Claude Swarm

An MCP server for orchestrating parallel Claude Code worker swarms with protocol-based behavioral governance. Enables multi-hour autonomous coding sessions with persistent state, parallel workers, and runtime enforcement of behavioral constraints.

Installation • Quick Start • Dashboard • Protocols • Tools

---

Features

Worker Orchestration

• Persistent State - Session state survives context compaction via MCP server
• Parallel Workers - Run multiple Claude Code workers simultaneously via tmux
• Git Worktree Isolation - Workers run in isolated git worktrees for safe parallel modification
• Worker Plan Mode - Workers analyze codebases and produce plans before implementing (auto-approved)
• Competitive Planning - Complex features get two competing implementation plans
• Confidence Monitoring - Multi-signal scoring detects struggling workers
• Enforced Verification - Test-as-supervisor pattern with configurable verification commands
• Auto-retry - Failed features automatically retry with configurable limits
• Feature Dependencies - Define execution order between features
• File-Based Task Locking - Atomic mutual exclusion prevents workers from conflicting
• Post-Completion Reviews - Automated code and architecture reviews with actionable findings

Long-Running Autonomy

• Ralph Loop - Fresh Claude context per iteration eliminates context rot for long sessions
• Days-Long Sessions - Supports hours/days of autonomous execution with checkpointing
• Crash Recovery - Automatic session resumption after crashes or machine restarts
• Failure Pattern Learning - Records what works/fails for future worker prompts

Protocol-Based Governance

• Behavioral Protocols - Define constraints on what workers can/cannot do
• Pre-spawn Validation - Verify protocols allow task before worker starts
• Continuous Monitoring - Track constraint violations during execution
• LLM-Generated Protocols - Workers can propose new protocols (validated against base constraints)
• Cross-instance Sync - Share protocols across MCP instances

Monitoring & Dashboard

• Real-time Web Dashboard - Live UI at http://localhost:3456 with Server-Sent Events
• Live Terminal Streaming - Watch worker output with ANSI color support
• Review Worker Visibility - Code and architecture review progress in dashboard
• Violation Tracking - Audit log of all protocol violations
• Git Checkpoints - Commit progress after each feature

Repository Setup

• Auto-Configuration - Set up CI/CD, issue templates, and documentation in parallel
• Platform Detection - GitHub, GitLab, Gitea, Bitbucket, Azure DevOps support
• Project Analysis - Detects languages, frameworks, and adapts configuration
• Merge Mode - Preserves existing configs by default, with optional force overwrite

How It Works

The orchestrator pattern separates concerns for reliable long-running sessions:

• Orchestrator (Claude Code): Plans work, monitors progress, makes decisions
• MCP Server: Maintains persistent state that survives context compaction
• Workers: Isolated Claude Code sessions in git worktrees via tmux that implement individual features
• Protocols: Behavioral constraints governing what workers can/cannot do
• Ralph Loop: External bash loop that launches fresh Claude sessions per iteration, with state persisted to the filesystem (progress files, git history)

Worker Lifecycle

Workers follow a two-phase lifecycle when plan mode is enabled (complexity >= 30):

1. Plan Phase - Worker runs with read-only tools (Read, Glob, Grep, Write), analyzes the codebase, and produces a structured plan
2. Auto-Review - Orchestrator scores the plan on test strategy, risk assessment, file specificity, and step count
3. Implement Phase - Worker runs with full tools, following the approved plan step by step

Ralph Loop (Long-Running Autonomy)

For long-running features, the Ralph Loop replaces single long-lived sessions:

1. Each iteration launches a fresh Claude session (no context rot)
2. State persists via filesystem: progress.md, git history, .done files
3. Prompt re-reads current state each iteration (self-reloading context)
4. Configurable stopping conditions: completion marker, time limit, max iterations
5. Git diff injected into prompt so worker sees what changed

Session Resilience

Sessions survive crashes and machine restarts:

• Checkpointing - State snapshots every ~15 minutes while workers are running
• Heartbeat Detection - PID-based liveness detection identifies stale sessions
• Crash Recovery - resume_session detects crashes, loads checkpoints, restarts dead workers
• Graceful Shutdown - shutdown_session creates checkpoint and stops workers cleanly

This separation enables:

• Parallel execution: Multiple workers implement features simultaneously
• State persistence: Session state survives context compaction via the MCP server
• Failure recovery: Workers can retry, rollback, or be guided when stuck
• Behavioral governance: Protocols enforce constraints on worker actions

Quick Start

Prerequisites

• Node.js 18+
• tmux (brew install tmux on macOS)
• Claude Code CLI

Installation

One-liner install (recommended):

curl -fsSL https://raw.githubusercontent.com/cj-vana/claude-swarm/main/install.sh | bash

This will clone the repo, build, register the MCP server, and install the /swarm skill.

