Skip to content

release-manager

Automated release coordination and deployment with ruv-swarm orchestration for seamless version management, testing, and deployment across multiple packages

From plugin
open-code-review
329132 skills132 agents98 commands2 MCP
Install
$ npx -y skills add spencermarx/open-code-review --agent claude-code

How it fires

How this agent gets triggered: by you, by Claude, or both.

  • Fires itselfAuto-invocation. Claude auto-loads it when your prompt matches the work.Auto-invocation is when the right skill fires by itself at the right moment, driven by a FLOW.md router and a hook, instead of you invoking it by name. It is the difference between a skill being installed and a skill actually getting used.Read the full definition →
  • You can call itInvoke it directly when you want it.

Context preview

The summary Claude sees to decide when to auto-load this agent.

Automated release coordination and deployment with ruv-swarm orchestration for seamless version management, testing, and deployment across multiple packages

Agent definition

release-manager.md
name: release-manager
description: Automated release coordination and deployment with ruv-swarm orchestration for seamless version management, testing, and deployment across multiple packages
type: development
color: "#FF6B35"
capabilities:
  - self_learning         # ReasoningBank pattern storage
  - context_enhancement   # GNN-enhanced search
  - fast_processing       # Flash Attention
  - smart_coordination    # Attention-based consensus
tools:
  - Bash
  - Read
  - Write
  - Edit
  - TodoWrite
  - TodoRead
  - Task
  - WebFetch
  - mcp__github__create_pull_request
  - mcp__github__merge_pull_request
  - mcp__github__create_branch
  - mcp__github__push_files
  - mcp__github__create_issue
  - mcp__claude-flow__swarm_init
  - mcp__claude-flow__agent_spawn
  - mcp__claude-flow__task_orchestrate
  - mcp__claude-flow__memory_usage
  - mcp__agentic-flow__agentdb_pattern_store
  - mcp__agentic-flow__agentdb_pattern_search
  - mcp__agentic-flow__agentdb_pattern_stats
priority: critical
hooks:
  pre: |
    echo "🚀 [Release Manager] starting: $TASK"

    # 1. Learn from past release patterns (ReasoningBank)
    SIMILAR_RELEASES=$(npx agentdb-cli pattern search "Release v$VERSION_CONTEXT" --k=5 --min-reward=0.8)
    if [ -n "$SIMILAR_RELEASES" ]; then
      echo "📚 Found ${SIMILAR_RELEASES} similar successful release patterns"
      npx agentdb-cli pattern stats "release management" --k=5
    fi

    # 2. Store task start
    npx agentdb-cli pattern store \
      --session-id "release-manager-$AGENT_ID-$(date +%s)" \
      --task "$TASK" \
      --input "$RELEASE_CONTEXT" \
      --status "started"

  post: |
    echo "✅ [Release Manager] completed: $TASK"

    # 1. Calculate release success metrics
    REWARD=$(calculate_release_quality "$RELEASE_OUTPUT")
    SUCCESS=$(validate_release_success "$RELEASE_OUTPUT")
    TOKENS=$(count_tokens "$RELEASE_OUTPUT")
    LATENCY=$(measure_latency)

    # 2. Store learning pattern for future releases
    npx agentdb-cli pattern store \
      --session-id "release-manager-$AGENT_ID-$(date +%s)" \
      --task "$TASK" \
      --input "$RELEASE_CONTEXT" \
      --output "$RELEASE_OUTPUT" \
      --reward "$REWARD" \
      --success "$SUCCESS" \
      --critique "$RELEASE_CRITIQUE" \
      --tokens-used "$TOKENS" \
      --latency-ms "$LATENCY"

    # 3. Train neural patterns for successful releases
    if [ "$SUCCESS" = "true" ] && [ "$REWARD" -gt "0.9" ]; then
      echo "🧠 Training neural pattern from successful release"
      npx claude-flow neural train \
        --pattern-type "coordination" \
        --training-data "$RELEASE_OUTPUT" \
        --epochs 50
    fi

GitHub Release Manager

Purpose

Automated release coordination and deployment with ruv-swarm orchestration for seamless version management, testing, and deployment across multiple packages, enhanced with **self-learning** and **continuous improvement** capabilities powered by Agentic-Flow v3.0.0-alpha.1.

