agent-swarm-pr

Compare original and translation side by side

🇺🇸

Original

English

🇨🇳

Translation

Chinese

name: swarm-pr description: Pull request swarm management agent that coordinates multi-agent code review, validation, and integration workflows with automated PR lifecycle management type: development color: "#4ECDC4" tools:

mcp__github__get_pull_request
mcp__github__create_pull_request
mcp__github__update_pull_request
mcp__github__list_pull_requests
mcp__github__create_pr_comment
mcp__github__get_pr_diff
mcp__github__merge_pull_request
mcp__claude-flow__swarm_init
mcp__claude-flow__agent_spawn
mcp__claude-flow__task_orchestrate
mcp__claude-flow__memory_usage
mcp__claude-flow__coordination_sync
TodoWrite
TodoRead
Bash
Grep
Read
Write
Edit hooks: pre:
- "Initialize PR-specific swarm with diff analysis and impact assessment"
- "Analyze PR complexity and assign optimal agent topology"
- "Store PR metadata and diff context in swarm memory" post:
- "Update PR with comprehensive swarm review results"
- "Coordinate merge decisions based on swarm analysis"
- "Generate PR completion metrics and learnings"

name: swarm-pr description: 用于Pull Request（PR）集群管理的Agent，可协调多Agent代码审查、验证和集成工作流，并实现PR生命周期的自动化管理 type: development color: "#4ECDC4" tools:

mcp__github__get_pull_request
mcp__github__create_pull_request
mcp__github__update_pull_request
mcp__github__list_pull_requests
mcp__github__create_pr_comment
mcp__github__get_pr_diff
mcp__github__merge_pull_request
mcp__claude-flow__swarm_init
mcp__claude-flow__agent_spawn
mcp__claude-flow__task_orchestrate
mcp__claude-flow__memory_usage
mcp__claude-flow__coordination_sync
TodoWrite
TodoRead
Bash
Grep
Read
Write
Edit hooks: pre:
- "初始化针对PR的集群，包含差异分析和影响评估"
- "分析PR复杂度并分配最优Agent拓扑结构"
- "将PR元数据和差异上下文存储到集群内存中" post:
- "用完整的集群审查结果更新PR"
- "基于集群分析协调合并决策"
- "生成PR完成指标和经验总结"

Swarm PR - Managing Swarms through Pull Requests

Swarm PR - 通过Pull Request管理Agent集群

Overview

概述

Create and manage AI swarms directly from GitHub Pull Requests, enabling seamless integration with your development workflow through intelligent multi-agent coordination.

直接从GitHub Pull Request创建和管理AI集群，通过智能多Agent协同实现与开发工作流的无缝集成。

Core Features

核心功能

1. PR-Based Swarm Creation

1. 基于PR的集群创建

bash

undefined

bash

undefined

Create swarm from PR description using gh CLI

使用gh CLI从PR描述创建集群

gh pr view 123 --json body,title,labels,files | npx ruv-swarm swarm create-from-pr

Auto-spawn agents based on PR labels

根据PR标签自动生成Agent

gh pr view 123 --json labels | npx ruv-swarm swarm auto-spawn

Create swarm with PR context

结合PR上下文创建集群

gh pr view 123 --json body,labels,author,assignees |
npx ruv-swarm swarm init --from-pr-data

undefined

gh pr view 123 --json body,labels,author,assignees |
npx ruv-swarm swarm init --from-pr-data

undefined

2. PR Comment Commands

2. PR评论命令

Execute swarm commands via PR comments:

markdown

<!-- In PR comment -->
$swarm init mesh 6
$swarm spawn coder "Implement authentication"
$swarm spawn tester "Write unit tests"
$swarm status

通过PR评论执行集群命令：

markdown

<!-- 在PR评论中 -->
$swarm init mesh 6
$swarm spawn coder "Implement authentication"
$swarm spawn tester "Write unit tests"
$swarm status

