multi_agents

multi_agents is a skill for Claude Code, Codex from tubecreate/tubecli. It costs 0 tokens per session (410 once invoked), scanned A, original, MIT.

A coordination system for using several coding agents as a team. It can create teams, assign tasks, and run agents in sequence, in parallel, or through a lead agent.

In plain words
What is it for?
Use it to split research or coding work into subtasks, delegate those tasks to agent teams, and review delegation logs.
Why use it?
It removes the need to coordinate separate agents manually and keeps delegated work organized. You can choose whether agents share results in order or work independently.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it to split research or coding work into subtasks, delegate those tasks to agent teams, and review delegation logs.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/tubecreate/tubecli/multi_agents
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 tubecreate/tubecli --skill multi_agents
Clone the repo
git clone --depth 1 https://github.com/tubecreate/tubecli

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 multi_agents

README.md
[![agentmods](https://agentmods.dev/badge/skills/tubecreate/tubecli/multi_agents/github.svg)](https://agentmods.dev/skills/tubecreate/tubecli/multi_agents)
Your own site
<a href="https://agentmods.dev/skills/tubecreate/tubecli/multi_agents"><img src="https://agentmods.dev/badge/skills/tubecreate/tubecli/multi_agents/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 multi_agents

Your own site · 80×15
<a href="https://agentmods.dev/skills/tubecreate/tubecli/multi_agents"><img src="https://agentmods.dev/badge/skills/tubecreate/tubecli/multi_agents.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 0 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 410 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 $0.00000 $0.00410
Opus 5 $0.00000 $0.00205
Sonnet 5 $0.00000 $0.00082
Haiku 4.5 $0.00000 $0.00041

Measured 9d ago against content hash 3e87dfe2f327, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

multi_agents 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 5 executable files (__init__.py, commands.py, extension.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.

tubecli/extensions/multi_agents/SKILL.md · 56 lines

What it actually says

Multi-Agent Orchestration — AI Skill Guide

Extension: multi_agents

Enables multi-agent collaboration through teams, task delegation, and coordinated workflows.

Strategies

  • sequential: Agents process in order, passing context forward (chain-of-thought)
  • parallel: All agents process independently on the same task
  • lead-delegate: Lead agent analyzes task and delegates to team members

Available Commands

List Teams

tubecli multi-agent teams

Create Team

tubecli multi-agent create-team "Research Team" -a agent_id1,agent_id2,agent_id3 -s sequential

Delete Team

tubecli multi-agent delete-team team_abc123

Delegate Task

tubecli multi-agent delegate team_abc123 "Summarize the latest news about AI"

View Log

tubecli multi-agent log

API Endpoints

Method Endpoint Description
GET /api/v1/multi-agents/teams List teams
POST /api/v1/multi-agents/teams Create team
GET /api/v1/multi-agents/teams/{id} Get team
DELETE /api/v1/multi-agents/teams/{id} Delete team
POST /api/v1/multi-agents/teams/{id}/delegate Delegate task
GET /api/v1/multi-agents/log Delegation log

AI Usage

  1. Create a team with agents that have complementary skills
  2. Choose strategy based on task type:
    • Use sequential for tasks that build on each other
    • Use parallel for independent sub-tasks
    • Use lead-delegate when one agent should coordinate
  3. Delegate the task and collect combined results
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 · 56 lines · 0 tokens per session scan A 3e87dfe2f327

Subscribe to this mod's changes

multi_agents is a skill published in the GitHub repository tubecreate/tubecli (167 stars, last pushed today), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 410 tokens. 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 2026-08-30.