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 project-managementgit 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/project-management)<a href="https://agentmods.dev/skills/agentscope-ai/agentteams/project-management"><img src="https://agentmods.dev/badge/skills/agentscope-ai/agentteams/project-management.svg" alt="Measured on agentmods" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
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 →
- medium Excessive Agency · line 18 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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 | $0.00043 | $0.00497 |
| Opus 5 | $0.00022 | $0.00249 |
| Sonnet 5 | $0.00009 | $0.00099 |
| Haiku 4.5 | $0.00004 | $0.00050 |
Grade A, and why
project-management scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 8d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
Project Management
A project has: a Project Room (Matrix), a plan.md (single source of truth), a meta.json, and individual task files under shared/tasks/{task-id}/.
shared/projects/{project-id}/
├── meta.json
└── plan.md
Gotchas
- Check YOLO mode BEFORE drafting the plan —
[ "${AGENTTEAMS_YOLO:-}" = "1" ] || [ -f ~/yolo-mode ]. In YOLO mode you MUST auto-confirm increate-project.mdStep 1c; never post a "please confirm" question, the admin will not reply and the project stalls forever. Seereferences/create-project.mdStep 0. - Project room MUST always include the human admin — non-negotiable. The script handles this, but if you ever create a room manually, always invite admin
- plan.md is the single source of truth — all task status, assignments, and dependencies live here. Always sync to MinIO after changes
- Do NOT proceed to next phase while REVISION_NEEDED is pending — revision must complete first
- "All tasks complete" step is mandatory even in YOLO mode — always update meta.json, plan.md, and notify admin
- plan.md had duplicate sections in the old version — use
references/plan-format.mdas the canonical format - Always adapt language to admin's preferred language when posting in rooms or DMs
- Always read SOUL.md before composing notifications — use the persona and language defined there
Operation Reference
Read the relevant doc before executing. Do not load all of them.
| Situation | Read |
|---|---|
| Admin asks to start a new project | references/create-project.md |
| Need to assign a task or handle completion | references/task-lifecycle.md |
| Need plan.md / result.md format | references/plan-format.md |
| Blocked task, plan changes, mid-project onboarding, headcount request, heartbeat monitoring | references/plan-changes.md |
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.
- 8d ago First seen · 37 lines · 43 tokens per session scan A 8df3f266590b
project-management is a skill published in the GitHub repository agentscope-ai/AgentTeams (5,576 stars, last pushed 2d ago), licensed Apache-2.0. It adds 43 tokens to every session and 497 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
add-linear
Add Linear channel integration via Chat SDK. Issue comment threads as conversations.
add-github
Add GitHub channel integration via Chat SDK. PR and 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.
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…