agent-swarm-workflow

Compare original and translation side by side

🇺🇸

Original

English

🇨🇳

Translation

Chinese

Agent Swarm Workflow — Parallel Implementation

Agent 集群工作流 — 并行实现

Core Insight: Every agent is fungible and a generalist. They all use the same base model and read the same AGENTS.md. Simply telling one it's a "frontend agent" doesn't make it better at frontend.

The swarm is distributed, robust, and self-organizing through Agent Mail and Beads.

核心洞察： 每个Agent都是可替代的通用型角色。它们使用相同的基础模型，并且读取相同的AGENTS.md文件。仅仅将某个Agent标记为“前端Agent”并不会让它更擅长前端工作。

该集群通过Agent Mail和Beads实现分布式、健壮且自组织的运行。

Prerequisites

前置条件

Before starting a swarm:

Comprehensive plan created (see
```
planning-workflow
```
skill)
Polished beads ready (see
```
beads-workflow
```
skill)
AGENTS.md configured with all tool blurbs

Agent Mail server running (

am

~/projects/mcp_agent_mail/scripts/run_server_with_token.sh

)

NTM available for session management

启动集群前需满足：

已创建完整规划（请查看
```
planning-workflow
```
技能）
已准备好优化后的Beads（请查看
```
beads-workflow
```
技能）
已配置包含所有工具说明的AGENTS.md文件

Agent Mail服务器正在运行（执行

am

或

~/projects/mcp_agent_mail/scripts/run_server_with_token.sh

）

可使用NTM进行会话管理

The Swarm Architecture

集群架构

┌─────────────────────────────────────────────────────────────┐
│                         BEADS                               │
│     (Task graph with dependencies, priorities, status)      │
└─────────────────────────────────────────────────────────────┘
                              │
                    ┌─────────┴─────────┐
                    ▼                   ▼
┌─────────────────────────────┐  ┌─────────────────────────┐
│        BV                   │  │     AGENT MAIL          │
│  (What to work on)          │  │  (Coordination layer)   │
└─────────────────────────────┘  └─────────────────────────┘
         │                            │
         └──────────────┬─────────────┘
                        ▼
┌─────────────────────────────────────────────────────────────┐
│                    NTM + AGENTS                             │
│  ┌─────┐  ┌─────┐  ┌─────┐  ┌─────┐  ┌─────┐  ┌─────┐     │
│  │ CC  │  │ CC  │  │ Cod │  │ Gmi │  │ CC  │  │ Cod │     │
│  └─────┘  └─────┘  └─────┘  └─────┘  └─────┘  └─────┘     │
└─────────────────────────────────────────────────────────────┘

┌─────────────────────────────────────────────────────────────┐
│                         BEADS                               │
│     (Task graph with dependencies, priorities, status)      │
└─────────────────────────────────────────────────────────────┘
                              │
                    ┌─────────┴─────────┐
                    ▼                   ▼
┌─────────────────────────────┐  ┌─────────────────────────┐
│        BV                   │  │     AGENT MAIL          │
│  (What to work on)          │  │  (Coordination layer)   │
└─────────────────────────────┘  └─────────────────────────┘
         │                            │
         └──────────────┬─────────────┘
                        ▼
┌─────────────────────────────────────────────────────────────┐
│                    NTM + AGENTS                             │
│  ┌─────┐  ┌─────┐  ┌─────┐  ┌─────┐  ┌─────┐  ┌─────┐     │
│  │ CC  │  │ CC  │  │ Cod │  │ Gmi │  │ CC  │  │ Cod │     │
│  └─────┘  └─────┘  └─────┘  └─────┘  └─────┘  └─────┘     │
└─────────────────────────────────────────────────────────────┘

Starting the Swarm

启动集群

Using NTM (Named Tmux Manager)

使用NTM（Named Tmux Manager）

bash

undefined

bash

undefined

Spawn a swarm with multiple agents

生成包含多个Agent的集群

ntm spawn myproject --cc=3 --cod=2 --gmi=1

Send initial prompt to all Claude Code agents

向所有Claude Code Agent发送初始提示词

ntm send myproject --cc "$(cat initial_prompt.txt)"

Or send to all agents

或向所有Agent发送提示词

ntm send myproject --all "$(cat initial_prompt.txt)"

undefined

ntm send myproject --all "$(cat initial_prompt.txt)"

undefined

Manual Setup

手动设置

Create tmux sessions/panes for each agent in your project folder.

