agent-avengers

Review·Scanned 2/18/2026

This skill orchestrates multi-agent workflows to decompose tasks, spawn agents, run them, and consolidate results. It contains explicit execution instructions (e.g., os.system('clear'), python3 scripts/consolidate.py) and network/install commands referencing https://github.com/oozoofrog/agent-avengers.git and the AVENGERS_WORKSPACE env var.

from clawhub.ai·v1.0.0·74.9 KB·0 installs
Scanned from 1.0.0 at 445e2a1 · Transparency log ↗
$ vett add clawhub.ai/oozoofrog/agent-avengersReview findings below

Agent Avengers

🦸 All-in-One Multi-Agent Orchestration

한국어 README

Installation

clawhub install agent-avengers

Or clone directly:

git clone https://github.com/oozoofrog/agent-avengers.git ~/.openclaw/workspace/skills/agent-avengers

Usage

Avengers assemble! [complex task description]

Examples

Avengers assemble! Analyze competitors A, B, and C, then create a comparison report
Avengers assemble! Build a full-stack todo app with React frontend and Node.js backend

How It Works

  1. Decompose — Break down the task into subtasks
  2. Compose — Assign specialized agents to each subtask
  3. Execute — Run in parallel or sequential order
  4. Consolidate — Collect and merge results
  5. Report — Deliver final output

Agent Types

TypeRole
🔬 ResearcherInvestigation, data collection
🔍 AnalystAnalysis, pattern discovery
🖊️ WriterDocumentation, content creation
💻 CoderCode implementation
✅ ReviewerQuality review
🔧 IntegratorResult consolidation

Agent Modes

ModeDescription
🔷 ExistingUse registered agents (watson, picasso, etc.)
🔶 SpawnedCreate one-off sub-agents on demand
🟣 Multi-ProfileInvolve other OpenClaw bot instances
🔷🔶🟣 HybridCombine all modes (recommended)

Emergent Collaboration Patterns

  • 🗳️ Competitive Draft — Multiple agents work independently, best solution wins
  • 🎭 Role Rotation — Agents swap roles each round
  • ⚔️ Adversarial Collaboration — Creator vs Critic iterations
  • 🧬 Evolutionary Selection — Solutions crossbreed and evolve
  • 🐝 Swarm Intelligence — Many micro-agents tackle small chunks
  • 🔗 Chain Relay — Output → Input chaining
  • 💭 Consensus Protocol — Unanimous agreement required
  • 🎪 Cross-Domain Jam — Combine different expertise areas
  • 🪞 Meta Observer — Agent watches and coaches the team
  • Temporal Split — Short/mid/long-term parallel approaches
  • 🎰 Task Auction — Confidence-based bidding
  • 🧠 Shared Memory — Real-time discovery sharing

Configuration

avengers.yaml:

maxAgents: 5
timeoutMinutes: 120
retryCount: 2
defaultModel: sonnet

Scripts

ScriptDescription
scripts/assemble.pyTask decomposition & plan generation
scripts/execute.pyGenerate execution commands
scripts/monitor.pyProgress monitoring (supports --watch)
scripts/consolidate.pyResult consolidation

License

MIT