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 instructions/celineycn/quantdata-plugin/gemini-mdgit clone --depth 1 https://github.com/celineycn/quantdata-pluginWhat 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 | $0.07478 | $0.07478 |
| Opus 5 | $0.03739 | $0.03739 |
| Sonnet 5 | $0.01496 | $0.01496 |
| Haiku 4.5 | $0.00748 | $0.00748 |
Grade A, and why
quantdata-plugin GEMINI.md scanned grade A with 1 finding 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 yesterday.
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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -s -X POST https://api.quantdata.uk/v1/access/free-key \ How it starts
The opening of the file, as written. The whole thing — 426 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Quant Data
Measured market statistics for stocks, ETFs and futures, served over plain HTTP. This context file teaches you, the agent, how to fetch these numbers and — more importantly — how to report them honestly.
The honest summary: the measured edges are 52–56%, published together with their baselines, sample sizes and the places the methods fail. Every percentage in this file traces to a real measurement. None of it is a forecast, and none of it is investment advice.
Base URL: https://api.quantdata.uk · Header: X-API-Key · Keys start qd_
| What | How | Key |
|---|---|---|
| Rolling Brooks price-action events with measured outcome rates, plus a day-type probability read and a shape description | GET /v1/brooks/{symbol} |
Free email key or paid key |
| Weis wave volume-price structure and events | GET /v1/weis/{symbol} |
Free email key or paid key |
| Options max pain per expiration | GET /v1/maxpain/{symbol} |
Free email key or paid key |
| Estimated dealer gamma exposure (GEX) | GET /v1/gamma/{symbol} |
Free email key or paid key |
| Permanently free max pain and GEX pages | https://quantdata.uk/max-pain/{ticker} and https://quantdata.uk/gex/{ticker} |
None |
Authentication and pricing
Read the key from the environment variable QUANTDATA_API_KEY. Never write a key into a
file, into generated code, into a commit, or into a message back to the user.
If the variable is unset, one complete anonymous first-look response may succeed per source per
UTC day. Its legacy-named free_tier object carries access_kind: "anonymous", the reset time,
and the next action.
For continued evaluation, ask the user which email address should receive a free key. Never invent an address. Then make this request:
curl -s -X POST https://api.quantdata.uk/v1/access/free-key \
-H 'Content-Type: application/json' \
-d '{"email":"[email protected]","marketing_opt_in":false,"source":"agent"}'
If Quant Data is connected over MCP, call quantdata_request_free_api_key instead. The raw
qd_ key is delivered only to that inbox and never returned in the REST or MCP result. No login,
password, card or GUI is required. The free key covers all four endpoints, sharing 10 successful
calls per UTC day.
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.
- yesterday First seen · 426 lines · 7,478 tokens per session scan A ad62ba280995
quantdata-plugin GEMINI.md is an instructions file published in the GitHub repository celineycn/quantdata-plugin (1 stars, last pushed 14d ago), licensed MIT. It adds 7,478 tokens to every session, about $0.0374 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other instructions, from other repositories
tasty-agent AGENTS.md
Instructions for ferdousbhai/tasty-agent, covering tasty-agent, delivery, rules, index and commands.
oathscore CLAUDE.md
Claude Code instructions for moxiespirit/oathscore, covering oathscore - claude code instructions, project overview, architecture, key directories and environment variables (railway).
TradingGoose.github.io CLAUDE.md
Claude Code instructions for TradingGoose/TradingGoose.github.io, a project described as: A Multi-Agents LLM Financial Trading Framework for both individual stock analysis & portfolio management.
jesse AGENTS.md
Instructions for jesse-ai/jesse, covering jesse repository guide for ai agents, skills, key characteristics, central framework and technology stack.
quant-mind AGENTS.md
Instructions for LLMQuant/quant-mind, covering quantmind — agent instructions, progressive context loading, what this is, positioning and module map.
polymarket-alpha-bot CLAUDE.md
Instructions for chainstacklabs/polymarket-alpha-bot, covering claude.md, commands, development, pipeline and seed data.