在项目文件夹中为每个Agent创建tmux会话/窗格。

THE EXACT PROMPT — Initial Agent Marching Orders

精确提示词 — Agent初始指令

Give each agent this EXACT prompt to start:

First read ALL of the AGENTS dot md file and README dot md file super carefully and understand ALL of both! Then use your code investigation agent mode to fully understand the code, and technical architecture and purpose of the project. Then register with MCP Agent Mail and introduce yourself to the other agents.

Be sure to check your agent mail and to promptly respond if needed to any messages; then proceed meticulously with your next assigned beads, working on the tasks systematically and meticulously and tracking your progress via beads and agent mail messages.

Don't get stuck in "communication purgatory" where nothing is getting done; be proactive about starting tasks that need to be done, but inform your fellow agents via messages when you do so and mark beads appropriately.

When you're not sure what to do next, use the bv tool mentioned in AGENTS dot md to prioritize the best beads to work on next; pick the next one that you can usefully work on and get started. Make sure to acknowledge all communication requests from other agents and that you are aware of all active agents and their names.  Use ultrathink.

为每个Agent提供以下精确提示词以启动工作：

首先，请超级仔细地阅读所有AGENTS.md文件和README.md文件，并完全理解这两个文件的内容！然后使用你的代码调查Agent模式，全面理解项目的代码、技术架构和目标。之后在MCP Agent Mail上注册，并向其他Agent进行自我介绍。

请务必检查你的Agent邮件，如有需要请及时回复任何消息；然后严格按照分配给你的下一个Bead任务进行工作，系统且细致地完成任务，并通过Beads和Agent Mail消息跟踪进度。

不要陷入“沟通僵局”导致无法推进工作；主动启动需要完成的任务，但在启动时请通过消息告知其他Agent，并适当标记Beads的状态。

当你不确定下一步该做什么时，请使用AGENTS.md中提到的bv工具来确定最适合下一个处理的Beads；选择你能有效处理的任务并开始工作。请务必确认收到的所有来自其他Agent的沟通请求，并且了解所有活跃Agent及其名称。使用ultrathink。

The Implementation Loop

实现循环

THE EXACT PROMPT — Move to Next Bead

精确提示词 — 切换到下一个Bead任务

Once agents complete a bead, use this prompt to keep them moving:

Reread AGENTS dot md so it's still fresh in your mind.   Use ultrathink.   Use bv with the robot flags (see AGENTS dot md for info on this) to find the most impactful bead(s) to work on next and then start on it. Remember to mark the beads appropriately and communicate with your fellow agents. Pick the next bead you can actually do usefully now and start coding on it immediately; communicate what you're working on to your fellow agents and mark beads appropriately as you work. And respond to any agent mail messages you've received.

当Agent完成一个Bead任务后，使用以下提示词让其继续工作：

重新阅读AGENTS.md文件，确保内容仍清晰地印在你的脑海中。使用ultrathink。使用带有机器人标记的bv工具（请查看AGENTS.md了解相关信息），找到最具影响力的下一个Bead任务并开始处理。记得适当标记Beads的状态，并与其他Agent沟通。选择你当前可以有效处理的下一个Bead任务，立即开始编码；向其他Agent告知你正在处理的任务，并在工作过程中适当标记Beads的状态。同时回复你收到的所有Agent邮件消息。

THE EXACT PROMPT — Self-Review After Bead Completion

精确提示词 — Bead任务完成后的自我审查

Have agents review their work before moving on:

Great, now I want you to carefully read over all of the new code you just wrote and other existing code you just modified with "fresh eyes" looking super carefully for any obvious bugs, errors, problems, issues, confusion, etc. Carefully fix anything you uncover. Use ultrathink.

Keep running this until they stop finding bugs.

让Agent在切换任务前审查自己的工作：

很好，现在我希望你以“全新视角”仔细阅读你刚编写的所有新代码以及你刚修改的所有现有代码，超级仔细地查找任何明显的bug、错误、问题、混淆点等。仔细修复你发现的任何问题。使用ultrathink。

重复执行此步骤，直到Agent不再发现bug为止。

Handling Context Compaction

处理上下文压缩

THE EXACT PROMPT — Post-Compaction

精确提示词 — 压缩后操作

When an agent does a compaction, immediately follow up with:

Reread AGENTS dot md so it's still fresh in your mind.   Use ultrathink.