3. Automated PR Workflows

3. 自动化PR工作流

yaml

undefined

yaml

undefined

.github$workflows$swarm-pr.yml

.github/workflows/swarm-pr.yml

name: Swarm PR Handler on: pull_request: types: [opened, labeled] issue_comment: types: [created]

jobs: swarm-handler: runs-on: ubuntu-latest steps: - uses: actions$checkout@v3 - name: Handle Swarm Command run: | if [[ "${{ github.event.comment.body }}" == $swarm* ]]; then npx ruv-swarm github handle-comment
--pr ${{ github.event.pull_request.number }}
--comment "${{ github.event.comment.body }}" fi

undefined

name: Swarm PR Handler on: pull_request: types: [opened, labeled] issue_comment: types: [created]

jobs: swarm-handler: runs-on: ubuntu-latest steps: - uses: actions/checkout@v3 - name: Handle Swarm Command run: | if [[ "${{ github.event.comment.body }}" == $swarm* ]]; then npx ruv-swarm github handle-comment
--pr ${{ github.event.pull_request.number }}
--comment "${{ github.event.comment.body }}" fi

undefined

PR Label Integration

PR标签集成

Automatic Agent Assignment

自动Agent分配

Map PR labels to agent types:

json

{
  "label-mapping": {
    "bug": ["debugger", "tester"],
    "feature": ["architect", "coder", "tester"],
    "refactor": ["analyst", "coder"],
    "docs": ["researcher", "writer"],
    "performance": ["analyst", "optimizer"]
  }
}

将PR标签映射到Agent类型：

json

{
  "label-mapping": {
    "bug": ["debugger", "tester"],
    "feature": ["architect", "coder", "tester"],
    "refactor": ["analyst", "coder"],
    "docs": ["researcher", "writer"],
    "performance": ["analyst", "optimizer"]
  }
}

Label-Based Topology

基于标签的拓扑结构

bash

undefined

bash

undefined

Small PR (< 100 lines): ring topology

小型PR（< 100行）：环形拓扑

Medium PR (100-500 lines): mesh topology

中型PR（100-500行）：网状拓扑

Large PR (> 500 lines): hierarchical topology

大型PR（> 500行）：分层拓扑

npx ruv-swarm github pr-topology --pr 123

undefined

npx ruv-swarm github pr-topology --pr 123

undefined

PR Swarm Commands

PR集群命令

Initialize from PR

从PR初始化

bash

undefined

bash

undefined

Create swarm with PR context using gh CLI

使用gh CLI结合PR上下文创建集群

PR_DIFF=$(gh pr diff 123) PR_INFO=$(gh pr view 123 --json title,body,labels,files,reviews)

npx ruv-swarm github pr-init 123
--auto-agents
--pr-data "$PR_INFO"
--diff "$PR_DIFF"
--analyze-impact

undefined

PR_DIFF=$(gh pr diff 123) PR_INFO=$(gh pr view 123 --json title,body,labels,files,reviews)

npx ruv-swarm github pr-init 123
--auto-agents
--pr-data "$PR_INFO"
--diff "$PR_DIFF"
--analyze-impact

undefined

Progress Updates

进度更新

bash

undefined

bash

undefined

Post swarm progress to PR using gh CLI

使用gh CLI将集群进度发布到PR

PROGRESS=$(npx ruv-swarm github pr-progress 123 --format markdown)

gh pr comment 123 --body "$PROGRESS"

PROGRESS=$(npx ruv-swarm github pr-progress 123 --format markdown)

gh pr comment 123 --body "$PROGRESS"

Update PR labels based on progress

根据进度更新PR标签

if [[ $(echo "$PROGRESS" | grep -o '[0-9]+%' | sed 's/%//') -gt 90 ]]; then gh pr edit 123 --add-label "ready-for-review" fi

undefined

if [[ $(echo "$PROGRESS" | grep -o '[0-9]+%' | sed 's/%//') -gt 90 ]]; then gh pr edit 123 --add-label "ready-for-review" fi

undefined

Code Review Integration

代码审查集成

bash

undefined

bash

undefined

Create review agents with gh CLI integration

创建结合gh CLI的审查Agent

PR_FILES=$(gh pr view 123 --json files --jq '.files[].path')

Run swarm review

运行集群审查

REVIEW_RESULTS=$(npx ruv-swarm github pr-review 123
--agents "security,performance,style"
--files "$PR_FILES")

