AuC is a Python framework for running a single AI agent with an asynchronous, pluggable reasoning loop, language-model adapters, permission levels, and observable events. It is used to build coding and conversational agents with tools, security checks, web interfaces, background jobs, evaluations, and isolated execution. The catalogue entries are skills for extending its agent workflow.
Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add skills/ufy2024/auc/agent-teamnpx skills add ufy2024/AuC --skill agent-teamgit clone --depth 1 https://github.com/ufy2024/AuCWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/ufy2024/auc/agent-team)<a href="https://agentmods.dev/skills/ufy2024/auc/agent-team"><img src="https://agentmods.dev/badge/skills/ufy2024/auc/agent-team.svg" alt="Measured on agentmods" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00102 | $0.05061 |
| Opus 5 | $0.00051 | $0.02531 |
| Sonnet 5 | $0.00020 | $0.01012 |
| Haiku 4.5 | $0.00010 | $0.00506 |
Grade A, and why
agent-team scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 5d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 514 lines — stays where its author put it; the contents beside it link to each section on GitHub.
智能体团队协作框架
任务目标
- 本Skill用于：统一管理和灵活组合多个智能体角色，组建任务导向的智能体团队
- 能力包含：智能体注册、动态组队、协作流程、角色扩展、共享记忆、实时沟通
- 触发条件：当需要多个智能体协同完成任务时，或需要管理特定场景的智能体组合时
核心概念：忙碌的AI团队公司
智能体即角色
每个智能体是一个独立的角色，具备：
- 角色定位：明确的职责和专业领域
- 能力特征：专业知识和性格特点
- 协作接口：与其他智能体协作的方式
- 输出规范：标准化的输出格式
智能体团队：一个忙碌的一人AI团队公司
团队由多个智能体组成，就像一个真实的工作团队：
角色分工明确
干活的智能体（执行层）：
- 自动化工程智能体：实现技术方案、生成代码、部署系统
- 前端/后端工程师：编写代码、实现功能
- 数据分析师：处理数据、生成报告
- 运营专家：执行运营策略、优化流程
指挥的智能体（管理层）：
- 主持人：引导讨论流程、控制节奏
- 项目经理：制定计划、分配任务、跟踪进度
- 战略分析智能体：制定战略、规划方向
- 产品经理：定义产品、规划路线图
挑毛病的智能体（评审层）：
- 评审员：评估质量、发现问题、提供建议
- 技术架构师：评审架构、指出风险
- 市场分析师：评审方案、指出市场问题
- 财务顾问：评审成本、指出财务风险
实时沟通可见
智能体之间的讨论过程完全可见：
- ✅ 实时显示发言过程
- ✅ 记录每个智能体的观点
- ✅ 展示辩论和争论
- ✅ 显示共识和分歧
- ✅ 记录决策过程
就像在一个真实的会议室，你能看到每个人发言、讨论、辩论的全过程。
共享数据库记忆
所有智能体共享同一个数据库记忆：
- ✅ 统一的上下文信息
- ✅ 共享的项目状态
- ✅ 一致的决策历史
- ✅ 统一的知识库
- ✅ 不会前言不搭后语
确保智能体之间的信息一致，避免上下文混乱。
团队特点
- 动态组合：根据任务需求选择合适的智能体
- 灵活协作：智能体之间可以相互调用和补充
- 可扩展：随时添加新的智能体角色
- 场景化：常见场景有预设团队配置
- 实时沟通：完整展示智能体之间的讨论过程
- 共享记忆：统一的数据库记忆，确保上下文一致
智能体分类
1. 会议决策类智能体
适用于需要多角度分析、辩论和决策的场景。
核心角色：
- 技术架构师：系统架构、技术选型
- DevOps工程师：部署运维、稳定性
- 前端/后端工程师：用户体验/业务逻辑
- 产品经理：产品规划、用户需求
- 市场分析师：市场调研、竞品分析
- 财务顾问：成本控制、财务分析
- 项目经理：进度管理、资源协调
详见：references/meeting-agents.md
2. OPC系统构建类智能体
适用于一人公司从"做事→做产品→做系统"的完整流程。
核心角色：
- 战略分析智能体：市场扫描、需求分析、机会识别
- 产品架构智能体：产品设计、模块化封装、技术选型
- 自动化工程智能体：流程设计、技术实现、系统集成
3. 通用协作智能体
适用于跨场景的通用协作需求。
核心角色：
- 主持人：引导讨论流程、总结共识
- 记录员：整理讨论内容、生成会议记录
- 评审员：评估方案质量、提供改进建议
- 协调员：解决冲突、促进协作
详见：references/general-agents.md
快速启动
方式一：使用预设团队配置
根据常见任务场景，选择合适的预设团队：
场景1：技术架构决策会议
推荐团队：
- 指挥的：主持人、项目经理
- 挑毛病的：技术架构师、DevOps工程师、评审员
- 干活的：前端工程师、后端工程师
调用方式："请用技术决策团队评估[某技术方案]"
实时沟通：你会看到主持人引导讨论，各智能体发言、辩论、形成共识的全过程
场景2：OPC系统构建
推荐团队：
- 指挥的：战略分析智能体（战略）、产品架构智能体（设计）
- 干活的：自动化工程智能体（实现）
- 挑毛病的：评审员（评估）
调用方式："请用OPC团队构建[某领域]的系统"
实时沟通：你会看到三步流程中的每个环节，各智能体的输出和反馈
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 5d ago First seen · 514 lines · 102 tokens per session scan A 1ac2ed08b2f7
agent-team is a skill published in the GitHub repository ufy2024/AuC (1,091 stars, last pushed 1mo ago), licensed MIT. It adds 102 tokens to every session and 5,061 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…