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/xbfighting/tdx2db/claude-mdgit clone --depth 1 https://github.com/xbfighting/tdx2dbWrote 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/xbfighting/tdx2db/claude-md)<a href="https://agentmods.dev/instructions/xbfighting/tdx2db/claude-md"><img src="https://agentmods.dev/badge/instructions/xbfighting/tdx2db/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 | $0.01771 | $0.01771 |
| Opus 5 | $0.00886 | $0.00886 |
| Sonnet 5 | $0.00354 | $0.00354 |
| Haiku 4.5 | $0.00177 | $0.00177 |
Grade C, and why
tdx2db CLAUDE.md scanned grade C 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 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.
Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
rm -rf dist && uv build How it starts
The opening of the file, as written. The whole thing — 97 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
项目概述
tdx2db：从本地通达信(TDX)行情软件读取 A 股数据，增量同步到数据库。是量化分析工作站的数据入口。
本文件面向贡献者（改 tdx2db 代码）。如果你是在消费数据库（查询 daily_data 等表做分析），请读 AGENTS.md——schema、典型查询、陷阱清单都在那里，配套 skill 见 .claude/skills/tdx2db-query/。
常用命令
# 安装依赖（开发模式，含 postgres/mysql 驱动）
pip install -e '.[all]'
# 一键增量同步（日线 + 5/15/30/60 分钟线）— 日常使用这一个命令即可
tdx2db sync
# 单独同步
tdx2db daily --db-only --auto-start --incremental
tdx2db minutes --db-only --auto-start --incremental
# 同步股票列表
tdx2db stock-list --db-only
# 数据库状态一览（只读，不需要 TDX_PATH；--json 机器可读）
tdx2db status
# 板块-个股关系同步（sync 已自动包含，也可单独跑）
tdx2db blocks --db-only
板块数据链（blocks.py，issue #39）：概念/指数/风格 ← T0002/hq_cache/infoharbor_block.dat（文本，板块名 8 字节截断需经 880 码还原全名）；行业 ← tdxhy.cfg X 码 × tdxzs3.cfg 类别 12（881 研究行业多级）；跨市场指数成分 ← spblock.dat；地区 ← base.dbf DY 字段 × tdxzs.cfg 类别 3。全量替换式快照（DELETE+INSERT），与行情表的增量语义不同。旧二进制 block_zs/gn/fg.dat 在新版通达信不存在，pytdx BlockReader 不适用。
python main.py <子命令> 与 tdx2db <子命令> 等价（main.py 是薄封装，保留老用户习惯）。包目录为 tdx2db/（v0.3.0 起从 src/ 改名，发布到 PyPI）。psycopg2-binary/pymysql 为可选依赖（extras: postgres/mysql/all），默认安装仅支持 SQLite。
测试：pytest tests/。CI 矩阵：ubuntu + windows × 3.9/3.11（+ ubuntu 3.10）——Windows 是用户主场景必须覆盖。tests/fixtures/ 存 .day/.lc5 二进制解析 fixture（合成字节，生成器 make_fixtures.py；断言值与生成参数一一对应）。数据正确性验证仍以运行 sync 后检查数据库为准。
发布 PyPI（维护者）
版本号需同步 bump 两处：pyproject.toml 与 tdx2db/__init__.py（教训：v0.3.0 曾漏改后者）。发布 token 为项目级，存本地 .env 的 PYPI_PROJECT_TOKEN（gitignored，勿打印其值）：
rm -rf dist && uv build
UV_PUBLISH_TOKEN=$(grep '^PYPI_PROJECT_TOKEN=' .env | cut -d= -f2-) uv publish
发布后必须在全新 venv pip install tdx2db==<版本> 验证（含从工作目录读 .env 的脚本入口场景，教训见 v0.3.1）。增量/幂等类改动的冒烟必须跑两轮（首轮全量 + 次轮增量）。
架构
四层管道，单向数据流：
CLI (cli.py) → Reader (reader.py) → Processor (processor.py) → Storage (storage.py)
↓ ↓ ↓ ↓
argparse pytdx 读取本地 校验 + 重采样 + 均线 SQLAlchemy 批量写库
命令分发 + .day/.lc5 文件 (OHLCV 校验, resample, 支持增量 ON CONFLICT
同步编排 MA5~MA250) 表名白名单保护
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 · 97 lines · 1,771 tokens per session scan C 99e6bc17e5c3
tdx2db CLAUDE.md is an instructions file published in the GitHub repository xbfighting/tdx2db (149 stars, last pushed 13d ago), licensed MIT. It adds 1,771 tokens to every session, about $0.0089 per session on Opus 5. A static security scan graded it C with 1 finding (recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other instructions, from other repositories
teamdynamix-mcp teamdynamix.instructions.md
Instructions for GitHub Copilot when operating against a TeamDynamix instance via the MCP server.
teamdynamix-mcp copilot-instructions.md
Copilot instructions for selfagency/teamdynamix-mcp, covering github copilot instructions, project goals, mcp architecture rules, typescript standards and error handling rules.
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).
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.
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.
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.