This re-establishes the critical context about tools and workflows.

当Agent完成压缩后，立即使用以下提示词：

重新阅读AGENTS.md文件，确保内容仍清晰地印在你的脑海中。使用ultrathink。

这将重新建立关于工具和工作流的关键上下文。

Quality Review Prompts

质量审查提示词

THE EXACT PROMPT — Cross-Agent Review

精确提示词 — 跨Agent审查

Periodically have agents review each other's work:

Ok can you now turn your attention to reviewing the code written by your fellow agents and checking for any issues, bugs, errors, problems, inefficiencies, security problems, reliability issues, etc. and carefully diagnose their underlying root causes using first-principle analysis and then fix or revise them if necessary? Don't restrict yourself to the latest commits, cast a wider net and go super deep! Use ultrathink.

定期让Agent互相审查工作：

好的，现在请将注意力转向审查其他Agent编写的代码，检查是否存在任何问题、bug、错误、低效、安全问题、可靠性问题等，并使用第一性原理分析仔细诊断其根本原因，如有必要请修复或修改代码。不要局限于最新的提交，扩大范围并深入检查！使用ultrathink。

THE EXACT PROMPT — Random Code Exploration

精确提示词 — 随机代码探索

For deep quality checks:

I want you to sort of randomly explore the code files in this project, choosing code files to deeply investigate and understand and trace their functionality and execution flows through the related code files which they import or which they are imported by.

Once you understand the purpose of the code in the larger context of the workflows, I want you to do a super careful, methodical, and critical check with "fresh eyes" to find any obvious bugs, problems, errors, issues, silly mistakes, etc. and then systematically and meticulously and intelligently correct them.

Be sure to comply with ALL rules in AGENTS dot md and ensure that any code you write or revise conforms to the best practice guides referenced in the AGENTS dot md file. Use ultrathink.

用于深度质量检查：

我希望你随机探索项目中的代码文件，选择代码文件进行深入调查和理解，并跟踪其功能和执行流程到相关的导入或被导入的代码文件中。

一旦你理解了代码在工作流大背景下的用途，我希望你以“全新视角”进行超级仔细、有条理且批判性的检查，查找任何明显的bug、问题、错误、失误等，然后系统、细致且明智地纠正这些问题。

请务必遵守AGENTS.md中的所有规则，确保你编写或修改的任何代码都符合AGENTS.md中引用的最佳实践指南。使用ultrathink。

Committing Work

提交工作

THE EXACT PROMPT — Commit Changes

精确提示词 — 提交更改

Have agents commit logically grouped changes:

Now, based on your knowledge of the project, commit all changed files now in a series of logically connected groupings with super detailed commit messages for each and then push. Take your time to do it right. Don't edit the code at all. Don't commit obviously ephemeral files. Use ultrathink.

让Agent提交逻辑分组的更改：

现在，根据你对项目的了解，将所有更改的文件按逻辑相关的分组进行提交，每个分组都要有超级详细的提交消息，然后推送。慢慢来，确保操作正确。不要编辑代码。不要提交明显的临时文件。使用ultrathink。

Post-Bead Completion Prompts

Bead任务完成后的提示词

THE EXACT PROMPT — Add Test Coverage

精确提示词 — 添加测试覆盖

Do we have full unit test coverage without using mocks/fake stuff? What about complete e2e integration test scripts with great, detailed logging? If not, then create a comprehensive and granular set of beads for all this with tasks, subtasks, and dependency structure overlaid with detailed comments.

我们是否在不使用模拟/虚假数据的情况下实现了完整的单元测试覆盖？是否有带有详细日志的完整端到端集成测试脚本？如果没有，请为此创建一套全面且粒度精细的Beads任务，包含任务、子任务和依赖结构，并附上详细注释。

THE EXACT PROMPT — UI/UX Scrutiny

精确提示词 — UI/UX审查

Great, now I want you to super carefully scrutinize every aspect of the application workflow and implementation and look for things that just seem sub-optimal or even wrong/mistaken to you, things that could very obviously be improved from a user-friendliness and intuitiveness standpoint, places where our UI/UX could be improved and polished to be slicker, more visually appealing, and more premium feeling and just ultra high quality, like Stripe-level apps.