Manual installation

git clone https://github.com/cj-vana/claude-swarm.git
cd claude-swarm
npm install
npm run build

# Add to Claude Code
claude mcp add claude-swarm --scope user -- node $(pwd)/dist/index.js

# Install the skill (optional but recommended)
mkdir -p ~/.claude/skills/swarm && cp skill/SKILL.md ~/.claude/skills/swarm/

Basic Usage

Tell Claude to use the swarm:

Use /swarm to build a REST API with authentication, user management, and tests

Or follow the workflow phases manually:

Phase 1: Setup
  → orchestrator_init - Initialize session with features
  → configure_verification - Set up test/build commands
  → set_dependencies - Define feature order

Phase 2: Pre-Work (per feature)
  → get_feature_complexity - Check if competitive planning needed
  → enrich_feature - Add relevant context

Phase 3: Execute
  → start_worker or start_parallel_workers

Phase 4: Monitor
  → sleep 180 - Wait before checking
  → check_worker (heartbeat: true) - Lightweight status
  → send_worker_message - Guide if stuck

Phase 5: Complete
  → run_verification - Run tests
  → mark_complete - Record success/failure
  → commit_progress - Git checkpoint

Phase 6: Review
  → check_reviews - Monitor automated reviews
  → get_review_results - See findings

The /swarm Skill

The /swarm skill provides guided orchestration with a complete workflow:

Use /swarm to build a REST API with authentication, user management, and tests

The skill automates:

• Phase 0: Repository readiness check (runs setup_analyze)
• Phase 1: Session setup with feature decomposition
• Phase 2: Pre-work preparation (complexity analysis, context enrichment)
• Phase 3: Execution (manual or auto-orchestration)
• Phase 4: Monitoring loop with confidence tracking
• Phase 5: Completion verification and git checkpoints
• Phase 6: Post-completion reviews

Installing the skill:

mkdir -p ~/.claude/skills/swarm && cp skill/SKILL.md ~/.claude/skills/swarm/

See skill/SKILL.md for the complete workflow reference.

Protocol System

Protocols define behavioral constraints that govern worker actions, enabling safe autonomous operation with clear boundaries.

Constraint Types

| Type | Description | Example | |------|-------------|---------| | tool_restriction | Allow/deny specific tools | Only allow Read, Glob, Grep | | file_access | Control file system access | Block access to .env files | | output_format | Require specific output patterns | Must include test coverage report | | behavioral | High-level behavior rules | Require confirmation before destructive actions | | temporal | Time-based constraints | Max 30 minutes per feature | | resource | Resource usage limits | Max 100 file operations | | side_effect | Control external effects | No network requests, no git push |

Example Protocol

{
  "id": "safe-refactoring-v1",
  "name": "Safe Refactoring Protocol",
  "version": "1.0.0",
  "priority": 100,
  "constraints": [
    {
      "id": "no-secrets",
      "type": "file_access",
      "rule": {
        "type": "file_access",
        "deniedPaths": ["**/.env", "**/secrets.*", "**/credentials.json"]
      },
      "severity": "error",
      "message": "Cannot access files that may contain secrets"
    }
  ],
  "enforcement": {
    "mode": "strict",
    "preExecution": true,
    "postExecution": true,
    "onViolation": "block"
  }
}

Protocol Workflow

1. protocol_register - Register a new protocol
2. protocol_activate - Activate for enforcement
3. start_worker - Workers are validated against active protocols
4. [worker runs with continuous monitoring]
5. get_violations - Review any constraint violations

LLM-Generated Protocols

Workers can propose new protocols validated against immutable base constraints:

1. get_base_constraints - View immutable security rules
2. propose_protocol - Worker submits proposal
3. review_proposals - See pending proposals with risk scores
4. approve_protocol / reject_protocol - Human review for high-risk

Base Constraints (cannot be overridden):

• Certain tools always denied (e.g., dangerous system commands)
• Critical paths always protected (e.g., /etc, system files)
• Maximum privilege ceiling enforced

Competitive Planning

For complex features, spawn two planners with different approaches:

1. get_feature_complexity(featureId)     # Analyze complexity (0-100)
2. start_competitive_planning(featureId) # Spawn Planner A & B
3. [wait for planners to complete]
4. evaluate_plans(featureId)             # Compare and pick winner
5. start_worker(featureId)               # Implement with winning plan

• Planner A: Incremental, safe approach
• Planner B: Elegant, innovative approach
• Threshold: Features scoring 60+ trigger competitive planning

Confidence Monitoring

Real-time confidence scoring detects struggling workers:

| Signal | Weight | Measures | |--------|--------|----------| | Tool Activity | 35% | Read->Edit->Test cycles, stuck loops | | Self-Reported | 35% | Worker writes to .confidence file | | Output Analysis | 30% | Error patterns, frustration language |

