Borrowing it
Nothing to install: this file belongs to offbeat-studio/shioaji-mcp. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/offbeat-studio/shioaji-mcp/master/CLAUDE.mdgit clone --depth 1 https://github.com/offbeat-studio/shioaji-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/offbeat-studio/shioaji-mcp/claude-md)<a href="https://agentmods.dev/instructions/offbeat-studio/shioaji-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/offbeat-studio/shioaji-mcp/claude-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 5.1 | $0.01617 | $0.01617 |
| Opus 5 | $0.00809 | $0.00809 |
| Sonnet 5 | $0.00323 | $0.00323 |
| Haiku 4.5 | $0.00162 | $0.00162 |
Grade A, and why
shioaji-mcp CLAUDE.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 6d 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 — 169 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Shioaji MCP Server - Claude Code 專案配置
專案概述
Shioaji MCP Server 是一個提供永豐金證券交易 API 功能的模型上下文協議 (MCP) 伺服器。專案已達到生產就緒狀態,支援完整的交易操作和市場資料存取功能。
任務管理系統
配置狀態: 使用本地 markdown 檔案進行任務管理
- 系統類型: Claude Code 內建 TodoWrite 工具
- 任務追蹤: 透過對話中的 todo list 進行即時追蹤
- 狀態同步: 任務狀態會在每次更新時同步顯示
技術棧和工具
開發環境
- Python: 3.10-3.12
- 套件管理:
uv(優先選擇) - MCP 框架:
mcp>=1.0.0 - 交易 API:
shioaji==1.2.5
程式碼品質工具
- 代碼檢查:
ruff(取代 black, isort, flake8) - 型別檢查:
mypy - 測試框架:
pytestwithpytest-asyncio
部署和分發
- 容器化: Docker with multi-platform support
- 容器註冊表: GitHub Container Registry (ghcr.io)
- CI/CD: GitHub Actions
開發工作流程
代碼提交規範
- 使用 conventional commits 格式:
<type>[optional scope]: <description> - 例如:
feat(trading): add order cancellation functionality - 例如:
fix(auth): resolve connection timeout issues
測試要求
- 所有新功能必須包含對應的單元測試
- 測試覆蓋率應保持在合理水平
- 使用 mock 進行 API 相關測試以避免真實交易
安全考量
- 交易安全: 交易功能預設關閉,需要明確啟用
SHIOAJI_TRADING_ENABLED=true - 憑證管理: 所有敏感資訊透過環境變數管理
- 權限控制: 實施分層權限管理系統
專案架構
src/shioaji_mcp/
├── server.py # MCP 伺服器主程式
├── tools/ # MCP 工具模組
│ ├── contracts.py # 合約搜尋工具
│ ├── market_data.py # 市場資料工具
│ ├── orders.py # 訂單操作工具
│ ├── positions.py # 持倉查詢工具
│ └── terms.py # 服務條款工具
└── utils/ # 共用工具程式
├── auth.py # 身份驗證管理
├── formatters.py # 資料格式化
├── permissions.py # 權限管理
└── shioaji_wrapper.py # Shioaji API 包裝器
期貨帳戶支援
自版本 0.1.1 起,get_positions 和 get_account_balance 工具新增期貨帳戶支援:
使用範例
// 查詢所有帳戶持倉(預設)
{"account_type": "all"}
// 只查詢股票帳戶
{"account_type": "stock"}
// 只查詢期貨帳戶
{"account_type": "futures"}
回應格式差異
- 股票持倉:包含股數、張數計算和持股成本分析
- 期貨持倉:包含合約數量、保證金和損益資訊
- 期貨餘額:額外提供維持保證金、初始保證金等期貨特有欄位
常用命令
開發環境設置
# 安裝開發相依套件
uv sync --extra dev
# 設定環境變數
export SHIOAJI_API_KEY=your_api_key
export SHIOAJI_SECRET_KEY=your_secret_key
export SHIOAJI_TRADING_ENABLED=false # 預設唯讀模式
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.
- 6d ago First seen · 169 lines · 1,617 tokens per session scan A 4d91c9addace
shioaji-mcp CLAUDE.md is an instructions file published in the GitHub repository offbeat-studio/shioaji-mcp (3 stars, last pushed 7mo ago), licensed MIT. It adds 1,617 tokens to every session, about $0.0081 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
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.