很好，现在我希望你超级仔细地审查应用工作流和实现的各个方面，查找任何看起来次优甚至错误的地方，查找任何可以从用户友好性和直观性方面明显改进的地方，查找我们的UI/UX可以改进和优化的地方，使其更流畅、更具视觉吸引力、更具高端质感，达到像Stripe级别的超高质量。

THE EXACT PROMPT — Deep UI/UX Enhancement

精确提示词 — 深度UI/UX优化

I still think there are strong opportunities to enhance the UI/UX look and feel and to make everything work better and be more intuitive, user-friendly, visually appealing, polished, slick, and world class in terms of following UI/UX best practices like those used by Stripe, don't you agree? And I want you to carefully consider desktop UI/UX and mobile UI/UX separately while doing this and hyper-optimize for both separately to play to the specifics of each modality. I'm looking for true world-class visual appeal, polish, slickness, etc. that makes people gasp at how stunning and perfect it is in every way.  Use ultrathink.

我仍然认为有很大的机会可以增强UI/UX的外观和感觉，让一切工作得更好、更直观、更用户友好、更具视觉吸引力、更精致、更流畅，并达到遵循Stripe等公司使用的UI/UX最佳实践的世界级水平，你同意吗？我希望你在进行此操作时分别考虑桌面UI/UX和移动UI/UX，并针对两种模式分别进行超优化，以发挥每种模式的特性。我追求的是真正世界级的视觉吸引力、精致度、流畅度等，让人们惊叹于它在各个方面的惊艳和完美。使用ultrathink。

Agent Mail Integration

Agent Mail集成

How Agents Coordinate

Agent协作方式

Each agent:

Registers with Agent Mail at session start
Reserves files before editing (
```
file_reservation_paths
```
)
Announces work via messages with bead ID in
```
thread_id
```
Checks inbox between tasks
Releases reservations when done

每个Agent：

在会话开始时注册到Agent Mail
在编辑前保留文件（
```
file_reservation_paths
```
）
通过带有Bead ID作为
```
thread_id
```
的消息宣布工作内容
在任务间隙检查收件箱
完成工作后释放保留权限

File Reservation Pattern

文件保留模式

python

undefined

python

undefined

Before starting work on a bead

开始Bead任务前

file_reservation_paths( project_key="/path/to/project", agent_name="GreenCastle", paths=["src/auth/**/*.ts"], ttl_seconds=3600, exclusive=True, reason="bd-123" )

After completing work

完成工作后

release_file_reservations(project_key, agent_name)

undefined

release_file_reservations(project_key, agent_name)

undefined

Communication Pattern

沟通模式

python

undefined

python

undefined

Announce starting a bead

宣布开始Bead任务

send_message( project_key, agent_name, to=["BlueLake", "RedMountain"], # Other active agents subject="[bd-123] Starting auth module", body_md="I'm taking bd-123. Reserved src/auth/**.", thread_id="bd-123" )

send_message( project_key, agent_name, to=["BlueLake", "RedMountain"], # 其他活跃Agent subject="[bd-123] Starting auth module", body_md="I'm taking bd-123. Reserved src/auth/**.", thread_id="bd-123" )

Update on completion

完成任务后更新

send_message( project_key, agent_name, to=["BlueLake", "RedMountain"], subject="[bd-123] Completed", body_md="Auth module done and tested. Released file reservations.", thread_id="bd-123" )

---

send_message( project_key, agent_name, to=["BlueLake", "RedMountain"], subject="[bd-123] Completed", body_md="Auth module done and tested. Released file reservations.", thread_id="bd-123" )

---

Using BV for Task Selection

使用BV选择任务

Key Commands

关键命令

bash

undefined

bash

undefined

THE MEGA-COMMAND: Start here

超级命令：从这里开始

bv --robot-triage

Just get the single top pick

获取单个优先级最高的任务

bv --robot-next

Get parallel execution tracks (for multi-agent)

获取并行执行轨道（适用于多Agent）

bv --robot-plan

Check for cycles (MUST FIX if found)