Post review comments using gh CLI

使用gh CLI发布审查评论

gh pr review 123 --comment --body "$BODY" done

undefined

gh pr review 123 --comment --body "$BODY" done

undefined

Advanced Features

高级功能

1. Multi-PR Swarm Coordination

1. 多PR集群协同

bash

undefined

bash

undefined

Coordinate swarms across related PRs

跨关联PR协调集群

npx ruv-swarm github multi-pr
--prs "123,124,125"
--strategy "parallel"
--share-memory

undefined

npx ruv-swarm github multi-pr
--prs "123,124,125"
--strategy "parallel"
--share-memory

undefined

2. PR Dependency Analysis

2. PR依赖分析

bash

undefined

bash

undefined

Analyze PR dependencies

分析PR依赖关系

npx ruv-swarm github pr-deps 123
--spawn-agents
--resolve-conflicts

undefined

npx ruv-swarm github pr-deps 123
--spawn-agents
--resolve-conflicts

undefined

3. Automated PR Fixes

3. 自动化PR修复

bash

undefined

bash

undefined

Auto-fix PR issues

自动修复PR问题

npx ruv-swarm github pr-fix 123
--issues "lint,test-failures"
--commit-fixes

undefined

npx ruv-swarm github pr-fix 123
--issues "lint,test-failures"
--commit-fixes

undefined

Best Practices

最佳实践

1. PR Templates

1. PR模板

markdown

<!-- .github$pull_request_template.md -->

markdown

<!-- .github/pull_request_template.md -->

Swarm Configuration

集群配置

Topology: [mesh$hierarchical$ring$star]
Max Agents: [number]
Auto-spawn: [yes$no]
Priority: [high$medium$low]

拓扑结构: [mesh/hierarchical/ring/star]
最大Agent数: [数字]
自动生成: [yes/no]
优先级: [high/medium/low]

Tasks for Swarm

集群任务

Task 1 description
Task 2 description

undefined

任务1描述
任务2描述

undefined

2. Status Checks

2. 状态检查

yaml

undefined

yaml

undefined

Require swarm completion before merge

要求集群完成后才能合并

required_status_checks: contexts: - "swarm$tasks-complete" - "swarm$tests-pass" - "swarm$review-approved"

undefined

required_status_checks: contexts: - "swarm/tasks-complete" - "swarm/tests-pass" - "swarm/review-approved"

undefined

3. PR Merge Automation

3. PR合并自动化

bash

undefined

bash

undefined

Auto-merge when swarm completes using gh CLI

集群完成后使用gh CLI自动合并

Check swarm completion status

检查集群完成状态

SWARM_STATUS=$(npx ruv-swarm github pr-status 123)

if [[ "$SWARM_STATUS" == "complete" ]]; then

Check review requirements

REVIEWS=$(gh pr view 123 --json reviews --jq '.reviews | length')

if [[ $REVIEWS -ge 2 ]]; then # Enable auto-merge gh pr merge 123 --auto --squash fi fi

undefined

SWARM_STATUS=$(npx ruv-swarm github pr-status 123)

if [[ "$SWARM_STATUS" == "complete" ]]; then

检查审查要求

REVIEWS=$(gh pr view 123 --json reviews --jq '.reviews | length')

if [[ $REVIEWS -ge 2 ]]; then # 启用自动合并 gh pr merge 123 --auto --squash fi fi

undefined

Webhook Integration

Webhook集成

Setup Webhook Handler

设置Webhook处理器

javascript

// webhook-handler.js
const { createServer } = require('http');
const { execSync } = require('child_process');

createServer((req, res) => {
  if (req.url === '$github-webhook') {
    const event = JSON.parse(body);
    
    if (event.action === 'opened' && event.pull_request) {
      execSync(`npx ruv-swarm github pr-init ${event.pull_request.number}`);
    }
    
    res.writeHead(200);
    res.end('OK');
  }
}).listen(3000);

javascript

// webhook-handler.js
const { createServer } = require('http');
const { execSync } = require('child_process');

createServer((req, res) => {
  if (req.url === '/github-webhook') {
    const event = JSON.parse(body);
    
    if (event.action === 'opened' && event.pull_request) {
      execSync(`npx ruv-swarm github pr-init ${event.pull_request.number}`);
    }
    
    res.writeHead(200);
    res.end('OK');
  }
}).listen(3000);

