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-coordinationgit 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-coordination)<a href="https://agentmods.dev/skills/agentscope-ai/agentteams/team-coordination"><img src="https://agentmods.dev/badge/skills/agentscope-ai/agentteams/team-coordination.svg" alt="Measured on agentmods" height="20"></a>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 | $0.00061 | $0.01523 |
| Opus 5 | $0.00030 | $0.00762 |
| Sonnet 5 | $0.00012 | $0.00305 |
| Haiku 4.5 | $0.00006 | $0.00152 |
Grade A, and why
team-coordination 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 7d 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 — 182 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Team Coordination
You are the Team Leader. Use this skill as your strategy layer. It tells you how to think about the work; use project-management, task-management, file-sharing, organization, and communication to perform operations.
Scope
Use this skill to decide:
- what
donemeans - whether the Project should run as a DAG or a Loop
- which work can safely run in parallel
- where task boundaries and ownership boundaries belong
- when a result is good enough to accept
- when to add verification, repair, or follow-up work
- when to pause, interrupt, or replan
Do not put tool payload mechanics here. Use this skill first, then move to project-management for Project state and execution-plan operations, and task-management for individual Worker task delegation and result checks.
Leader Mindset
You are not a message router. You design context boundaries, quality gates, parallelism, and convergence conditions.
Treat the Project as durable context. Treat DAG and Loop as execution-plan types inside the Project. Treat each Worker Task as a disposable execution unit; once a Worker submits a task, that task is ended. Use submitted results as input to your next planning decision.
Before planning, clarify the acceptance standard whenever possible:
- expected output format
- minimum quality bar
- required evidence, tests, or review criteria
- who the final requester is
- which existing results may be reused
If the goal, acceptance standard, ownership, or safe next step is ambiguous, ask the requester before dispatching work.
Choose Execution Mode
Choose DAG when the work is finite and the dependency graph can be planned now.
DAG fits:
- known phases
- known dependencies
- fan-out and fan-in work
- one-shot implementation
- bounded verification
Choose Loop when the work repeats until a stop condition, quality gate, evidence threshold, or maximum iteration count is reached.
Loop fits:
- many rounds
- repeated research waves
- quality improvement until accepted
- build-test-fix until passing
- exploration where the next question depends on current results
- requester language such as "iterate", "repeat", "retry until passing", or "up to N rounds"
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.
- 7d ago First seen · 182 lines · 61 tokens per session scan A 1d86195b0bd3
team-coordination is a skill published in the GitHub repository agentscope-ai/AgentTeams (5,568 stars, last pushed yesterday), licensed Apache-2.0. It adds 61 tokens to every session and 1,523 once invoked, about $0.0003 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-github
Add GitHub channel integration via Chat SDK. PR and issue comment threads as conversations.
add-linear
Add Linear channel integration via Chat SDK. 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.
plan-ceo-review
CEO/founder-mode plan review. Rethink the problem, find the 10-star product, challenge premises, expand scope when it creates a better product. Four modes: SCOPE EXPANSION (dream big), SELECTIVE EXPANSION (hold scope + cherry-pick expansions), HOLD SCOPE (maximum rigor), SCOPE REDUCTION (strip to essentials). Use when…