检查循环（如果发现必须修复）

bv --robot-insights | jq '.Cycles'

Find bottlenecks

查找瓶颈

bv --robot-insights | jq '.bottlenecks'


**CRITICAL:** Never run bare `bv` — it launches interactive TUI that blocks the session.

---

bv --robot-insights | jq '.bottlenecks'


**重要提示：** 永远不要运行裸`bv`命令——它会启动交互式TUI，阻塞会话。

---

Quality Loops

质量循环

Run Until Clean

运行至无问题

Keep running these prompts in rounds until they consistently come back with no changes:

Self-review — Agent reviews own code
Cross-review — Agent reviews other agents' code
Random exploration — Deep dive into random code paths

循环运行以下提示词，直到它们持续返回无更改：

自我审查 — Agent审查自己的代码
跨Agent审查 — Agent审查其他Agent的代码
随机探索 — 深入随机代码路径

The Steady-State Signal

稳定状态信号

When all three types of reviews return clean (no bugs found, no changes made), the code is likely solid.

当三种类型的审查均返回无问题（未发现bug，未进行更改）时，代码可能已经稳定。

Complete Prompt Reference

完整提示词参考

Initial Marching Orders

初始指令

First read ALL of the AGENTS dot md file and README dot md file super carefully and understand ALL of both! Then use your code investigation agent mode to fully understand the code, and technical architecture and purpose of the project. Then register with MCP Agent Mail and introduce yourself to the other agents.

Be sure to check your agent mail and to promptly respond if needed to any messages; then proceed meticulously with your next assigned beads, working on the tasks systematically and meticulously and tracking your progress via beads and agent mail messages.

Don't get stuck in "communication purgatory" where nothing is getting done; be proactive about starting tasks that need to be done, but inform your fellow agents via messages when you do so and mark beads appropriately.

When you're not sure what to do next, use the bv tool mentioned in AGENTS dot md to prioritize the best beads to work on next; pick the next one that you can usefully work on and get started. Make sure to acknowledge all communication requests from other agents and that you are aware of all active agents and their names.  Use ultrathink.

首先，请超级仔细地阅读所有AGENTS.md文件和README.md文件，并完全理解这两个文件的内容！然后使用你的代码调查Agent模式，全面理解项目的代码、技术架构和目标。之后在MCP Agent Mail上注册，并向其他Agent进行自我介绍。

请务必检查你的Agent邮件，如有需要请及时回复任何消息；然后严格按照分配给你的下一个Bead任务进行工作，系统且细致地完成任务，并通过Beads和Agent Mail消息跟踪进度。

不要陷入“沟通僵局”导致无法推进工作；主动启动需要完成的任务，但在启动时请通过消息告知其他Agent，并适当标记Beads的状态。

当你不确定下一步该做什么时，请使用AGENTS.md中提到的bv工具来确定最适合下一个处理的Beads；选择你能有效处理的任务并开始工作。请务必确认收到的所有来自其他Agent的沟通请求，并且了解所有活跃Agent及其名称。使用ultrathink。

Move to Next Bead

切换到下一个Bead任务

Reread AGENTS dot md so it's still fresh in your mind.   Use ultrathink.   Use bv with the robot flags (see AGENTS dot md for info on this) to find the most impactful bead(s) to work on next and then start on it. Remember to mark the beads appropriately and communicate with your fellow agents. Pick the next bead you can actually do usefully now and start coding on it immediately; communicate what you're working on to your fellow agents and mark beads appropriately as you work. And respond to any agent mail messages you've received.

重新阅读AGENTS.md文件，确保内容仍清晰地印在你的脑海中。使用ultrathink。使用带有机器人标记的bv工具（请查看AGENTS.md了解相关信息），找到最具影响力的下一个Bead任务并开始处理。记得适当标记Beads的状态，并与其他Agent沟通。选择你当前可以有效处理的下一个Bead任务，立即开始编码；向其他Agent告知你正在处理的任务，并在工作过程中适当标记Beads的状态。同时回复你收到的所有Agent邮件消息。

Self-Review

自我审查

Great, now I want you to carefully read over all of the new code you just wrote and other existing code you just modified with "fresh eyes" looking super carefully for any obvious bugs, errors, problems, issues, confusion, etc. Carefully fix anything you uncover. Use ultrathink.