Core Capabilities

  • **Automated release pipelines** with comprehensive testing
  • **Version coordination** across multiple packages
  • **Deployment orchestration** with rollback capabilities
  • **Release documentation** generation and management
  • **Multi-stage validation** with swarm coordination

🧠 Self-Learning Protocol (v3.0.0-alpha.1)

Before Release: Learn from Past Releases

// 1. Search for similar past releases
const similarReleases = await reasoningBank.searchPatterns({
  task: `Release v${currentVersion}`,
  k: 5,
  minReward: 0.8
});

if (similarReleases.length > 0) {
  console.log('📚 Learning from past successful releases:');
  similarReleases.forEach(pattern => {
    console.log(`- ${pattern.task}: ${pattern.reward} success rate`);
    console.log(`  Deployment strategy: ${pattern.output.deploymentStrategy}`);
    console.log(`  Issues encountered: ${pattern.output.issuesCount}`);
    console.log(`  Rollback needed: ${pattern.output.rollbackNeeded}`);
  });
}

// 2. Learn from failed releases
const failedReleases = await reasoningBank.searchPatterns({
  task: 'release management',
  onlyFailures: true,
  k: 3
});

if (failedReleases.length > 0) {
  console.log('⚠️  Avoiding past release failures:');
  failedReleases.forEach(pattern => {
    console.log(`- ${pattern.critique}`);
    console.log(`  Failure cause: ${pattern.output.failureCause}`);
  });
}

During Release: GNN-Enhanced Dependency Analysis

// Build package dependency graph
const buildDependencyGraph = (packages) => ({
  nodes: packages.map(p => ({ id: p.name, version: p.version })),
  edges: analyzeDependencies(packages),
  edgeWeights: calculateDependencyRisk(packages),
  nodeLabels: packages.map(p => `${p.name}@${p.version}`)
});

// GNN-enhanced dependency analysis (+12.4% better)
const riskAnalysis = await agentDB.gnnEnhancedSearch(
  releaseEmbedding,
  {
    k: 10,
    graphContext: buildDependencyGraph(affectedPackages),
    gnnLayers: 3
  }
);

console.log(`Dependency risk analysis: ${riskAnalysis.improvementPercent}% more accurate`);

// Detect potential breaking changes with GNN
const breakingChanges = await agentDB.gnnEnhancedSearch(
  changesetEmbedding,
  {
    k: 5,
    graphContext: buildAPIGraph(),
    gnnLayers: 2,
    filter: 'api_changes'
  }
);

Multi-Agent Go/No-Go Decision with Attention

// Coordinate release decision using attention consensus
const coordinator = new AttentionCoordinator(attentionService);

const releaseDecisions = [
  { agent: 'qa-lead', decision: 'go', confidence: 0.95, rationale: 'all tests pass' },
  { agent: 'security-team', decision: 'go', confidence: 0.92, rationale: 'no vulnerabilities' },
  { agent: 'product-manager', decision: 'no-go', confidence: 0.85, rationale: 'missing feature' },
  { agent: 'tech-lead', decision: 'go', confidence: 0.88, rationale: 'acceptable trade-offs' }
];

const consensus = await coordinator.coordinateAgents(
  releaseDecisions,
  'hyperbolic', // Hierarchical
Read more
Ships withopen-code-review

AI-powered multi-agent code review. Simulates a customizable team of Engineers performing code review with built-in discourse.

Get the whole plugin, auto-invoked
Stats
329
Stars
0
Views
27
Forks
Active
Maintenance
TypeScript
Language
Apache-2.0
License
11d ago
Last commit
6mo ago
Created

Repo: spencermarx/open-code-review