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.
npx skills add tubecreate/tubecli --skill multi_agentsgit clone --depth 1 https://github.com/tubecreate/tubecliWrote 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.
[](https://agentmods.dev/skills/tubecreate/tubecli/multi_agents)<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.
<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>- NVIDIA SkillSpector pass
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.
| Model | Per session | Once 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 |
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.
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.
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
- Create a team with agents that have complementary skills
- 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
- Delegate the task and collect combined results
What ships with it
14 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- __init__.py 182 B runs code
- commands.py 4.7 KB runs code
- extension.py 16 KB runs code
- locales/en.json 2.5 KB
- locales/es.json 2.6 KB
- locales/ja.json 2.9 KB
- locales/ko.json 2.6 KB
- locales/ru.json 3.6 KB
- locales/tr.json 2.7 KB
- locales/vi.json 2.7 KB
- locales/zh-TW.json 2.4 KB
- locales/zh.json 2.4 KB
- routes.py 5.6 KB runs code
- templates.py 18 KB runs code
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.
- 9d ago First seen · 56 lines · 0 tokens per session scan A 3e87dfe2f327
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.
Other skills, from other repositories
auth_manager
Manage OAuth credentials & tokens for Google, Facebook, TikTok.
cloud_api
Manages cloud AI provider API keys for Gemini, OpenAI, Claude, DeepSeek, Grok.
multi_agents
Enables multi-agent collaboration through teams, task delegation, and coordinated workflows.
ollama_manager
Manages local Ollama AI models for agents to use without cloud API keys.
Browser Automation
Core browser automation features including profile management, fingerprint spoofing, and AI interaction.
rework-rate
Measure and interpret PR rework rate — the emerging 5th DORA metric.