核心:代理工作台——共享规则、技能和工具
概览
为我的开发环境提供便携智能和工程指导层。 Workbench 是我版本化 Pi、Claude Code 和 Codex 共享行为的地方:代理规则、技能、提示、安全策略、工程原则和可复用的项目健康工具。它将这些规范源转换为每个框架的原生配置,并验证实时结果。 这是一个个人化、观点丰富的仓库。它优化了一个工作流程,而不是试图成为通用的代理平台。 Workbench 是能力栈中的代理智能层,规范描述如下 STACK.md: dotfiles 负责主机配置并安装 Workbench;私有工作流层可以通过其 CLI 合同应用这两个公共层。每个层都是独立的——集成是组合和配置顺序,绝不是跨仓库的 Python 导入。 Workbench 给了我一个地方来回答四个问题: 1.
概述(AI 翻译)
我开发的便携智能和工程指导层 环境。
Workbench 是我把想要的 Pi、Claude Code 和 Codex 的行为版本化的地方 分享:代理规则、技能、提示、安全政策, 工程学说,以及可重复使用的项目健康工具。它让这些成为正规 获取每个线束的原生配置并验证实时结果。
这是一个个人化、观点丰富的仓库。它优化了单一的工作流程 而不是试图成为一个通用代理平台。
堆栈中的位置
Workbench 是上述能力栈中的代理智能层
在STACK.md中,正统观点如下:
dotfiles 为宿主提供资源 和
安装 Workbench;私有工作流层可以通过
它们的CLI契约。每一层都是独立的——集成就是组合和
配置顺序,绝不跨仓库导入 Python 。
它的作用
Workbench 给了我一个地方来回答四个问题:
- 我的编码代理应该如何表现? 共享规则,安全界限,
可重复使用技能,复习指导在线,见于
agents/。 - 这些指令是如何传达每个背带的?
workbench sync翻译
本页由 AI 翻译,技术细节请以原文为准。
README
以下为原文 README 节选,完整内容请查看原文。
Workbench
The portable intelligence and engineering-guidance layer for my development environment.
Workbench is where I version the behavior I want Pi, Claude Code, and Codex to share: agent rules, skills, prompts, safety policy, engineering doctrine, and reusable project-health tools. It turns those canonical sources into each harness’s native configuration and verifies the live result.
This is a personal, opinionated repository. It optimizes one workflow rather than trying to become a general agent platform.
Position in the Stack
Workbench is the agent-intelligence layer of the capability stack described
canonically in STACK.md:
dotfiles host foundation and machine capabilities
↓
workbench reusable agent intelligence and engineering standards
↓
private workflow layers
dotfiles provisions the host and
installs Workbench; private workflow layers may apply both public layers through
their CLI contracts. Each layer stands alone - integration is composition and
provisioning order, never cross-repository Python imports.
What It Does
Workbench gives me one place to answer four questions:
- How should my coding agents behave? Shared rules, safety boundaries,
reusable skills, and review guidance live under
agents/. - How do those instructions reach each harness?
workbench synctranslates and deploys the canonical sources into Pi, Claude Code, and Codex configuration. - Has live configuration drifted?
workbench driftcompares the deployed files and installed plugins directly with the repository. - What engineering judgment should carry between projects? The playbook, health kit, and review skills preserve reusable decisions without coupling them to a particular codebase.
canonical sources
agents/ playbook/ health/
│
workbench sync all
│
┌───────────────┼───────────────┐
│ │ │
Pi Claude Code Codex
rules, settings, rules, settings, rules, TOML,
skills, extensions skills, plugins skills, plugins
│ │ │
└───────────────┼───────────────┘
│
workbench drift all
live drift report
The repository is both the source material and the deployment contract. It does not store a snapshot of the machine and compare against that stale observation.
Ownership Boundaries
| Concern | Owner |
|---|---|
| Agent rules, skills, prompts, MCP declarations, hooks, and permissions | Workbench |
| Engineering doctrine, stack guidance, review skills, and portable health tooling | Workbench |
推荐工具
换一个关键词,或者移除筛选条件。
安装
npx skillfish add e-m-albright/workbench