AgentTeams is a runtime platform where multiple AI agents collaborate in shared Matrix rooms under the coordination of a manager. It is for human-supervised or enterprise workflows that need visible, auditable cooperation among agents running on different runtimes, with shared files and centralized traffic management.
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 agentscope-ai/AgentTeams --skill team-managementgit clone --depth 1 https://github.com/agentscope-ai/AgentTeamsWrote 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/agentscope-ai/agentteams/team-management)<a href="https://agentmods.dev/skills/agentscope-ai/agentteams/team-management"><img src="https://agentmods.dev/badge/skills/agentscope-ai/agentteams/team-management.svg" alt="Measured on agentmods" 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 | $0.00036 | $0.00596 |
| Opus 5 | $0.00018 | $0.00298 |
| Sonnet 5 | $0.00007 | $0.00119 |
| Haiku 4.5 | $0.00004 | $0.00060 |
Grade A, and why
team-management 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 8d 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.
How it starts
The opening of the file, as written. The whole thing — 49 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Team Management
A Team consists of 1 Team Leader + N Workers. The Team Leader is a special Worker with management skills that handles task decomposition and assignment within the team. Manager delegates tasks to Team Leaders, not directly to team workers.
Quick Create
# 1. Create each Worker CR with worker-management, then reference them
agt create team \
--name <TEAM_NAME> \
--leader-name <LEADER_NAME> \
--workers <w1>,<w2>
# 2. @mention the Leader in Leader Room to assign task
The Team command fails if a referenced Worker does not exist. Configure model, runtime, image, resources, identity, skills, MCP, channel policy, and lifecycle on each Worker CR. After Team reconciliation, @mention the Leader in the Leader Room; the Leader will coordinate referenced workers in the Team Room.
Full workflow: read
references/create-team.md
If admin asks for CPU or memory requests/limits, update Worker.spec.resources. Changing resources recreates that Worker's container, so confirm it is not mid-task.
Gotchas
- Team Leader is a Worker container — same runtime, but with team-leader-agent skills instead of worker-agent skills
- Team workers only talk to their Leader — their groupAllowFrom has [Leader, Team Admin], NOT Manager
- Manager only talks to Team Leader — never @mention team workers directly
- Team Room includes Team Admin — it's Leader + Team Admin + all team workers (no Global Admin unless they are Team Admin)
- Leader Room is standard 3-party — Manager + Global Admin + Leader (same as regular worker room)
- Leader DM is Team Admin ↔ Leader — for team-level management
- Team Admin defaults to Global Admin — if
--team-adminnot specified - Delegated tasks use
--delegated-to-team— so heartbeat knows to check with Leader, not workers - Team never owns Worker runtime configuration or lifecycle — update the referenced Worker CR directly
Operation Reference
| Admin wants to... | Read | Command |
|---|---|---|
| Create a new team | references/create-team.md |
agt create team |
| Understand team lifecycle | references/team-lifecycle.md |
— |
| Delegate task to team | references/team-task-delegation.md |
— |
| Add/remove worker from team | references/team-lifecycle.md |
agt get team |
| Stop/delete a member Worker | references/team-lifecycle.md |
scripts/lifecycle-worker.sh (per worker) |
What ships with it
4 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.
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.
- 8d ago First seen · 49 lines · 36 tokens per session scan A 07be1f3bb798
team-management is a skill published in the GitHub repository agentscope-ai/AgentTeams (5,579 stars, last pushed 3d ago), licensed Apache-2.0. It adds 36 tokens to every session and 596 once invoked, about $0.0002 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 2026-08-30.
Other skills, from other repositories
add-linear
Add Linear channel integration via Chat SDK. Issue comment threads as conversations.
add-github
Add GitHub channel integration via Chat SDK. PR and issue comment threads as conversations.
slack-construct-agents
Standing context for Slack sibling agents — one room per team, creator-posted introductions, bot-to-bot hop discipline. Ships as instructions.md composed into the group's CLAUDE.md at spawn; there is no workflow to invoke.
mission-control
Interact with Mission Control — AI agent orchestration dashboard. Use when registering agents, managing tasks, syncing skills, or querying agent/task status via MC APIs.
multi-agent
A process for coordinating multiple coding agents by splitting work among scouts, workers, reviewers, and repair agents. Each agent has a defined role and task.
ship
Ship workflow: detect + merge base branch, run tests, review diff, bump VERSION, update CHANGELOG, commit, push, create PR. Use when asked to "ship", "deploy", "push to main", "create a PR", "merge and push", or "get it deployed". Proactively invoke this skill (do NOT push/PR directly) when the user says code is…