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/quantgist-technologies/quantgist_mcp/agents-mdgit clone --depth 1 https://github.com/QuantGist-Technologies/QuantGist_MCPWrote 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/instructions/quantgist-technologies/quantgist_mcp/agents-md)<a href="https://agentmods.dev/instructions/quantgist-technologies/quantgist_mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/quantgist-technologies/quantgist_mcp/agents-md.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 | $0.00940 | $0.00940 |
| Opus 5 | $0.00470 | $0.00470 |
| Sonnet 5 | $0.00188 | $0.00188 |
| Haiku 4.5 | $0.00094 | $0.00094 |
Grade A, and why
QuantGist_MCP AGENTS.md 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 4d 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 — 55 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md — quantgist-mcp
QuantGist MCP server: 22 tools — 15 read-only (macro events, earnings, markets, discovery) plus 7
account tools (webhooks, API keys, billing) — over two transports from one codebase: stdio
(quantgist-mcp) and streamable-HTTP (quantgist-mcp-http). Thin client over
https://api.quantgist.com/v1. Python 3.10+, low-level mcp SDK.
Consent model: mutating tools (create_webhook, delete_webhook, create_api_key,
create_checkout_session) require confirm: true; without it they make no API call and return
an approval preview. create_checkout_session never charges — it returns a Stripe-hosted checkout
URL a human must open and complete. Once-only secrets ship with a store-securely warning.
CLAUDE.md is the full source of truth (architecture, tool list, release & deploy, rules). Read it
before non-trivial work. This file is the short version for any agent.
Commands
uv sync
uv run quantgist-mcp # stdio server (needs QUANTGIST_API_KEY)
uv run quantgist-mcp-http # HTTP server (PORT/HOST env; /health + /mcp)
uvx ruff check src/ # lint
uv build # sdist + wheel
Test against prod with a real key before shipping: build + clean-install, then a full MCP handshake (initialize → list_tools → call_tool) over both transports.
Layout
src/quantgist_mcp/: server.py (tools, dispatch, stdio main), http.py (HTTP transport),
api.py (async httpx client + per-request key contextvar), formatters.py (dicts → text). All tool
schemas/handlers live in server.py (no tools/ subpackage).
Invariants — do NOT regress
- HTTP serves the MCP app at the mount ROOT (
Mount("/", _root)), neverMount("/mcp")— the sub-mount adds a 307 redirect that breaks strict gateways (Smithery → 502).POST /mcpmust be 200. - Every tool handler returns a
(text, structured_dict)tuple; the dict matches the tool'soutputSchema. Errors returnCallToolResult(isError=True)(not a tuple). - Keep on every tool:
description+ per-param descriptions,title,annotations,outputSchema. - Keep the empty
list_resources/list_promptshandlers (avoids "method not found" in scans). - Never hardcode the API key (env for stdio;
X-API-Keyheader for HTTP).
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.
- 4d ago First seen · 55 lines · 940 tokens per session scan A 2c2cc2efaac8
QuantGist_MCP AGENTS.md is an instructions file published in the GitHub repository QuantGist-Technologies/QuantGist_MCP (2 stars, last pushed 1mo ago), licensed MIT. It adds 940 tokens to every session, about $0.0047 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 instructions, from other repositories
llm-context.py CLAUDE.md
Instructions for cyberchitta/llm-context.py, covering claude.md, working notes (gitignored) and draining the field notes.
openrouter-mcp-multimodal AGENTS.md
AGENTS.md instructions for stabgan/openrouter-mcp-multimodal, covering agent instructions, before you ship, releasing (read this before publishing), short version and version files (must all match package.json).
seekstone CLAUDE.md
Instructions for shaqmughal/seekstone, covering claude.md, what this repo is, commands, the harness itself (run after npm install) and architecture.
Plonk AGENTS.md
AGENTS.md instructions for ostapondo/Plonk, covering agent rules, layout, adding a module, build & verify and code style.
mcp-dockhand copilot-review.instructions.md
Copilot instructions for strausmann/mcp-dockhand: When reviewing pull requests in this repository.
second-brain AGENTS.md
Instructions for LindaHaviv/second-brain, covering instructions for ai coding agents, what to read first, the rules (non-negotiable), common tasks, the sanctioned way and enforcement, not just instructions.