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 service-publishinggit 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/service-publishing)<a href="https://agentmods.dev/skills/agentscope-ai/agentteams/service-publishing"><img src="https://agentmods.dev/badge/skills/agentscope-ai/agentteams/service-publishing/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/service-publishing"><img src="https://agentmods.dev/badge/skills/agentscope-ai/agentteams/service-publishing.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 | $0.00032 | $0.00613 |
| Opus 5 | $0.00016 | $0.00307 |
| Sonnet 5 | $0.00006 | $0.00123 |
| Haiku 4.5 | $0.00003 | $0.00061 |
Grade A, and why
service-publishing 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 10d 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 — 101 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Service Publishing
Overview
Expose HTTP services running inside worker containers to the outside world via the Higress gateway. Each exposed port gets an auto-generated domain name.
How It Works
Add expose to a Worker's spec to publish container ports. The controller automatically creates the Higress domain, service source, and route.
Auto-generated domain pattern:
worker-{name}-{port}-local.agentteams.io
Example: worker alice exposing port 8080 → worker-alice-8080-local.agentteams.io
Usage
Via CLI
# Expose port 8080 for worker alice
agt apply worker --name alice --model qwen3.5-plus --expose 8080
# Expose multiple ports
agt apply worker --name alice --model qwen3.5-plus --expose 8080,3000
# Check exposed ports
agt get worker alice
# Look for status.exposedPorts in the output
# Remove exposed ports (update without --expose)
agt apply worker --name alice --model qwen3.5-plus
Via YAML
apiVersion: agentteams.io/v1beta1
kind: Worker
metadata:
name: alice
spec:
model: qwen3.5-plus
expose:
- port: 8080
- port: 3000
Apply with:
agt apply -f worker.yaml
Workers referenced by a Team
Configure expose on the Worker CR, then reference that Worker from the Team:
apiVersion: agentteams.io/v1beta1
kind: Worker
metadata:
name: lead
spec:
model: qwen3.5-plus
---
apiVersion: agentteams.io/v1beta1
kind: Worker
metadata:
name: backend
spec:
model: qwen3.5-plus
expose:
- port: 8080
---
apiVersion: agentteams.io/v1beta1
kind: Team
metadata:
name: dev-team
spec:
workerMembers:
- name: lead
role: team_leader
- name: backend
role: worker
Important Notes
- The worker container must be running and the service must be listening on the specified port before it can be accessed
- Domains are auto-generated; custom domains are not yet supported
- No authentication is configured on exposed routes (public access)
- Docker DNS resolves the worker container name (
agentteams-worker-{name}) automatically withinagentteams-net - To stop exposing a port, remove it from the
exposelist and re-apply
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.
- 10d ago First seen · 101 lines · 32 tokens per session scan A f243ae38639e
service-publishing is a skill published in the GitHub repository agentscope-ai/AgentTeams (5,584 stars, last pushed 4d ago), licensed Apache-2.0. It adds 32 tokens to every session and 613 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
Pynchy Ops
Use when managing the pynchy service on the server — deploying changes, observing logs, checking service status, restarting the service, setting up GitHub auth, rebuilding the agent container, or running commands on the live Pynchy host. Also use when interacting with the LiteLLM proxy — investigating failed requests…
aws-serverless
Specialized skill for building production-ready serverless applications on AWS. Covers Lambda functions, API Gateway, DynamoDB, SQS/SNS event-driven patterns, SAM/CDK deployment, and cold start optimization.
pilot-api-gateway-manager-setup
Deploy an API gateway management system with 4 agents. Use this skill when: 1. User wants to set up API gateway management with service discovery, routing, auth, and monitoring 2. User is configuring agents for API request routing, rate limiting, or backend health tracking 3. User asks about API gateway pipelines…
azure-functions
Expert patterns for Azure Functions development including isolated worker model, Durable Functions orchestration, cold start optimization, and production patterns. Covers .NET, Python, and Node.js programming models. Use when: azure function, azure functions, durable functions, azure serverless, function app.
aws-serverless
Specialized skill for building production-ready serverless applications on AWS. Covers Lambda functions, API Gateway, DynamoDB, SQS/SNS event-driven patterns, SAM/CDK deployment, and cold start optimization.
azure-functions
Expert patterns for Azure Functions development including isolated worker model, Durable Functions orchestration, cold start optimization, and production patterns. Covers .NET, Python, and Node.js programming models. Use when: azure function, azure functions, durable functions, azure serverless, function app.