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.
Borrowing it
Nothing to install: this file belongs to agentscope-ai/AgentTeams. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/agentscope-ai/AgentTeams/main/AGENTS.mdgit 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/instructions/agentscope-ai/agentteams/agents-md)<a href="https://agentmods.dev/instructions/agentscope-ai/agentteams/agents-md"><img src="https://agentmods.dev/badge/instructions/agentscope-ai/agentteams/agents-md/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/instructions/agentscope-ai/agentteams/agents-md"><img src="https://agentmods.dev/badge/instructions/agentscope-ai/agentteams/agents-md.svg" alt="Reviewed on agentmods" width="80" 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 | $0.04279 | $0.04279 |
| Opus 5.5 | $0.01712 | $0.01712 |
| Sonnet 5.5 | $0.00856 | $0.00856 |
| Haiku 4.5 | $0.00428 | $0.00428 |
Grade A, and why
AgentTeams AGENTS.md 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 29d 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 — 273 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AgentTeams Codebase Navigation Guide
This file helps AI Agents (and human developers) quickly understand the project structure and find relevant code.
What is AgentTeams
AgentTeams is an open-source Agent Teams system that uses IM (Matrix protocol) for multi-Agent collaboration with human-in-the-loop oversight. It consists of a Manager Agent (coordinator) and Worker Agents (task executors), connected via an AI Gateway (Higress), Matrix Homeserver (Tuwunel), and HTTP file storage (MinIO or cloud OSS). Production-style deployments use the Kubernetes operator and Helm chart; local installs use Docker Compose scripts under install/.
Project Structure
AgentTeams/
├── agentteams-controller/ # Kubernetes operator (Go): reconciles Worker, Manager, Team, Human CRDs
├── helm/ # Helm chart (K8s): Higress, Tuwunel, MinIO, controller, Manager CR, defaults
├── manager/ # Manager images: OpenClaw-based (Dockerfile) and QwenPaw-based (Dockerfile.qwenpaw)
├── worker/ # OpenClaw Worker image (shared base pattern; runtime also selected at deploy time)
├── hermes/ # Hermes Python package source (Hermes Matrix worker runtime)
├── deepseek-harness/ # Experimental headless DeepSeek Harness Worker image and Matrix bridge
├── openhuman/ # OpenHuman Worker image: Rust core + native Matrix (channel-matrix feature)
├── openclaw-base/ # Base image: Ubuntu + Node.js + bundled agent assets + mcporter
├── shared/lib/ # Shared shell libs copied into images (agentteams-env.sh, render-skills.sh, …)
├── install/ # Local install scripts (Docker Compose / embedded “all-in-one” stack)
├── scripts/ # Project-level utilities (e.g. replay-task.sh)
├── tests/ # Automated integration tests
├── docs/ # User-facing documentation
├── design/ # Internal design notes and API specs
├── changelog/ # Archived release notes from earlier releases
├── hack/ # Maintenance helpers (e.g. image mirror scripts)
├── migrate/ # Optional migration helpers
├── blog/ # Announcement / blog source
└── .github/workflows/ # CI: build images, tests, release automation
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.
- 29d ago Changed · -8 lines · -147 tokens per session c8d0dca5d776
- 2mo ago Changed · +8 lines · +163 tokens per session 0e6731f8e3f2
- 2mo ago First seen · 273 lines · 4,263 tokens per session scan A ceec080a70e1
AgentTeams AGENTS.md is an instructions file published in the GitHub repository agentscope-ai/AgentTeams (5,941 stars, last pushed yesterday), licensed Apache-2.0. It adds 4,279 tokens to every session, about $0.0171 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.
AgentTeams AGENTS.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| AgentTeams AGENTS.mdagentscope-ai/AgentTeams | Instructions file | 5.9k | yesterday | Apache-2.0 | A | 4,279 | Codex, OpenCode |
| vscode buildNext.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 9,719 | GitHub Copilot |
| next.js AGENTS.mdvercel/next.js | Instructions file | 143k | yesterday | MIT | A | 7,461 | Codex, OpenCode |
| langchain AGENTS.mdlangchain-ai/langchain | Instructions file | 149k | yesterday | MIT | A | 4,680 | Codex, OpenCode |
| vscode oss-third-party-notices.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 5,516 | GitHub Copilot |
| vscode copilot-instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 3,093 | GitHub Copilot |
| deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness | Instructions file | 274k | 2d ago | MIT | A | 4,313 | Codex, OpenCode |