agent-avengers

agent-avengers is a skill for Claude Code, Codex from LeoYeAI/openclaw-master-skills. It costs 97 tokens per session (6,198 once invoked), scanned A, original, MIT.

A multi-agent orchestration system that breaks a complex task into smaller jobs, creates specialist agents for them, runs independent work in parallel, and combines the results.

In plain words
What is it for?
Use it for tasks such as researching several companies at once, assigning different roles to agents, collecting their findings, and producing one combined report.
Why use it?
It reduces the manual effort of coordinating several agents on a large task. The workflow also includes checking, merging, and cleaning up temporary agents after the work is done.

Skill for Claude CodeCodex

Which agent this was written for is unclear — built for openclaw. Also seen: built for openclaw.

Good fit Use it for tasks such as researching several companies at once, assigning different roles to agents, collecting their findings, and producing one combined report.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/leoyeai/openclaw-master-skills/agent-avengers
About the project

OpenClaw Master Skills is a curated, regularly updated collection of skills that extends an AI personal assistant platform with capabilities such as research, browser automation, presentation creation, and prompt work. It is intended for people using OpenClaw or MyClaw.ai to give their agents additional tasks and workflows. The catalogue contains many skills and agents from this collection.

LeoYeAI/openclaw-master-skills · 2,141 stars · on GitHub · myclaw.ai

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent
npx skills add LeoYeAI/openclaw-master-skills --skill agent-avengers
Clone the repo
git clone --depth 1 https://github.com/LeoYeAI/openclaw-master-skills

Made for: Claude Code, Codex.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for agent-avengers

README.md
[![agentmods](https://agentmods.dev/badge/skills/leoyeai/openclaw-master-skills/agent-avengers/github.svg)](https://agentmods.dev/skills/leoyeai/openclaw-master-skills/agent-avengers)
Your own site
<a href="https://agentmods.dev/skills/leoyeai/openclaw-master-skills/agent-avengers"><img src="https://agentmods.dev/badge/skills/leoyeai/openclaw-master-skills/agent-avengers/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for agent-avengers

Your own site · 80×15
<a href="https://agentmods.dev/skills/leoyeai/openclaw-master-skills/agent-avengers"><img src="https://agentmods.dev/badge/skills/leoyeai/openclaw-master-skills/agent-avengers.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 97 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 6,198 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00097 $0.06198
Opus 5 $0.00048 $0.03099
Sonnet 5 $0.00019 $0.01240
Haiku 4.5 $0.00010 $0.00620

Measured 9d ago against content hash d6a3f5abd327, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

agent-avengers scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 9d ago.

The scan reads SKILL.md. This mod also ships 7 executable files (scripts/assemble.py, scripts/consolidate.py, scripts/execute.py, …), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

skills/agent-avengers/SKILL.md · 832 lines

How it starts

The opening of the file, as written. The whole thing — 832 lines — stays where its author put it; the contents beside it link to each section on GitHub.

🦸 Agent Avengers

"어벤저스, 어셈블!" — 복잡한 태스크를 자동으로 에이전트 팀이 처리

핵심 기능

  1. 자동 태스크 분해 — 큰 작업을 독립적 서브태스크로 분할
  2. 동적 에이전트 생성 — 각 태스크에 맞는 전문 에이전트 즉석 생성
  3. 병렬 실행 — 독립 태스크는 동시 처리
  4. 자동 통합 — 결과 수집, 검증, 병합
  5. 완료 후 정리 — 임시 에이전트 자동 해제

사용법

기본 사용

사용자: "어벤저스 어셈블! [복잡한 태스크 설명]"

예시

"어벤저스 어셈블! 경쟁사 A, B, C 분석해서 비교 리포트 만들어줘"

→ 자동으로:
  1. 태스크 분해 (3개 리서치 + 1개 통합)
  2. 에이전트 3개 스폰 (각 회사 담당)
  3. 병렬 리서치 실행
  4. 결과 통합 에이전트가 최종 리포트 생성
  5. 완료 보고

워크플로우

┌─────────────────────────────────────────────────────────────────┐
│                    🦸 AVENGERS ASSEMBLE                         │
├─────────────────────────────────────────────────────────────────┤
│                                                                 │
│  1️⃣  ANALYZE — 태스크 분석 및 분해                              │
│      └─ 목표 파악 → 서브태스크 도출 → 의존성 매핑                 │
│                                                                 │
│  2️⃣  RECRUIT — 에이전트 팀 구성                                 │
│      └─ 각 서브태스크에 최적 에이전트 프로필 생성                 │
│      └─ 에이전트 역할: 🔬연구 🖊️작성 🔍분석 ✅검토 🔧통합        │
│                                                                 │
│  3️⃣  DEPLOY — 에이전트 스폰 및 태스크 할당                      │
│      └─ sessions_spawn으로 병렬 실행                            │
│      └─ 각 에이전트에 명확한 입력/출력 지정                      │
│                                                                 │
│  4️⃣  MONITOR — 진행 상황 추적                                   │
│      └─ 완료 대기, 실패 시 재시도 또는 대체                      │
│                                                                 │
│  5️⃣  ASSEMBLE — 결과 통합                                       │
│      └─ 모든 산출물 수집 → 검증 → 병합                          │
│                                                                 │
│  6️⃣  REPORT — 최종 보고 및 정리                                 │
│      └─ 사용자에게 결과 전달, 임시 리소스 정리                   │
│                                                                 │
└─────────────────────────────────────────────────────────────────┘

Read the full file on GitHub · 832 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 9d ago First seen · 832 lines · 97 tokens per session scan A d6a3f5abd327

Subscribe to this mod's changes

agent-avengers is a skill published in the GitHub repository LeoYeAI/openclaw-master-skills (2,141 stars, last pushed 1mo ago), licensed MIT. It adds 97 tokens to every session and 6,198 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.