hermes-finance

hermes-finance is a cursor rule for Cursor from Lzh-xbccz/hermes-finance. It costs 272 tokens per session, scanned A, original, MIT.

Project rules for Hermes Finance's market-analysis workflow and its finance tool entry points. They specify which server or command-line fallbacks to use and what a complete market report must contain.

In plain words
What is it for?
Use them when running Hermes Finance analyses, choosing fallback commands, consulting the relevant analysis framework and writing full reports with evidence, counterchecks and final direction.
Why use it?
They keep analyses consistent, require source failures and uncertainty to be stated, and prevent incomplete evidence from being presented as a confident trade direction.

Cursor rule for Cursor

Written for Cursor: installed under .cursor/.

Needs its repository: it runs a file that does not travel with it, so clone the repository first. The line is python3 scripts/czsc_analyze.py BTCUSDT --freqs 4h,15m --report.

Good fit Use them when running Hermes Finance analyses, choosing fallback commands, consulting the relevant analysis framework and writing full reports with evidence, counterchecks and final direction.

Compare 6 cursor rules from other repositories ↓
Install

Getting it into your agent

It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.

Clone the repo
git clone --depth 1 https://github.com/Lzh-xbccz/hermes-finance
agentmods
npx agentmods add rules/lzh-xbccz/hermes-finance/hermes-finance

Made for: Cursor.

Wrote 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.

agentmods badge for hermes-finance

README.md
[![agentmods](https://agentmods.dev/badge/rules/lzh-xbccz/hermes-finance/hermes-finance/github.svg)](https://agentmods.dev/rules/lzh-xbccz/hermes-finance/hermes-finance)
Your own site
<a href="https://agentmods.dev/rules/lzh-xbccz/hermes-finance/hermes-finance"><img src="https://agentmods.dev/badge/rules/lzh-xbccz/hermes-finance/hermes-finance/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.

agentmods 80×15 button for hermes-finance

Your own site · 80×15
<a href="https://agentmods.dev/rules/lzh-xbccz/hermes-finance/hermes-finance"><img src="https://agentmods.dev/badge/rules/lzh-xbccz/hermes-finance/hermes-finance.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 272 This file is loaded in full into every session.
When invoked 272 The same file — it is already loaded in full.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00272 $0.00272
Opus 5 $0.00136 $0.00136
Sonnet 5 $0.00054 $0.00054
Haiku 4.5 $0.00027 $0.00027

Measured 12d ago against content hash 35b0451aedf0, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

hermes-finance 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.

.cursor/rules/hermes-finance.mdc · 23 lines

What it actually says

Hermes Finance

Prefer the project MCP server from .cursor/mcp.json when it is available. The server is hermes-finance.

Use these fallback commands:

python3 -m hermes_finance route BTC
python3 -m hermes_finance fetch crypto BTC --blocks all
python3 -m hermes_finance analyze crypto BTC --blocks all
python3 -m hermes_finance analyze futures CL
python3 scripts/czsc_analyze.py BTCUSDT --freqs 4h,15m --report

Read the relevant skills/*/SKILL.md framework before writing a final market view. Treat CZSC as confirmation, separate raw facts from inference, and state source failures.

For every market analysis request, do not write a compressed summary. Fetch full data, run CZSC when available, and answer with the full eight dimensions plus 七维主判断, 方向质量门槛, 反向审计, 缠论确认, and 最终方向. Do not force 做多 / 做空; mixed, stale, incomplete, or contradicted evidence must end as 观望, 震荡, or 无方向优势.

Changes

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.

  1. 12d ago First seen · 23 lines · 272 tokens per session scan A 35b0451aedf0

Subscribe to this mod's changes

hermes-finance is a cursor rule published in the GitHub repository Lzh-xbccz/hermes-finance (24 stars, last pushed 2mo ago), licensed MIT. It adds 272 tokens to every session, about $0.0014 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.