Borrowing it
Nothing to install: this file belongs to Michelia-L/AI-WealthPilot. 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/Michelia-L/AI-WealthPilot/main/AGENTS.mdgit clone --depth 1 https://github.com/Michelia-L/AI-WealthPilotWrote 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/michelia-l/ai-wealthpilot/agents-md)<a href="https://agentmods.dev/instructions/michelia-l/ai-wealthpilot/agents-md"><img src="https://agentmods.dev/badge/instructions/michelia-l/ai-wealthpilot/agents-md/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.
<a href="https://agentmods.dev/instructions/michelia-l/ai-wealthpilot/agents-md"><img src="https://agentmods.dev/badge/instructions/michelia-l/ai-wealthpilot/agents-md.svg" alt="Reviewed on agentmods" width="80" 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 | $0.01978 | $0.01978 |
| Opus 5 | $0.00989 | $0.00989 |
| Sonnet 5 | $0.00396 | $0.00396 |
| Haiku 4.5 | $0.00198 | $0.00198 |
Grade A, and why
AI-WealthPilot 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 2d 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 — 89 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AI WealthPilot — Agent Guide
AI WealthPilot 是面向私人财富管理研究与决策支持的开源工作站。核心由 Python 量化引擎、FastAPI 传输层、Next.js 前端,以及基于 LangGraph 的 AI/IPS 工作流组成。LLM 接入采用 OpenAI-compatible 配置;环境变量可使用 DeepSeek,运行时也可通过应用设置覆盖 endpoint / model / API key。
本文件只放全仓长期有效的规则和导航。进入 web/ 或 guide/ 工作前,还必须阅读该目录下更具体的 AGENTS.md;更深层规则在冲突时优先。
工作原则
- 先读后改:先确认相关代码、测试、配置和最近的局部
AGENTS.md,再修改。 - 以代码事实为准:README、guide、注释或历史 issue 与当前实现冲突时,以可验证的代码和测试为准,并同步修正文档。
- 第一性原理:从用户目标、系统边界和验证结果出发,不因为旧实现或旧文档存在就默认它仍合理。
- 最小必要改动:解决当前问题,不顺手扩张范围;公共抽象只有在重复模式已经明确时再引入。
- 提交匿名:提交信息、PR 描述和解释性文本中不添加 co-author,也不暴露 Agent 身份。
- 文案务实:README / docs / 用户文案只写可验证事实。避免“机构级、企业级、工业级、极致、赋能、world-class、cutting-edge、seamless”等无法由代码或测试支撑的包装词。
- 维护指令分层:几乎影响所有任务的规则放这里;只影响某个子树的规则放最近的子目录
AGENTS.md。
产品与数据边界
- 本项目用于 research、education、technical evaluation 与 decision support。不要把输出描述为持牌投资建议、监管认证、保证收益或已执行交易。
- 组合权重、IPS、再平衡金额和退休模拟均是模型输出或建议性结果;除非代码明确实现,否则不得暗示下单、托管、税务处理或经纪账户同步。
- Demo fixture、synthetic market data、回放报告和样例客户不得用于宣称真实历史业绩、真实客户结果或实时 LLM 质量。
- 用户画像、API key、token、连接串和其他敏感配置不得写入日志、测试夹具、提交内容、截图或用户可见错误信息。新增调试输出前先检查是否会暴露这些字段。
- Live LLM 请求会向配置的模型服务发送完成任务所需的画像或报告上下文;新增 LLM 路径时保持最小数据传递原则,并复用统一配置入口。
架构地图
src/:领域与计算核心。src/portfolio/:组合构建、风险、回测、退休与相关量化逻辑。src/data/:市场数据适配与派生数据。src/agents/:LLM 顾问、IPS 工作流、报告/IPS 存储与 demo fixture。src/visualization/:Plotly 图表构建。- 金融模型、量化规则和可复用领域逻辑应放在
src/,不要复制到 API 或前端。
api/:传输、持久化和任务编排。 FastAPI 路由负责验证、调用src/、组装响应;api/db.py、api/tasks.py等可以拥有持久化与后台任务生命周期逻辑,但不要在这里重新实现量化/领域规则。Pydantic API 模型集中在api/schemas.py。web/:Next.js 应用。 Web 专属的数据访问、i18n、设计系统、测试与 Next.js 规则见web/AGENTS.md。guide/:MkDocs Internals 站点。 写作纪律与构建要求见guide/AGENTS.md。docs/:工程记录与被代码/README 引用的资产。 包括 known issues、迁移记录、IPS reference 和 screenshots;它不是 MkDocsdocs_dir。
API 与本地化
- 用户可见的 API 文案使用
X-Locale(en/zh,缺省en)并统一走api/i18n.py;路由里不要新增内联中文错误文案。 - 新增 API endpoint 时,通常同时需要:路由、
api/schemas.py中的模型,以及正常/404/422 等相关测试。 src/中会直接产出用户可见文本的计算函数,应显式接收 locale 或由上层传入,不要读取 Web cookie 或 Next.js 状态。
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.
- 2d ago Changed · +19 lines · -1,078 tokens per session ca98a0c219ee
- 5d ago Changed · +1 lines · +93 tokens per session 273cbfb2ca5b
- 9d ago First seen · 69 lines · 2,963 tokens per session scan A 86586f451237
AI-WealthPilot AGENTS.md is an instructions file published in the GitHub repository Michelia-L/AI-WealthPilot (2 stars, last pushed today), licensed MIT. It adds 1,978 tokens to every session, about $0.0099 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.
deepseek-harness AGENTS.md
AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.