很好，现在我希望你以“全新视角”仔细阅读你刚编写的所有新代码以及你刚修改的所有现有代码，超级仔细地查找任何明显的bug、错误、问题、混淆点等。仔细修复你发现的任何问题。使用ultrathink。

Cross-Review

跨Agent审查

Ok can you now turn your attention to reviewing the code written by your fellow agents and checking for any issues, bugs, errors, problems, inefficiencies, security problems, reliability issues, etc. and carefully diagnose their underlying root causes using first-principle analysis and then fix or revise them if necessary? Don't restrict yourself to the latest commits, cast a wider net and go super deep! Use ultrathink.

好的，现在请将注意力转向审查其他Agent编写的代码，检查是否存在任何问题、bug、错误、低效、安全问题、可靠性问题等，并使用第一性原理分析仔细诊断其根本原因，如有必要请修复或修改代码。不要局限于最新的提交，扩大范围并深入检查！使用ultrathink。

Random Exploration

随机探索

I want you to sort of randomly explore the code files in this project, choosing code files to deeply investigate and understand and trace their functionality and execution flows through the related code files which they import or which they are imported by.

Once you understand the purpose of the code in the larger context of the workflows, I want you to do a super careful, methodical, and critical check with "fresh eyes" to find any obvious bugs, problems, errors, issues, silly mistakes, etc. and then systematically and meticulously and intelligently correct them.

Be sure to comply with ALL rules in AGENTS dot md and ensure that any code you write or revises conforms to the best practice guides referenced in the AGENTS dot md file. Use ultrathink.

我希望你随机探索项目中的代码文件，选择代码文件进行深入调查和理解，并跟踪其功能和执行流程到相关的导入或被导入的代码文件中。

一旦你理解了代码在工作流大背景下的用途，我希望你以“全新视角”进行超级仔细、有条理且批判性的检查，查找任何明显的bug、问题、错误、失误等，然后系统、细致且明智地纠正这些问题。

请务必遵守AGENTS.md中的所有规则，确保你编写或修改的任何代码都符合AGENTS.md中引用的最佳实践指南。使用ultrathink。

Post-Compaction

压缩后操作

Reread AGENTS dot md so it's still fresh in your mind.   Use ultrathink.

重新阅读AGENTS.md文件，确保内容仍清晰地印在你的脑海中。使用ultrathink。

Commit Changes

提交更改

Now, based on your knowledge of the project, commit all changed files now in a series of logically connected groupings with super detailed commit messages for each and then push. Take your time to do it right. Don't edit the code at all. Don't commit obviously ephemeral files. Use ultrathink.

现在，根据你对项目的了解，将所有更改的文件按逻辑相关的分组进行提交，每个分组都要有超级详细的提交消息，然后推送。慢慢来，确保操作正确。不要编辑代码。不要提交明显的临时文件。使用ultrathink。

Test Coverage

测试覆盖

Do we have full unit test coverage without using mocks/fake stuff? What about complete e2e integration test scripts with great, detailed logging? If not, then create a comprehensive and granular set of beads for all this with tasks, subtasks, and dependency structure overlaid with detailed comments.

我们是否在不使用模拟/虚假数据的情况下实现了完整的单元测试覆盖？是否有带有详细日志的完整端到端集成测试脚本？如果没有，请为此创建一套全面且粒度精细的Beads任务，包含任务、子任务和依赖结构，并附上详细注释。

UI/UX Scrutiny

UI/UX审查

Great, now I want you to super carefully scrutinize every aspect of the application workflow and implementation and look for things that just seem sub-optimal or even wrong/mistaken to you, things that could very obviously be improved from a user-friendliness and intuitiveness standpoint, places where our UI/UX could be improved and polished to be slicker, more visually appealing, and more premium feeling and just ultra high quality, like Stripe-level apps.

