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 agentmods add skills/agentscope-ai/agentteams/roomflownpx skills add agentscope-ai/AgentTeams --skill roomflowgit 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/roomflow)<a href="https://agentmods.dev/skills/agentscope-ai/agentteams/roomflow"><img src="https://agentmods.dev/badge/skills/agentscope-ai/agentteams/roomflow.svg" alt="Measured on agentmods" 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 | $0.00063 | $0.00373 |
| Opus 5 | $0.00032 | $0.00187 |
| Sonnet 5 | $0.00013 | $0.00075 |
| Haiku 4.5 | $0.00006 | $0.00037 |
Grade A, and why
teamharness-roomflow 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 6d 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
Roomflow
Use this skill when a Leader needs to identify the current Matrix room or prepare the Matrix task room before Quick Task or Project Work state exists.
Describe Room
Call roomflow describe_room when a Matrix room's purpose is unclear.
Classify from Matrix state:
- Source channel / requester room: external channel, or Matrix room whose name indicates DM or Team room.
- Task room: Matrix room whose name starts with
TASK：<projectId>, or whose topic/tags carry a Project/Task marker.
Do not infer room purpose from joined-room IDs alone.
Create Or Reuse Task Room
From a Source channel / requester room, call roomflow create_task_room before
creating project or task state.
Pass a stable projectId. The tool normalizes the Matrix room name to
TASK：<projectId> and reuses task rooms only by that project id.
Pass the current source metadata exactly as received, such as DingTalk
sourceRoomId and sender, so project state can keep the requester route.
Do not use source room or sender identity to decide task-room reuse. Different
projects from the same DingTalk group or same person still get different task
rooms.
Pass the complete Matrix user IDs for Workers who must receive or observe work in the task room. Use the returned Matrix room as the task room for the handoff, project state, task delegation, and Worker completion reports.
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.
- 6d ago First seen · 41 lines · 63 tokens per session scan A dac6fc720665
teamharness-roomflow is a skill published in the GitHub repository agentscope-ai/AgentTeams (5,564 stars, last pushed yesterday), licensed Apache-2.0. It adds 63 tokens to every session and 373 once invoked, about $0.0003 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
ship
Ship workflow: detect + merge base branch, run tests, review diff, bump VERSION, update CHANGELOG, commit, push, and create a PR. Use for an explicit /ship invocation or when the user requests the full ship, release, or deploy workflow. For an ordinary commit, push, or pull-request publishing request, use the built-in…
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…
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…
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…
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…
retro
Weekly engineering retrospective. Analyzes commit history, work patterns, and code quality metrics with persistent history and trend tracking. Team-aware: breaks down per-person contributions with praise and growth areas. Use when asked to "weekly retro", "what did we ship", or "engineering retrospective". Proactively…