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 skillgit 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/skill)<a href="https://agentmods.dev/skills/agentscope-ai/agentteams/skill"><img src="https://agentmods.dev/badge/skills/agentscope-ai/agentteams/skill/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/skill"><img src="https://agentmods.dev/badge/skills/agentscope-ai/agentteams/skill.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 3 findings, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Prompt Injection · line 25 Hidden instructions were detected in comments or invisible text. These could contain malicious directives. Manual review is recommended.Fix: Audit all comments and invisible characters. Remove any instructions that direct the agent to perform unauthorized actions. Use plain, reviewable content.
- high Memory Poisoning · line 234 Skill manipulates agent memory, state, or stored context. Memory corruption can alter personality, override safety rules, or cause unpredictable behavior.Fix: Protect agent memory and state from modification by untrusted content. Use read-only memory for critical instructions and validate all state changes.
- medium Rogue Agent · line 87 Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
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 | $0.00028 | $0.02448 |
| Opus 5.5 | $0.00011 | $0.00979 |
| Sonnet 5.5 | $0.00006 | $0.00490 |
| Haiku 4.5 | $0.00003 | $0.00245 |
Grade A, and why
agentteams-migrate scanned grade A with 1 finding 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 1mo 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
`bash, git, python3, make, g++, curl, jq, nginx, openssh-client, ca-certificates, procps, tzdata, nodejs, npm, pnpm, mc (MinIO client), openclaw, mcporter, skills` How it starts
The opening of the file, as written. The whole thing — 238 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AgentTeams Migration Skill
This skill guides you through migrating your current OpenClaw instance into a AgentTeams managed Worker. You need to understand AgentTeams's architecture to produce a correct migration package.
AgentTeams Worker Architecture (Read This First)
AgentTeams is a multi-agent system where a Manager orchestrates multiple Workers:
- Workers run in Docker containers based on
agentteams/worker-agentimage (Ubuntu 22.04 + Node.js 22 + OpenClaw + mcporter + mc) - Workers communicate via Matrix (not Discord/Slack) — each Worker has a dedicated 3-party room (Human + Manager + Worker)
- All configuration is stored in MinIO (S3-compatible), not local filesystem
- Workers are stateless — containers can be recreated at any time, all state lives in MinIO
- The Manager controls Worker skills — Workers cannot modify their own
skills/directory
AGENTS.md Builtin-Merge System
AgentTeams uses a marker system in AGENTS.md to separate managed content from user content:
<!-- agentteams-builtin-start -->
> ⚠️ **DO NOT EDIT** this section. It is managed by AgentTeams and will be automatically
> replaced on upgrade.
(AgentTeams's Worker workspace rules, communication protocol, task execution rules, etc.)
<!-- agentteams-builtin-end -->
(Your custom content goes here — this part survives upgrades)
The builtin section (between the markers) is injected by the import script and contains:
- Workspace layout and file sync instructions
- Matrix @mention communication protocol
- Task execution workflow
- Memory and session management rules
Your migrated AGENTS.md content must go AFTER the <!-- agentteams-builtin-end --> marker. The import script handles the marker injection — you only need to produce the user content portion.
What the Worker Base Image Already Has
These tools are pre-installed — do NOT include them in the Dockerfile:
bash, git, python3, make, g++, curl, jq, nginx, openssh-client, ca-certificates, procps, tzdata, nodejs, npm, pnpm, mc (MinIO client), openclaw, mcporter, skills
What ships with it
5 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.
- 1mo ago First seen · 238 lines · 28 tokens per session scan A 154d38124851
agentteams-migrate is a skill published in the GitHub repository agentscope-ai/AgentTeams (5,825 stars, last pushed yesterday), licensed Apache-2.0. It adds 28 tokens to every session and 2,448 once invoked, about $0.0001 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
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…
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…
design-review
Designer's eye QA: finds visual inconsistency, spacing issues, hierarchy problems, AI slop patterns, and slow interactions — then fixes them. Iteratively fixes issues in source code, committing each fix atomically and re-verifying with before/after screenshots. For plan-mode design review (before implementation), use…
plan-eng-review
Eng manager-mode plan review. Lock in the execution plan — architecture, data flow, diagrams, edge cases, test coverage, performance. Walks through issues interactively with opinionated recommendations. Use when asked to "review the architecture", "engineering review", or "lock in the plan". Proactively suggest when…
pre-landing-review
Pre-landing PR review. Analyzes diff against the base branch for SQL safety, LLM trust boundary violations, conditional side effects, and other structural issues. Use when explicitly asked for the specialized pre-landing workflow. Product /review requests are handled by OpenBitFun's unified Review mechanism instead.…
autoplan
Auto-review pipeline — reads the full CEO, design, eng, and DX review skills from disk and runs them sequentially with auto-decisions using 6 decision principles. Surfaces taste decisions (close approaches, borderline scope, codex disagreements) at a final approval gate. One command, fully reviewed plan out. Use when…