Levels: High (80-100), Medium (50-79), Low (25-49), Critical (0-24)

set_confidence_threshold(35)       # Configure alert level
get_worker_confidence(featureId)   # Get detailed breakdown

Auto-Orchestration

For fully autonomous execution, use auto_orchestrate:

auto_orchestrate(projectDir, strategy: "adaptive", maxConcurrent: 5)

This handles Phases 3-5 automatically:

• Schedules workers based on dependencies
• Monitors progress and handles failures
• Runs verification commands
• Marks features complete
• Commits progress at checkpoints

Scheduling Strategies

| Strategy | Behavior | |----------|----------| | breadth-first | Maximize parallel execution of independent features | | depth-first | Focus on unblocking dependent feature chains | | adaptive | System decides based on dependency graph (default) |

When to Use

• Auto-orchestration: Large feature sets, hands-off execution
• Manual orchestration: Fine-grained control, complex dependencies, debugging

Post-Completion Reviews

Automated code and architecture reviews run after all workers complete:

1. All features complete -> session status changes to "reviewing"
2. Code review worker analyzes: bugs, security, style, test coverage
3. Architecture review worker analyzes: coupling, patterns, scalability
4. Findings aggregated into progress log
5. Session completes with review summary

Review workers output structured JSON findings:

• .claude/orchestrator/workers/code-review.findings.json
• .claude/orchestrator/workers/architecture-review.findings.json

Severity levels: clean, minor, moderate, major, critical

Acting on Review Findings

Convert review findings into actionable features:

# View available issues from reviews
implement_review_suggestions(projectDir)

# Create features from specific issues
implement_review_suggestions(projectDir, issueIndices: [0, 2, 5])

# Auto-select warnings and errors
implement_review_suggestions(projectDir, autoSelect: true, minSeverity: "warning")

Configure or trigger manually:

configure_reviews(enabled: true, skipOnFailure: false)
run_review(reviewTypes: ["code", "architecture"])
get_review_results(format: "detailed")

Repository Setup

Automatically configure repositories with development best practices:

# Analyze repository freshness and missing configs
setup_analyze(projectDir)

# Initialize setup with parallel workers
setup_init(projectDir)

# Check setup progress
setup_status(projectDir)

Configuration Types

| Type | Description | Files Created | |------|-------------|---------------| | CLAUDE.md | Project guidance for Claude Code | CLAUDE.md | | GitHub CI | Build, test, lint workflows | .github/workflows/ci.yml | | Dependabot | Automated dependency updates | .github/dependabot.yml | | Release Please | Automated version bumps and changelogs | .github/workflows/release-please.yml | | Issue Templates | Structured bug/feature reporting | .github/ISSUE_TEMPLATE/*.yml | | PR Template | Consistent pull request descriptions | .github/PULL_REQUEST_TEMPLATE.md | | CONTRIBUTING.md | Contribution guidelines | CONTRIBUTING.md | | SECURITY.md | Security policy and vulnerability reporting | SECURITY.md |

Customization

# Skip specific config types
setup_init(projectDir, skipConfigs: ["dependabot", "release-please"])

# Force overwrite existing files
setup_init(projectDir, force: true)

# Override platform detection
setup_init(projectDir, platform: "gitlab")

Feature Rollback

The orchestrator creates git snapshot branches before each worker starts, enabling safe rollback of failed features.

How Rollback Works

1. Snapshot Creation: start_worker creates swarm/{featureId} branch at current HEAD
2. Worker Execution: Worker makes changes to working directory
3. On Failure: Use rollback_feature to restore pre-worker state

Rollback Tools

| Tool | Description | |------|-------------| | rollback_feature | Restore files changed by a worker | | check_rollback_conflicts | Check for conflicts with other workers |

Usage

# Rollback all files changed by feature
rollback_feature(projectDir, featureId: "feature-1")

# Rollback specific files only
rollback_feature(projectDir, featureId: "feature-1", files: ["src/component.ts"])

Warning: When rolling back in parallel worker environments, other workers' changes to the same files will also be reverted.

Web Dashboard

A real-time web dashboard is available at http://localhost:3456:

• Session Overview - Progress bar, feature counts, session statistics
• Feature Cards - Status, dependencies, worker assignment
• Live Terminal Output - Real-time streaming with ANSI color support
• Review Worker Progress - Code and architecture review visibility
• Dark Mode - Automatic theme detection

Dashboard API

The dashboard exposes a REST API for programmatic access:

| Endpoint | Method | Description | |----------|--------|-------------| | /api/status | GET | Session overview with elapsed time and progress summary | | /api/features | GET | Feature list with detail

…

Source & license

This open-source MCP server is cataloged on AgentStack and links to its original source — we do not rehost the code.

• Author: cj-vana
• Source: cj-vana/claude-swarm
• License: MIT

Install and usage instructions live in the source repository linked above.