aai-coding 답이 포함되어 있습니다. AI의 공유 구성, 기술 및 도구 Claude Code 및 Codex. 팀의 코딩 및 쓰기 지침, 도구 권한 및 Python 워크플로를 정의합니다. LLM 설정 하네스 다음 하기 전에이 README를 읽아야 합니다 SETUP.md. 아래 디자인 결정은 기존 설정의 광고 사용자에 대한 컨텍스트를 제공합니다.

시작하기

답변이 필요하지 않습니다. AI 계정 또는 기존 작업 공간. SETUP.md는 선택된 디렉토리의 작업 공간으로 시작하며, Quickws에 의해 관리됩니다. 그 다음 하네스 구성을 다룹니다.

작업 공간은 하나의 uv 환경을 공유하는 별도의 Git 체크 아웃을 보유하고 있습니다. Python 프로젝트는 편집 가능한 설치를 사용합니다. 체크 아웃의 변경은 제거하지 않고 사용할 수 있습니다.

시작하기:

새로운 환경을 활성화하고 SETUP.md를 따르십시오. public aai-ws baseline에는 aai-coding, fastws, 커널 시작 및 편집 도구가 포함되어 있으며, Claude Hooks에 의해 사용됩니다. 다른 Python 의존도는 패키지로 설치합니다.

Answer.AI 팀 멤버는 AnswerDotAI/private-ws] 대신 AnswerDotAI/aai-ws] 를 명령어로 사용한다. 모두 workspace repos는 ws-sync]를 통해 공유 기본 업데이트를받습니다. 설정 중:

-`repos.

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.