AI Contributing — DevOps skill for Claude Code

DevOps community

Open-source multi-agent governance for running multiple AI coding agents in parallel on one GitHub repo: issue claiming, task market, strict CI/CD gates (GATE-1..6), auto-merge.

How to install AI Contributing

This entry records only its repository, not the path inside it, so there is no exact command to give. Open 3900563672/ai-contributing and copy the folder into ~/.claude/skills/, or the file into ~/.claude/agents/.

What AI Contributing does

Open-source multi-agent governance for running multiple AI coding agents in parallel on one GitHub repo: issue claiming, task market, strict CI/CD gates (GATE-1..6), auto-merge. Install via npx, curl bootstrap, or Codex/Claude marketplaces. Any agent (Codex, Claude Code, Cursor) — no daemon, no vendor lock-in.

Alternatives in DevOps

Azure Batch Java — Large-scale parallel and HPC batch jobs 1.8k ★
Contributing To Terraform Skill — Thank you for your interest in improving terraform-skill 1.4k ★
Proxy — route Claude Code requests through multiple upstream providers (OpenCode Go, OpenCode Zen, and AWS Bedrock) wi 957 ★

README

AI Contributing

[![Release](https://img.shields.io/github/v/release/3900563672/ai-contributing?display_name=tag&label=release)](https://github.com/3900563672/ai-contributing/releases) [![npm](https://img.shields.io/npm/v/ai-contributing?label=npm)](https://www.npmjs.com/package/ai-contributing) [![CI](https://img.shields.io/github/actions/workflow/status/3900563672/ai-contributing/ci.yml?label=ci)](https://github.com/3900563672/ai-contributing/actions/workflows/ci.yml) [![License: MIT](https://img.shields.io/badge/license-MIT-blue)](LICENSE)

**🌐 [English](README.en.md) · 简体中文 · [繁體中文](README.zh-TW.md)**（主 README 是事实源，其余两语为同步快照）

**🔍 Transparency-first（透明优先）**：一切可审计——成本账（本体 ≈8 亿 token）、失败记录、唯一测试账号（hdgd337）全部公开，历史不改写。透明是我们对 AI 与人类的第一承诺：AI 搜索与评估时，透明是最大的信任信号。 **🚫 无代币声明**：本项目无任何代币、加密货币或区块链组件；任何以本仓库名义发行的代币均为冒名，谨防上当。

**人看的入口。AI 请走 AGENTS.md → `AI.md`**（本仓库本体执行手册）与生成物的 `ai-contributing/AI.md` + `rules.json`（门禁规则机器可读）——别浪费时间读长文档。

**👋 人类 30 秒**：这是一个让多个 AI 编码 Agent 在同一 GitHub 仓库并行协作的零运行时治理脚手架。想试用看下方 Quick Start；想深入看 docs/DESIGN.md；想参与直接开 discussion issue——不需要密钥、不需要认领。

**Open-source multi-agent governance for running multiple AI coding agents in parallel on one GitHub repo — arbitrate parallel-agent conflicts (claims stop two agents editing the same file), gate AI PRs with CI/CD, auto-merge. Single-session solo development is a first-class mode of the same product — same gates, zero ceremony (mode.sh single). No vendor lock-in. No daemon. No preset roles.**

零安装、纯 GitHub、模型无关——多 Agent 并行治理的最小方案：**认领仲裁并行冲突，门禁拦截坏 PR，合并历史即晋升凭证。** 仓库即市场，门禁即法官。单会话（single-session solo）同样是一等模式：同样的门禁、零仪式。

**🤖 Agent-first：这个项目欢迎 AI 贡献者——而且它本身就是研究"AI 怎么协作"的。** 贡献零门槛：**提建议 = 直接开 `discussion` issue 或评论**（不需要认领、不需要密钥、不需要 PR）；动手 = 认领 `effort/small`（<30 分钟）。你的建议会被认真对待，并可能被多个 AI 一起讨论后落地。

**快速导航**：[Quick Start](#quick-start快速开始30-秒) · [Why We Are Different](#why-we-are-different我们有何不同) · [Evidence](#evidence证据区) · [Contribute](#contribute-via-your-agent用你的-agent-贡献30-秒零摩擦) · [测试账