Borrowing it
Nothing to install: this file belongs to Chasen-Liao/FinTrack. 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/Chasen-Liao/FinTrack/main/AGENTS.mdgit clone --depth 1 https://github.com/Chasen-Liao/FinTrackWrote 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/chasen-liao/fintrack/agents-md)<a href="https://agentmods.dev/instructions/chasen-liao/fintrack/agents-md"><img src="https://agentmods.dev/badge/instructions/chasen-liao/fintrack/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 5.1 | $0.01230 | $0.01230 |
| Opus 5 | $0.00615 | $0.00615 |
| Sonnet 5 | $0.00246 | $0.00246 |
| Haiku 4.5 | $0.00123 | $0.00123 |
Grade A, and why
FinTrack 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 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 — 70 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
本文件为进入 PokieTicker / FinTrack 仓库的 AI 编码代理提供项目级默认指引。目标只有两个：
- 先理解实验语境、目录分层与约束
- 再做小而准、可验证、尽量不外溢的修改
开始前先读
- 总览与架构：
README.md - 课程要求：
项目七_基于AI算法的量化交易策略_实验要求.md - 当前实验结果：
量化交易策略结果.md - 设计文档：
docs/superpowers/specs/2026-04-25-ai-quant-strategy-backtest-design.md
仓库定位
- 后端：
FastAPI+SQLite+Polygon+LLM - 前端：
React 19+TypeScript+Vite+D3 - 机器学习：特征工程、
XGBoost/LSTM、推理、策略回测 - 仓库同时包含课程文档、实验结果与报告草稿；除非用户明确要求，不要主动修改这些教学材料
目录分层
backend/api/：API 入口与路由；优先在现有 router 中扩展backend/pipeline/：新闻分层处理、对齐、相似度backend/ml/：特征、训练、推理、回测、模型元数据backend/llm/：LLM 客户端封装backend/polygon/：行情/新闻数据访问frontend/src/：页面、组件、样式、i18ntests/：测试，重点覆盖 ML 与回测逻辑
默认工作方式
- 先判断任务属于
api / pipeline / ml / frontend / docs哪一层，再决定改动位置。 - 优先最小改动，复用现有函数、路由、数据结构和模式，不为了“更优雅”引入新架构。
- 不打破分层边界：API 负责输入输出，pipeline 负责新闻处理，ml 负责特征、训练、推理与回测。
- 不硬编码密钥、模型名、地址或环境差异；继续使用
.env、配置模块或现有 settings。 - 变更接口、模型输出或数据结构时，优先保持兼容；如果必须变更，要同步更新调用方与测试。
- 遇到歧义时先判断影响面：如果会影响架构、数据含义、用户体验、安全性或破坏现有产物，应先确认；否则可做最合理假设，但完成后要说明。
项目特有约束
- 涉及交易日对齐、
T+N收益、标签生成或回测时，必须显式避免前视偏差。 backend/ml/models/存放现有模型产物与回测 JSON；除非用户明确要求重新训练，不要覆盖、重写或清理。- 修改 LLM 相关逻辑时，注意全局配置与 Layer1 独立配置可能不同，不要默认两者完全一致。
- 新增 SQLite schema、字段或迁移逻辑前，先检查
backend/migration.py与现有初始化流程。 - 后端 CORS 当前已允许
5173和7777；前端端口、调用地址或部署方式有变动时，要一并验证。
验证要求
- 先把请求转换成可验证的成功标准，再实施修改。
- 修改
backend/ml/、strategy_backtest.py、特征工程、收益计算、标签生成时，尽量补或更新tests/。 - 修改 API 序列化字段时，至少检查受影响路由和前端调用点是否一致。
- 修改前端图表、页面或数据字段时，至少完成一次构建验证；如条件允许，再补充实际页面检查。
- 完成后明确区分：哪些已经验证，哪些因环境、数据或时间限制尚未验证。
常用命令
- 后端启动：
python -m uvicorn backend.api.main:app --reload --host 127.0.0.1 --port 8000 - Python 测试：
pytest tests/ -v - 前端开发：
cd frontend && npm run dev - 前端构建：
cd frontend && npm run build - 前端检查：
cd frontend && npm run lint
专用 Agents
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 · 70 lines · 1,230 tokens per session scan A fddba9da09f0
FinTrack AGENTS.md is an instructions file published in the GitHub repository Chasen-Liao/FinTrack (5 stars, last pushed 2mo ago), licensed MIT. It adds 1,230 tokens to every session, about $0.0062 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
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.
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).
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).
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.
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.