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/jiayuxu0/zipagent/claude-mdgit clone --depth 1 https://github.com/JiayuXu0/ZipAgentWrote 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/jiayuxu0/zipagent/claude-md)<a href="https://agentmods.dev/instructions/jiayuxu0/zipagent/claude-md"><img src="https://agentmods.dev/badge/instructions/jiayuxu0/zipagent/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 | $0.02397 | $0.02397 |
| Opus 5 | $0.01198 | $0.01198 |
| Sonnet 5 | $0.00479 | $0.00479 |
| Haiku 4.5 | $0.00240 | $0.00240 |
Grade C, and why
ZipAgent CLAUDE.md scanned grade C with 2 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 5d 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.
Downloads and executes remote codehighSupply chain
curl | sh runs whatever the server returns today, which is not necessarily what it returned when this was reviewed.
curl -LsSf https://astral.sh/uv/install.sh | sh Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -LsSf https://astral.sh/uv/install.sh | sh How it starts
The opening of the file, as written. The whole thing — 301 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
LiteAgent 是一个轻量级的 AI Agent 框架,设计简洁且易于扩展。项目采用模块化架构,每个模块职责单一明确。
核心架构
模块结构
- agent.py: Agent 核心类,管理代理配置、指令和工具集
- context.py: 对话上下文管理,维护消息历史和 token 统计
- model.py: LLM 接口抽象层,基于 OpenAI 客户端
- runner.py: 执行引擎,处理工具调用循环和对话流程
- tool.py: 工具系统,支持函数装饰器自动转换
设计模式
- 策略模式:Model 抽象基类支持不同 LLM 实现
- 装饰器模式:@function_tool 简化工具创建
- 数据类:广泛使用 @dataclass 减少样板代码
开发环境设置
使用 uv 原生管理(推荐)
# 安装 uv
curl -LsSf https://astral.sh/uv/install.sh | sh
# 克隆项目
git clone https://github.com/JiayuXu0/LiteAgent.git
cd LiteAgent
# uv 会自动创建虚拟环境并管理依赖
# 添加核心依赖
uv add openai pydantic
# 添加开发依赖
uv add --dev pyright ruff pytest pytest-cov pytest-asyncio
# 添加可选依赖
uv add python-dotenv
验证安装
# 检查依赖状态
uv tree
# 检查虚拟环境
uv run python --version
uv run python -c "import liteagent; print('✅ 安装成功')"
环境变量配置
# 创建 .env 文件
MODEL=gpt-3.5-turbo # 或其他支持的模型
API_KEY=your_api_key
BASE_URL=https://api.openai.com/v1 # 可选
常用开发命令
构建和打包
# 使用 uv 构建
uv build
# 构建后的文件在 dist/ 目录
# - liteagent-0.1.0-py3-none-any.whl # wheel 包
# - liteagent-0.1.0.tar.gz # 源码包
# 安装构建的 wheel 包
pip install dist/liteagent-0.1.0-py3-none-any.whl
类型检查
# 使用 uv run 运行 pyright
uv run pyright
# 检查特定目录
uv run pyright src/
# 检查特定文件
uv run pyright src/liteagent/agent.py
代码风格检查
# 运行 ruff 代码检查
uv run ruff check .
# 自动修复可修复的问题
uv run ruff check --fix .
# 格式化代码
uv run ruff format .
# 检查特定文件
uv run ruff check src/liteagent/
运行测试
# 运行所有测试
uv run pytest
# 运行特定测试文件
uv run pytest tests/test_agent.py
# 运行并显示覆盖率
uv run pytest --cov=src/liteagent --cov-report=html
# 运行特定标记的测试
uv run pytest -m unit # 只运行单元测试
uv run pytest -m integration # 只运行集成测试
# 详细输出
uv run pytest -v --cov-report=term-missing
当前项目状态
- ✅ 测试: 37 个测试全部通过
- 📊 覆盖率: 60% (核心模块 90%+)
- 🔧 依赖: 2 个核心,5 个开发依赖
- 📦 包大小: wheel 12.4KB
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.
- 5d ago First seen · 301 lines · 2,397 tokens per session scan C 28335327bcef
ZipAgent CLAUDE.md is an instructions file published in the GitHub repository JiayuXu0/ZipAgent (110 stars, last pushed 1mo ago), licensed MIT. It adds 2,397 tokens to every session, about $0.0120 per session on Opus 5. A static security scan graded it C with 2 findings (downloads and executes remote code, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other instructions, from other repositories
open-swe AGENTS.md
AGENTS.md instructions for langchain-ai/open-swe, covering agents.md, project, commands, architecture and conventions.
LangBot AGENTS.md
AGENTS.md instructions for langbot-app/LangBot, covering agents.md, quick facts, essential commands, where to look and cross-repo sdk work.
open-swe CLAUDE.md
Claude Code instructions for langchain-ai/open-swe, a project described as: An Open-Source Asynchronous Coding Agent.
awesome-ChatGPT-repositories CLAUDE.md
Claude Code instructions for taishi-i/awesome-ChatGPT-repositories, covering awesome-chatgpt-repositories — claude code guide, repository structure, plugin skill (when installed via /plugin), local standalone command (when repo is cloned) and compact data format (plugins/awesome-chatgpt-search/data/).
dify AGENTS.md
AGENTS.md instructions for langgenius/dify, covering agents.md, repository gotchas and frontend workflow.
dify CLAUDE.md
Claude Code instructions for langgenius/dify, a project described as: Build Agentic workflows, RAG pipelines, with rich AI model and tool support on one collaborative workspace. Deploy on cloud, VPC, or self-hosted, so teams move from prototype to production without rebuilding the stack.