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 task-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/task-coordination)<a href="https://agentmods.dev/skills/agentscope-ai/agentteams/task-coordination"><img src="https://agentmods.dev/badge/skills/agentscope-ai/agentteams/task-coordination/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/agentscope-ai/agentteams/task-coordination"><img src="https://agentmods.dev/badge/skills/agentscope-ai/agentteams/task-coordination.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 | $0.00036 | $0.01165 |
| Opus 5.5 | $0.00014 | $0.00466 |
| Sonnet 5.5 | $0.00007 | $0.00233 |
| Haiku 4.5 | $0.00004 | $0.00117 |
Grade A, and why
task-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 5d 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 — 157 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Task Coordination
This skill provides a general coordination mechanism for shared task directories. It prevents conflicts when both Manager and Workers need to access/modify the same task workspace.
Problem
When a Worker delegates work to Manager (e.g., git operations), the Manager modifies the Worker's workspace. During this time, the Worker might also be modifying files, causing potential conflicts.
Solution
Use .processing marker files to signal "work in progress". Any party (Worker or Manager) must check for this marker before modifying a task directory.
Task Directory Structure
tasks/{task-id}/
├── workspace/ # Code workspace (shared between Worker and Manager)
├── notes/ # Worker's notes, plan.md, memory (not synced by Manager)
├── meta.json # Task metadata
└── .processing # Processing marker file (created when work in progress)
The .processing Marker
Format
Location: tasks/{task-id}/.processing
{
"processor": "manager",
"started_at": "2026-02-25T10:30:00Z",
"expires_at": "2026-02-25T10:45:00Z",
"operation": "git-delegation"
}
Fields
| Field | Description |
|---|---|
processor |
Who is processing: manager or worker name |
started_at |
ISO 8601 timestamp when processing started |
expires_at |
ISO 8601 timestamp when marker expires (15 min default) |
operation |
What operation is in progress (optional) |
run_id |
Optional unique identifier for your current operation; coding CLI execution requires it to match before passing through an active marker |
Expiration
The marker auto-expires after 15 minutes (configurable). This prevents deadlocks if a process crashes without removing the marker.
Coordination Protocol
Before Modifying Task Directory
Always follow this sequence:
- Sync from MinIO first:
mc mirror "${AGENTTEAMS_STORAGE_PREFIX}/shared/tasks/${task_id}/" "/root/agentteams-fs/shared/tasks/${task_id}/"
What ships with it
3 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.
- 5d ago Changed · +4 lines 3a6f7b9dcbe4
- 1mo ago First seen · 153 lines · 36 tokens per session scan A cc43404226a6
task-coordination is a skill published in the GitHub repository agentscope-ai/AgentTeams (5,772 stars, last pushed 3d ago), licensed Apache-2.0. It adds 36 tokens to every session and 1,165 once invoked, about $0.0001 per session on Opus 5.5. 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.
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.
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.
review-offered-task
Turn prompt for an offered swarm task: read the offer, accept with task-action and start work-on-task, or reject with a reason.