>, a card is collected up front, and the key is shown immediately
on the page Stripe returns you to. Cancel any time from the Stripe receipt.

| Endpoint | Returns |
|---|---|
| `GET /v1/brooks/{symbol}` | Day-type probabilities over five classes for the session so far |
| `GET /v1/weis/{symbol}` | Volume waves and five named volume-price events with measured win rates |
| `GET /v1/maxpain/{symbol}` | Max pain per expiration, from open interest alone — pure arithmetic, no pricing model |
| `GET /v1/gamma/{symbol}` | Estimated dealer gamma exposure: net GEX, the zero gamma (flip) level, the heaviest strikes |

One key covers all four. The two options endpoints are deliberately separate because the two
figures are not equally reliable: max pain is arithmetic anyone can reproduce from the same
chain, gamma is a Black-Scholes estimate built on an unobservable dealer-positioning
convention. The skills quote the first as a figure and the second as an estimate.

The fact-check verdicts live on <https://quantdata.uk/methodology> as a static table — a web
page to read, free and needing no key, not an endpoint to call.

Keys bought under the older two-product pricing keep working at their original price.

**An AI agent cannot buy this for you.** Card authentication (3-D Secure) requires the
cardholder, so the skills are written to hand you the link and stop rather than attempt a
purchase. That is deliberate.

### Set your key

Never paste a key into `SKILL.md` — those files are meant to be copied, committed and shared.

```bash
# ~/.zshrc (macOS default) or ~/.bashrc
export QUANTDATA_API_KEY="qd_your_key_here"
```

Then open a new terminal, or run `source ~/.zshrc`. Check it:

```bash
curl -s -H "X-API-Key: $QUANTDATA_API_KEY" https://api.quantdata.uk/v1/brooks/SPY
```

For an agent with no shell, the key goes wherever that tool stores secrets — an Actions
authentication field, a credential entry, a `.env` loaded by your runtime. Same rule: a secret
store, not a shared file.

---

## Using these on platforms with no plugin system

Nothing here is specific to any one agent. A `SKILL.md` body is instructions plus an HTTP
contract, so it works anywhere you can set a system prompt and send a request with a custom
header. (Claude Code, Codex and Gemini CLI install natively — see Install above.)

1. Open the `SKILL.md` you want, under `quantdata/skills/`.
2. Copy everything **below** the closing `---` of the YAML header.
3. Paste it into your agent's system prompt, custom instructions or persona field.
4. Replace the `$QUANTDATA_API_KEY` references with whatever your platform calls its secret.

Known to work this way: ChatGPT Custom GPTs (paste into Instructions, and add
`api.quantdata.uk` as an Action with an `X-API-Key` header), Cursor and Windsurf rules files,
Cline, GitHub Copilot instructions, n8n and Dify agent nodes, CrewAI and AutoGen
agent backstories, LangChain system messages, and anything built directly on the OpenAI or
Anthropic SDKs.

If your tool can send one HTTP request with one custom header, it is supported. There is no
SDK, no OAuth flow and no callback URL.

---

## What every one of these skills enforces

These rules are written into each `SKILL.md` and they are the reason the plugin exists:

- **Never present output as a buy or sell recommendation.** The API returns a probability
  distribution and historical frequencies. It does not know your position, account or risk.
  Turning "TrendUp 0.34" into "go long" is the agent inventing advice.
- **Always carry the disclaimer.** Every response has a `disclaimer` field; it travels with the
  numbers.
- **Never claim precision the numbers do not have.** The honest win rates are 52–56%. An agent
  that rounds that into "strong signal" has broken the product.
- **Name the baseline.** 66% top-1 accuracy is meaningless until you also say the
  majority-class baseline is 37%.
- **Flag out-of-distribution use.** The day-type model was trained on S&P 500 E-mini futures.
  A read on a single stock, on gold, or on crypto is descriptive, not validated.
- **At a paywall, relay `message_for_your_human` and stop.** Never retry a 402, and never
  substitute a different data source and present the result as Quant Data output.

## Where this does not work

Publishing this is the point, not a disclaimer:

- **Crypto and gold have a consistent anti-signature.** Of eight pre-registered Bitcoin
  signals, zero confirmed, and `no_supply` reversed direction outright.
- **Chart patterns did not survive testing.** Over 121,000 pattern detections produced an AUC
  of 0.54 — near a coin flip.
- **The Asian session did not transfer.** The pre-registered test of day-type gating on the
  Asian session returned NO_GO.

---

Educational analytics and developer tooling. Not investment advice, not a recommendation to
buy or sell, not a price forecast. Trading involves risk of loss; past performance does not
guarantee future results. Independent research — not affiliated with or endorsed by Al Brooks,
David Weis, or any exchange or broker.

Docs: <https://quantdata.uk/skills> · Questions: quantdata@agentmail.to