aai-coding 包含 Answer.AI 共享的 Claude 代码和 Codex 配置、技能和工具。它定义了团队的编码和写作指导、工具权限以及 Python 工作流程。设置 harness 的 LLM 应先阅读此 README，然后再遵循 SETUP.md。以下设计决策也为用户提供现有设置的建议。

开始

你不需要 Answer.AI 账户或我们现有的工作空间。SETUP.md 从你选择的目录中的一个工作区开始，由fastws管理。然后它会介绍束带配置。

工作区包含独立的 Git 检查，共享一个 UV 环境。其 Python 项目使用可编辑安装。检查窗口的更改无需重新安装即可访问。

开头：

激活新环境并遵循 SETUP.md。公开的 aai-ws 基线包括 aai-coding、fastws、内核启动和编辑工具，以及 Claude 钩子使用的工具。其他 Python 依赖以包形式安装。

Answer.AI 团队成员在该命令中使用 AnswerDotAI/private-ws 而非 AnswerDotAI/aai-ws。两个工作区仓库通过 ws-sync 共享基线更新。无论哪种配置：

• ‘回收’。

aai-coding

aai-coding contains Answer.AI’s shared configuration, skills, and tools for Claude Code and Codex. It defines the team’s coding and writing guidance, tool permissions, and Python workflows. An LLM setting up the harness should read this README before following SETUP.md. The design decisions below also provide context for advising users of an existing setup.

Getting started

You do not need an Answer.AI account or our existing workspace. SETUP.md starts with a workspace in a directory you choose, managed by fastws. It then covers harness configuration.

The workspace holds separate Git checkouts sharing one uv environment. Its Python projects use editable installs. Changes in a checkout are available without reinstalling it.

Start with:

uvx --from 'fastws-cli>=0.0.14' ws-setup AnswerDotAI/aai-ws ~/aai-ws

Activate the new environment and follow SETUP.md. The public aai-ws baseline includes aai-coding, fastws, kernel startup and editing tools, and tools used by the Claude hooks. Other Python dependencies install as packages.

Answer.AI team members use AnswerDotAI/private-ws instead of AnswerDotAI/aai-ws in that command. Both workspace repos receive shared baseline updates through ws-sync. In either setup:

• repos.txt holds the shared baseline.
• Gitignored repos-local.txt holds personal extras.
• fastws creates and maintains the workspace’s untracked pyproject.toml.

Reuse existing workspaces. Do not run ws-setup on them. See the team migration instructions.

Tool workflows

Claude Code and Codex use persistent kernels for Python, file inspection, searching, notebooks, and most edits. Pyskills provide the tools; exhash provides hash-verified editing. Use Bash for shell commands, builds, and Git. Native tools remain available where the installed skills call for them.

Run ordinary Claude Code or Codex with clikernel-mcp registered as an MCP server. Each agent has its own kernel and Python state. Claude’s clikernel-hook supplies subagent identity; Codex isolates its MCP sessions without that hook.

Claude uses the persistent-python and pyskills host skills. Codex uses kernel-notebook-editing from skills/clikernel. Its cli-notebook-editing skill applies only when the user explicitly requests working without a kernel. Setup links the existing skills without changing them.

Task guidance lives in pyskills. A pyskill is a Python module docstring, listed by list_pyskills() and read with doc(). Pyskills are versioned, released, and installed with their Python packages.

What is in here

The repository contains:

• aai_coding/: Python pyskills and the hook implementation, listed below.