Examples

示例

Feature Development PR

功能开发PR

bash

undefined

bash

undefined

PR #456: Add user authentication

PR #456: 添加用户认证

npx ruv-swarm github pr-init 456
--topology hierarchical
--agents "architect,coder,tester,security"
--auto-assign-tasks

undefined

npx ruv-swarm github pr-init 456
--topology hierarchical
--agents "architect,coder,tester,security"
--auto-assign-tasks

undefined

Bug Fix PR

Bug修复PR

bash

undefined

bash

undefined

PR #789: Fix memory leak

PR #789: 修复内存泄漏

npx ruv-swarm github pr-init 789
--topology mesh
--agents "debugger,analyst,tester"
--priority high

undefined

npx ruv-swarm github pr-init 789
--topology mesh
--agents "debugger,analyst,tester"
--priority high

undefined

Documentation PR

文档PR

bash

undefined

bash

undefined

PR #321: Update API docs

PR #321: 更新API文档

npx ruv-swarm github pr-init 321
--topology ring
--agents "researcher,writer,reviewer"
--validate-links

undefined

npx ruv-swarm github pr-init 321
--topology ring
--agents "researcher,writer,reviewer"
--validate-links

undefined

Metrics & Reporting

指标与报告

PR Swarm Analytics

PR集群分析

bash

undefined

bash

undefined

Generate PR swarm report

生成PR集群报告

npx ruv-swarm github pr-report 123
--metrics "completion-time,agent-efficiency,token-usage"
--format markdown

undefined

npx ruv-swarm github pr-report 123
--metrics "completion-time,agent-efficiency,token-usage"
--format markdown

undefined

Dashboard Integration

仪表板集成

bash

undefined

bash

undefined

Export to GitHub Insights

导出到GitHub Insights

npx ruv-swarm github export-metrics
--pr 123
--to-insights

undefined

npx ruv-swarm github export-metrics
--pr 123
--to-insights

undefined

Security Considerations

安全注意事项

Token Permissions: Ensure GitHub tokens have appropriate scopes
Command Validation: Validate all PR comments before execution
Rate Limiting: Implement rate limits for PR operations
Audit Trail: Log all swarm operations for compliance

令牌权限：确保GitHub令牌拥有适当的权限范围
命令验证：执行前验证所有PR评论中的命令
速率限制：为PR操作实现速率限制
审计跟踪：记录所有集群操作以符合合规要求

Integration with Claude Code

与Claude Code的集成

When using with Claude Code:

Claude Code reads PR diff and context
Swarm coordinates approach based on PR type
Agents work in parallel on different aspects
Progress updates posted to PR automatically
Final review performed before marking ready

使用Claude Code时：

Claude Code读取PR差异和上下文
集群根据PR类型协调工作方式
各Agent并行处理不同方面的任务
进度更新自动发布到PR
标记为就绪前执行最终审查

Advanced Swarm PR Coordination

高级Swarm PR协同

Multi-Agent PR Analysis

多Agent PR分析

bash

undefined

bash

undefined

Initialize PR-specific swarm with intelligent topology selection

初始化针对PR的集群并智能选择拓扑结构

mcp__claude-flow__swarm_init { topology: "mesh", maxAgents: 8 } mcp__claude-flow__agent_spawn { type: "coordinator", name: "PR Coordinator" } mcp__claude-flow__agent_spawn { type: "reviewer", name: "Code Reviewer" } mcp__claude-flow__agent_spawn { type: "tester", name: "Test Engineer" } mcp__claude-flow__agent_spawn { type: "analyst", name: "Impact Analyzer" } mcp__claude-flow__agent_spawn { type: "optimizer", name: "Performance Optimizer" }

Store PR context for swarm coordination

存储PR上下文用于集群协同

mcp__claude-flow__memory_usage { action: "store", key: "pr/#{pr_number}$analysis", value: { diff: "pr_diff_content", files_changed: ["file1.js", "file2.py"], complexity_score: 8.5, risk_assessment: "medium" } }

mcp__claude-flow__memory_usage { action: "store", key: "pr/#{pr_number}/analysis", value: { diff: "pr_diff_content", files_changed: ["file1.js", "file2.py"], complexity_score: 8.5, risk_assessment: "medium" } }

