Skip to content
Agentmart
Submit a tool

AGENTS.md · Usagi-org/ai-goofish-monitor

AGENTS.md from Usagi-org/ai-goofish-monitor: 40 lines covering 项目结构与模块组织, 构建、测试与本地开发, 编码风格与命名约定, 架构与运行时 and more.

Template by Usagi-org

IndexedMIT★ 15,133
Write a review

Chalk Labs

Need help deploying AGENTS.md · Usagi-org/ai-goofish-monitor?

Chalk Labs sets up agents like this inside real teams: connected to your tools, tested on your data, with a human in the loop where it matters.

Book a call

Install

Works with Codex, Cursor, GitHub Copilot, Gemini CLI, OpenCode, Claude Code. Read the repository before you give any tool access to your data.

curl -fsSL https://raw.githubusercontent.com/Usagi-org/ai-goofish-monitor/master/AGENTS.md -o AGENTS.md

Read it and adapt it to your project before use.

Get the weekly diff

The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.

We use your email only for this newsletter. Privacy

About

The AGENTS.md file that Usagi-org/ai-goofish-monitor (15,132 stars) keeps for coding agents. It has 40 lines in 7 sections: 项目结构与模块组织; 构建、测试与本地开发; 编码风格与命名约定; 架构与运行时; 测试指南; 提交与 PR 规范; 安全与配置提示. Use it as a model for your own project's instructions.

Use cases: prompt-engineering

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

What's in it

An AGENTS.md file: instructions coding agents (Codex, Cursor, Copilot, Gemini CLI and others) read before working in a repo.

For
Codex, Cursor, GitHub Copilot, Gemini CLI, OpenCode, Claude Code
Length
40 lines
File
AGENTS.md

Sections

  1. 项目结构与模块组织
  2. 构建、测试与本地开发
  3. 编码风格与命名约定
  4. 架构与运行时
  5. 测试指南
  6. 提交与 PR 规范
  7. 安全与配置提示

First lines (shown under the repo's MIT license)

# Repository Guidelines

## 项目结构与模块组织
- 后端位于 `src/`,入口 `src/app.py`,API 路由在 `src/api/routes/`,服务层在 `src/services/`,领域模型在 `src/domain/`,基础设施在 `src/infrastructure/`。
- 前端在 `web-ui/`(Vue 3 + Vite),视图放于 `web-ui/src/views/`,组件在 `web-ui/src/components/`,构建产物会复制到根目录 `dist/`。
- 测试位于 `tests/`,命名遵循 `test_*.py` 或 `tests/*/test_*.py`。
- 运行数据与资源:`prompts/`、`jsonl/`、`logs/`、`images/`、`static/`、`state/`,配置文件 `config.json` 与 `.env` 位于仓库根目录。

## 构建、测试与本地开发
- 后端开发:`python -m src.app` 或 `uvicorn src.app:app --host 0.0.0.0 --port 8000 --reload`。
- 爬虫任务:`python spider_v2.py --task-name "MacBook Air M1" --debug-limit 3`(可用 `--config` 指定自定义配置)。
- 前端开发:`cd web-ui && npm install && npm run dev`;构建:`cd web-ui && npm run build`(产物复制到根目录 `dist/`)。
- 一键本地启动:`bash start.sh`(自动安装依赖、前端构建并启动后端)。
- Docker:`docker compose up --build -d`,查看日志 `docker compose logs -f app`,停止 `docker compose down`。

## 编码风格与命名约定
- 保持分层:API → services → domain → infrastructure,避免跨层耦合,模块保持精简。
- Python 测试函数命名为 `test_*`,文件与路径遵循上述测试目录规范。
- 使用描述性、任务导向的命名(如爬虫任务名、配置键),与业务含义对应。

## 架构与运行时
- 后端使用 FastAPI 提供 API 与静态资源,爬虫与 AI 推理在独立任务进程中协作,前后端通过 HTTP/Web UI 交互。
- 任务运行会在 `jsonl/` 写入结果、在 `logs/` 留存运行日志、在 `images/` 下载图片,前端监控页面依赖这些数据。
- 默认监听 8000 端口,前端构建后静态文件可由后端或 Docker 镜像直接提供。

## 测试指南
- 测试框架:`pytest`(默认同步测试,无需 `pytest-asyncio`)。
- 运行全部测试:`pytest`;覆盖率:`pytest --cov=src` 或 `coverage run -m pytest`;定向测试:`pytest tests/test_utils.py::test_safe_get`。
- 优先覆盖核心服务、爬虫管道的异常分支与重试逻辑,避免回归。
- PR 前请运行相关测试,新增逻辑补充针对性用例。

## 提交与 PR 规范
- Commit 采用类 Conventional Commits:`feat(...)`、`fix(...)`、`refactor(...)`、`chore(...)`、`docs(...)` 等。
- PR 需说明变更范围与影响模块;UI 变更在 `web-ui/` 提供截图;关联相关 Issue;提及配置或迁移步骤。

## 安全与配置提示
- 复制 `.env.example` 为 `.env`,设置必填项 `OPENAI_API_KEY`、`OPENAI_BASE_URL`、`OPENAI_MODEL_NAME` 等。
- 不要提交真实凭据或 cookies(如 `state.json`);Playwright 需本地浏览器,Docker 镜像已预装 Chromium。
- Web 认证默认 `admin/admin123`,生产环境务必修改,推荐启用 HTTPS 并限制访问来源。

Signals

Stars
15,133
Forks
2,670
Open issues
30
Last commit (this folder)
Jan 13, 2026 (9 months ago)
Last release
Oct 9, 2026 (22 days ago)

From GitHub (fetched Oct 24, 2026).

Details

License
MIT
First seen
Oct 24, 2026
Last checked
Oct 24, 2026

More from Usagi-org

Done for you

Rather not set it up yourself?

Chalk Labs scopes, builds and runs agents for your team: the task audit, the eval harness, the integrations and the weekly ops report. Fixed scope, priced before we start.

See how we build AI agents →Read the case studies

Chalk Labs is a two-founder AI and growth studio. We build AI agents, CRMs and MVPs for Web3 and AI companies, and have shipped 50+ product and token launches.

launches shipped
50+
launches shipped
media placements
500+
media placements
founders on every account
2
founders on every account

Press we've placed: Forbes · CoinDesk · Decrypt · Cointelegraph · The Block

Rahil Jain, Co-founder, Chalk Labs. Ex-Goldman Sachs engineer. You talk to the person who builds it.

Get AGENTS.md · Usagi-org/ai-goofish-monitor running in your business

Tell us what you want to automate. A founder replies within one working day with a plan, not a pitch deck.

Goes to the Chalk Labs founders, not the newsletter. Privacy

Need help deploying AGENTS.md · Usagi-org/ai-goofish-monitor?

CallGet help
Cite this page

AGENTS.md · Usagi-org/ai-goofish-monitor. Agent Mart. https://agentmart.dev/templates/usagi-org-ai-goofish-monitor-agents-md (last updated 2026-10-24)