QwenPaw is a personal AI assistant that runs on a local machine or in the cloud and connects to multiple chat applications. It provides memory, file workspaces, multiple agents, skills, plugins, and integrations with language-model providers and external tools. The catalogue entries are skills that extend its capabilities.
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/QwenPaw --skill multi_agent_collaboration-zhgit clone --depth 1 https://github.com/agentscope-ai/QwenPawWrote 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/qwenpaw/multi_agent_collaboration-zh)<a href="https://agentmods.dev/skills/agentscope-ai/qwenpaw/multi_agent_collaboration-zh"><img src="https://agentmods.dev/badge/skills/agentscope-ai/qwenpaw/multi_agent_collaboration-zh/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/qwenpaw/multi_agent_collaboration-zh"><img src="https://agentmods.dev/badge/skills/agentscope-ai/qwenpaw/multi_agent_collaboration-zh.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 | $0.00052 | $0.03342 |
| Opus 5 | $0.00026 | $0.01671 |
| Sonnet 5 | $0.00010 | $0.00668 |
| Haiku 4.5 | $0.00005 | $0.00334 |
Grade A, and why
multi_agent_collaboration 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 11d 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- multi_agent_collaboration — 100% identical, 0 lines differ
How it starts
The opening of the file, as written. The whole thing — 477 lines — stays where its author put it; the contents beside it link to each section on GitHub.
多智能体协作
什么时候用
当你需要其他 agent 的专业能力、上下文、workspace 内容或协作支持时，使用本 skill。
如果用户明确要求某个 agent 参与/协助/回答，也应使用本 skill。
应该使用
- 当前任务明显更适合某个专用 agent
- 需要另一个 agent 的 workspace / 文件 / 上下文
- 需要第二意见或专业复核
- 用户明确要求某个 agent 参与或调用其他 agent
不应使用
- 你自己可以直接完成，且用户没有明确要求调用其他 agent
- 只是普通问答，不需要专门 agent
- 信息不足，应先追问用户
- 刚收到 Agent B 的消息，不要再调用 Agent B，避免循环
决策规则
- 如果用户明确要求调用其他 agent，优先按要求执行
- 否则，能自己做，就不要调用
- 调用前先查 agent，不要猜 ID
- 需要上下文续聊时，必须传
--session-id - 不要回调消息来源 agent
最常用命令
1) 先查询可用 agents
qwenpaw agents list
2) 发起新对话（实时模式）
qwenpaw agents chat \
--from-agent <your_agent> \
--to-agent <target_agent> \
--text "[Agent <your_agent> requesting] ..."
3) 发起复杂任务（后台模式）
复杂任务包括：数据分析、报告生成、批量处理、外部API调用等。
qwenpaw agents chat --background \
--from-agent <your_agent> \
--to-agent <target_agent> \
--text "[Agent <your_agent> requesting] ..."
输出：
[TASK_ID: xxx-xxx-xxx]
[SESSION: ...]
4) 查询后台任务状态
qwenpaw agents chat --background --task-id <task_id>
重要：不要频繁查询！提交任务后：
- 不要硬等 - 继续处理其他任务或工作
- 等待合理时间后再查 - 根据任务复杂度选择：
- 简单分析：10-20 秒后查询
- 复杂分析：30-60 秒后查询
- 批量处理：1-3 分钟后查询
- 在等待期间 - 可以回复用户、处理其他请求、或执行其他任务
5) 继续已有对话
qwenpaw agents chat \
--from-agent <your_agent> \
--to-agent <target_agent> \
--session-id "<session_id>" \
--text "[Agent <your_agent> requesting] ..."
重点:
- 不传
--session-id= 新对话 - 传
--session-id= 续聊（保留上下文） - 复杂任务用
--background，提交后记录 task_id
任务模式选择
实时模式 vs 后台模式
| 任务类型 | 使用模式 | 命令 |
|---|---|---|
| 简单快速查询 | 实时模式 | qwenpaw agents chat |
| 复杂任务（数据分析、批量处理等） | 后台模式 | qwenpaw agents chat --background |
复杂任务示例：
- 分析大量数据或日志文件
- 生成详细报告
- 批量处理文件（10+ 个文件）
- 调用慢速外部 API
- 需要并行执行的独立任务
判断标准：如果不确定任务会花多长时间，或者任务很复杂，优先使用后台模式。
最小工作流
实时模式工作流
1. 判断是否需要其他 agent，或用户是否明确要求调用
2. qwenpaw agents list
3. qwenpaw agents chat 发起对话
4. 从输出中记录 [SESSION: ...]
5. 后续需要上下文时带上 --session-id
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.
- 11d ago First seen · 477 lines · 52 tokens per session scan A 56f8278044b5
multi_agent_collaboration is a skill published in the GitHub repository agentscope-ai/QwenPaw (34,741 stars, last pushed today), licensed Apache-2.0. It adds 52 tokens to every session and 3,342 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
officecli-word-form
Use this skill to create fillable Word forms (.docx) with real Content Controls (SDT) + legacy FormField checkboxes + MERGEFIELD mail-merge placeholders + document protection. Trigger on: 'fillable form', 'form fields', 'content controls', 'SDT', 'word form', 'fill in', 'only editable fields', 'protect document'…
new
Create a new project to start development quickly.
agent-coverage-check
Check agent configuration coverage across hierarchy levels and phases. Use to ensure complete agent system coverage.
meeting-summarizer
Summarize a completed meeting from its transcript. Produces a structured summary with key decisions, action items, and discussion highlights. Triggered automatically when a meeting ends.
yida-formula
A reference and set of rules for writing formulas in Yida form fields. It covers built-in functions, field references, calculated defaults, and custom submission checks.
yida-publish-page
A skill for compiling and publishing custom pages on OpenYida, a platform for building business applications. It works with the platform's page source and publishing process.