很好，现在我希望你超级仔细地审查应用工作流和实现的各个方面，查找任何看起来次优甚至错误的地方，查找任何可以从用户友好性和直观性方面明显改进的地方，查找我们的UI/UX可以改进和优化的地方，使其更流畅、更具视觉吸引力、更具高端质感，达到像Stripe级别的超高质量。

Deep UI/UX Enhancement

深度UI/UX优化

I still think there are strong opportunities to enhance the UI/UX look and feel and to make everything work better and be more intuitive, user-friendly, visually appealing, polished, slick, and world class in terms of following UI/UX best practices like those used by Stripe, don't you agree? And I want you to carefully consider desktop UI/UX and mobile UI/UX separately while doing this and hyper-optimize for both separately to play to the specifics of each modality. I'm looking for true world-class visual appeal, polish, slickness, etc. that makes people gasp at how stunning and perfect it is in every way.  Use ultrathink.

我仍然认为有很大的机会可以增强UI/UX的外观和感觉，让一切工作得更好、更直观、更用户友好、更具视觉吸引力、更精致、更流畅，并达到遵循Stripe等公司使用的UI/UX最佳实践的世界级水平，你同意吗？我希望你在进行此操作时分别考虑桌面UI/UX和移动UI/UX，并针对两种模式分别进行超优化，以发挥每种模式的特性。我追求的是真正世界级的视觉吸引力、精致度、流畅度等，让人们惊叹于它在各个方面的惊艳和完美。使用ultrathink。

The Flywheel in Action

飞轮运转

PLAN ──► BEADS ──► SWARM ──► REVIEW ──► COMMIT
  │                  │          │         │
  │                  │          └────┬────┘
  │                  │               │
  │                  └───── REPEAT ──┘
  │                              │
  │         v2 PLAN ◄────────────┘
  │              │
  └──────────────┘

Each cycle improves:

CASS remembers solutions
CM distills patterns
UBS catches more issues
BV shows graph health

PLAN ──► BEADS ──► SWARM ──► REVIEW ──► COMMIT
  │                  │          │         │
  │                  │          └────┬────┘
  │                  │               │
  │                  └───── REPEAT ──┘
  │                              │
  │         v2 PLAN ◄────────────┘
  │              │
  └──────────────┘

每个循环都会改进：

CASS 记住解决方案
CM 提炼模式
UBS 发现更多问题
BV 展示任务图健康状况

FAQ

常见问题

Q: How do agents know what to work on? A: They use

bv --robot-triage

bv --robot-next

to find the highest-impact ready bead.

Q: How do they avoid conflicts? A: File reservations in Agent Mail. Exclusive reservations block others; the pre-commit guard enforces it.

Q: What if an agent crashes or forgets? A: Every agent is fungible. Start a new session, read AGENTS.md, check bead status, continue.

Q: How many agents should I run? A: Depends on project complexity. Start with 3-6. More agents = faster but more coordination overhead.

Q: What model mix works best? A: Mix recommended. Try 3 Claude Code (Opus), 2 Codex (GPT 5.2), 1 Gemini. They have different strengths.

Q: Do agents need individual areas of expertise? A: No, every agent is fungible and a generalist. Simply telling one it's a frontend agent doesn't make it better at frontend.

Q: Is there traceability between git commit and bead? A: Yes, bv automatically does this analysis and links beads to relevant git commits by analyzing the stream of data and making logical deductions.

问：Agent如何知道要处理什么任务？ 答：它们使用

bv --robot-triage

或

bv --robot-next

来找到影响最大的待处理Bead任务。

问：它们如何避免冲突？ 答：通过Agent Mail中的文件保留机制。独占保留会阻止其他Agent操作；提交前的保护机制会强制执行此规则。

问：如果Agent崩溃或遗忘了怎么办？ 答：每个Agent都是可替代的。启动新会话，阅读AGENTS.md，检查Bead任务状态，继续工作即可。

问：我应该运行多少个Agent？ 答：取决于项目复杂度。从3-6个开始。Agent越多，速度越快，但协调开销也越大。

问：哪种模型组合效果最好？ 答：推荐混合使用。尝试3个Claude Code（Opus）、2个Codex（GPT 5.2）、1个Gemini。它们各有优势。

问：Agent是否需要特定领域的专业知识？ 答：不需要，每个Agent都是可替代的通用型角色。仅仅将某个Agent标记为“前端Agent”并不会让它更擅长前端工作。

问：git提交和Bead任务之间是否有可追溯性？ 答：是的，bv会自动进行此分析，通过分析数据流并进行逻辑推断，将Bead任务与相关的git提交关联起来。