经 AI Skill Hub 精选评估,Probity 获评「推荐使用」。这款Agent工作流在功能完整性、社区活跃度和易用性方面表现出色,AI 评分 7.5 分,适合有一定技术背景的用户使用。
Probity 是一套完整的 AI Agent 自动化工作流方案。通过可视化的节点编排,将复杂的多步骤任务拆解为清晰的自动化流程,实现全程无人值守的智能处理。支持与数百种外部服务和 API 无缝集成,适合构建数据处理管线、业务自动化和 AI 辅助决策系统。
Probity 是一套完整的 AI Agent 自动化工作流方案。通过可视化的节点编排,将复杂的多步骤任务拆解为清晰的自动化流程,实现全程无人值守的智能处理。支持与数百种外部服务和 API 无缝集成,适合构建数据处理管线、业务自动化和 AI 辅助决策系统。
# 方式一:npm 全局安装 npm install -g probity # 方式二:npx 直接运行(无需安装) npx probity --help # 方式三:项目依赖安装 npm install probity # 方式四:从源码运行 git clone https://github.com/nizos/probity cd probity npm install npm start
# 命令行使用
probity --help
# 基本用法
probity [options] <input>
# Node.js 代码中使用
const probity = require('probity');
const result = await probity.run(options);
console.log(result);
# probity 配置说明 # 查看配置选项 probity --config-example > config.yml # 常见配置项 # output_dir: ./output # log_level: info # workers: 4 # 环境变量(覆盖配置文件) export PROBITY_CONFIG="/path/to/config.yml"
Probity blocks AI coding agents from breaking your rules — adding production code without a failing test, disabling lint rules instead of fixing the issue, reaching for rm -rf when something more targeted would do. It works through your agent's existing hook system.
<p align="center"> <img src="docs/assets/probity-tdd-demo.gif" alt="Probity blocking an over-implementation attempt" width="1200"> </p>
Probity is the successor to TDD Guard (~2k stars, ~200k downloads), now with one config across Claude Code, Codex, and GitHub Copilot CLI.
npm install -D @nizos/probity
Create probity.config.ts at your project root:
import {
defineConfig,
enforceTdd,
forbidCommandPattern,
forbidContentPattern,
} from '@nizos/probity'
export default defineConfig({
rules: [
forbidCommandPattern({
match: /rm\s+-rf/,
reason: '`rm -rf` is too broad; remove specific paths instead.',
}),
{
files: ['src/**', 'test/**'],
rules: [
enforceTdd(),
forbidContentPattern({
match: 'eslint-disable',
reason: 'Fix the lint violation rather than disabling the rule.',
}),
],
},
],
})
Then wire it into your agent. One-time setup per agent.
Does it work with my agent? Probity currently works with Claude Code, Codex, and GitHub Copilot CLI, with more coming.
Does it work with my language? Probity reads each agent's session transcript directly, so there are no per-framework reporters to install. It works with any language and test runner that your agent can work with.
Does Probity need its own API key or subscription? No. AI-validated rules use each vendor's official SDK and reuse whatever authentication your agent already has, so Probity doesn't require its own access or billing.
I'm already using TDD Guard. Should I switch? Probity's TDD validation reads the session transcript, which lets it handle refactors and multi-step edits more reliably. It also supports more agents and is safe with parallel sessions. The one gap: TDD Guard has a lint integration that Probity doesn't yet match.
Probity是一个有潜力的AI工作流项目
AI Skill Hub 为第三方内容聚合平台,本页面信息基于公开数据整理,不对工具功能和质量作任何法律背书。
建议在沙箱或测试环境中充分验证后,再部署至生产环境,并做好必要的安全评估。
✅ MIT 协议 — 最宽松的开源协议之一,可自由商用、修改、分发,仅需保留版权声明。
AI Skill Hub 点评:Probity 的核心功能完整,质量良好。对于自动化工程师和运维人员来说,这是一个值得纳入个人工具库的选择。建议先在非生产环境试用,再逐步推广。
| 原始名称 | probity |
| 原始描述 | 开源AI工作流:Process discipline for AI coding agents。⭐76 · TypeScript |
| Topics | AI工作流TypeScript |
| GitHub | https://github.com/nizos/probity |
| License | MIT |
| 语言 | TypeScript |
收录时间:2026-06-10 · 更新时间:2026-06-10 · License:MIT · AI Skill Hub 不对第三方内容的准确性作法律背书。
选择 Agent 类型,复制安装指令后粘贴到对应客户端