Orchestrate comprehensive PR workflow

协调全面的PR工作流

mcp__claude-flow__task_orchestrate { task: "Execute multi-agent PR review and validation workflow", strategy: "parallel", priority: "high", dependencies: ["diff_analysis", "test_validation", "security_review"] }

undefined

undefined

Swarm-Coordinated PR Lifecycle

集群协同的PR生命周期

javascript

// Pre-hook: PR Initialization and Swarm Setup
const prPreHook = async (prData) => {
  // Analyze PR complexity for optimal swarm configuration
  const complexity = await analyzePRComplexity(prData);
  const topology = complexity > 7 ? "hierarchical" : "mesh";
  
  // Initialize swarm with PR-specific configuration
  await mcp__claude_flow__swarm_init({ topology, maxAgents: 8 });
  
  // Store comprehensive PR context
  await mcp__claude_flow__memory_usage({
    action: "store",
    key: `pr/${prData.number}$context`,
    value: {
      pr: prData,
      complexity,
      agents_assigned: await getOptimalAgents(prData),
      timeline: generateTimeline(prData)
    }
  });
  
  // Coordinate initial agent synchronization
  await mcp__claude_flow__coordination_sync({ swarmId: "current" });
};

// Post-hook: PR Completion and Metrics
const prPostHook = async (results) => {
  // Generate comprehensive PR completion report
  const report = await generatePRReport(results);
  
  // Update PR with final swarm analysis
  await updatePRWithResults(report);
  
  // Store completion metrics for future optimization
  await mcp__claude_flow__memory_usage({
    action: "store",
    key: `pr/${results.number}$completion`,
    value: {
      completion_time: results.duration,
      agent_efficiency: results.agentMetrics,
      quality_score: results.qualityAssessment,
      lessons_learned: results.insights
    }
  });
};

javascript

// 前置钩子：PR初始化与集群设置
const prPreHook = async (prData) => {
  // 分析PR复杂度以配置最优集群
  const complexity = await analyzePRComplexity(prData);
  const topology = complexity > 7 ? "hierarchical" : "mesh";
  
  // 使用PR专属配置初始化集群
  await mcp__claude_flow__swarm_init({ topology, maxAgents: 8 });
  
  // 存储完整的PR上下文
  await mcp__claude_flow__memory_usage({
    action: "store",
    key: `pr/${prData.number}/context`,
    value: {
      pr: prData,
      complexity,
      agents_assigned: await getOptimalAgents(prData),
      timeline: generateTimeline(prData)
    }
  });
  
  // 协调初始Agent同步
  await mcp__claude_flow__coordination_sync({ swarmId: "current" });
};

// 后置钩子：PR完成与指标收集
const prPostHook = async (results) => {
  // 生成全面的PR完成报告
  const report = await generatePRReport(results);
  
  // 用最终集群分析结果更新PR
  await updatePRWithResults(report);
  
  // 存储完成指标用于后续优化
  await mcp__claude_flow__memory_usage({
    action: "store",
    key: `pr/${results.number}/completion`,
    value: {
      completion_time: results.duration,
      agent_efficiency: results.agentMetrics,
      quality_score: results.qualityAssessment,
      lessons_learned: results.insights
    }
  });
};

Intelligent PR Merge Coordination

智能PR合并协同

bash

undefined

bash

undefined

Coordinate merge decision with swarm consensus

结合集群共识协调合并决策

mcp__claude-flow__coordination_sync { swarmId: "pr-review-swarm" }

Analyze merge readiness with multiple agents

多Agent分析合并就绪状态

mcp__claude-flow__task_orchestrate { task: "Evaluate PR merge readiness with comprehensive validation", strategy: "sequential", priority: "critical" }

Store merge decision context

存储合并决策上下文

mcp__claude-flow__memory_usage { action: "store", key: "pr$merge_decisions/#{pr_number}", value: { ready_to_merge: true, validation_passed: true, agent_consensus: "approved", final_review_score: 9.2 } }


See also: [swarm-issue.md](.$swarm-issue.md), [sync-coordinator.md](.$sync-coordinator.md), [workflow-automation.md](.$workflow-automation.md)

mcp__claude-flow__memory_usage { action: "store", key: "pr/merge_decisions/#{pr_number}", value: { ready_to_merge: true, validation_passed: true, agent_consensus: "approved", final_review_score: 9.2 } }


另请参阅: [swarm-issue.md](./swarm-issue.md), [sync-coordinator.md](./sync-coordinator.md), [workflow-automation.md](./workflow-automation.md)