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 mailbox-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/mailbox-zh)<a href="https://agentmods.dev/skills/agentscope-ai/qwenpaw/mailbox-zh"><img src="https://agentmods.dev/badge/skills/agentscope-ai/qwenpaw/mailbox-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/mailbox-zh"><img src="https://agentmods.dev/badge/skills/agentscope-ai/qwenpaw/mailbox-zh.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, 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 Privilege Escalation · line 61 Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.Fix: Remove references to credential paths. Use environment variables or secrets managers. For docs, use placeholder paths (e.g., /path/to/config). Never load .env or token files in production code paths.
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 | $0.00079 | $0.02447 |
| Opus 5 | $0.00039 | $0.01223 |
| Sonnet 5 | $0.00016 | $0.00489 |
| Haiku 4.5 | $0.00008 | $0.00245 |
Grade A, and why
mailbox 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 yesterday.
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 — 167 lines — stays where its author put it; the contents beside it link to each section on GitHub.
邮箱操作 (qwenpawmail-mcp)
使用 qwenpawmail-mcp 绑定或注册邮箱并执行邮件操作。
支持的邮箱服务商
QwenPaw 托管邮箱流程当前支持以下 9 个邮箱域名:
| 服务商 | 域名 | 登录凭据 |
|---|---|---|
| 网易 | 163.com、126.com、yeah.net |
16 位授权码 |
| 腾讯 | qq.com、foxmail.com |
16 位授权码 |
| 新浪 | sina.com、sina.cn |
16 位授权码 |
| 阿里 | aliyun.com |
邮箱登录密码;仅支持已有账号 |
gmail.com |
开启两步验证后生成的 16 位应用专用密码 |
当前托管流程不支持企业邮箱、自定义域名和 Microsoft 邮箱。
create_mailbox 仅为 163.com、126.com、yeah.net、qq.com 和 foxmail.com 提供内置注册引导。其他受支持域名需走服务商官方注册流程。aliyun.com 已关闭个人邮箱新注册,只能绑定已有账号。
调用规则
任何邮件操作都必须从此技能进入。不要自行编造其他邮件流程,也不要绕过 qwenpawmail-mcp 直接执行原始 IMAP/SMTP 命令。
凭据与配置模型
agent.json 只保存公开邮箱配置。mail 的预期结构为:
{
"mail": {
"is_new_account": false,
"credential": {
"name": "myaccount",
"domain": "163.com",
"provider": ""
},
"push": {
"mode": "off",
"rules": [],
"poll_interval_seconds": 120,
"access_control_enabled": false
}
}
}
敏感字段 auth_code、password 和 phone_number 会被刻意排除在 agent.json 之外,Agent API 响应也不会返回它们。服务商凭据统一通过 auth_code 表示,配置后会被加密保存;注册密码和手机号只在对应邮箱的注册网页内填写,当前 QwenPaw 流程不会保存。公开配置中看不到 auth_code 并不表示用户没有配置凭据。
QwenPaw 仅在运行时通过托管 DriverCard 解析加密的服务商凭据。绝不要读取、解密、打印、复制或修改 credentials.yaml,也不要在文件或日志中搜索 secret。请严格使用下述流程。
工作流程:绑定或注册邮箱账号
第 1 步 — 读取公开邮箱状态
从 agent.json 读取 mail.is_new_account、mail.credential.name 和 mail.credential.domain。当前支持的个人邮箱域名对应的 provider 应为空字符串。
如果不存在 mail,请用户先在 QwenPaw 的智能体设置界面配置“邮箱管理”。
第 2a 步 — is_new_account 为 false:管理已有邮箱
- 直接调用
check_auth。托管 DriverCard 已经通过运行时凭据引用获取加密存储中的邮箱凭据;不要从agent.json查找凭据,也不要因为看不到 secret 字段就调用set_credentials。 check_auth成功后,执行用户要求的邮件操作。- 如果凭据缺失或失效,请用户在 QwenPaw 中编辑当前智能体,选择“管理你的个人邮箱”,重新填写邮箱凭据并保存。智能体重载后再次调用
check_auth。 - 如果用户在当前对话中明确提供邮箱地址和凭据,可以调用
set_credentials作为仅限当前会话的临时覆盖,随后调用check_auth。它不会更新 QwenPaw 的加密配置,MCP 进程重启后即失效。
临时调用 set_credentials 时,传入完整邮箱地址,并把服务商所需凭据放入名为 auth_code 的参数。对于 aliyun.com,该参数实际填写登录密码;其他受支持域名填写 16 位授权码或应用专用密码。
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.
- yesterday Changed d2931eb02f50
- 12d ago First seen · 167 lines · 79 tokens per session scan A f7b7f8700633
mailbox is a skill published in the GitHub repository agentscope-ai/QwenPaw (34,741 stars, last pushed yesterday), licensed Apache-2.0. It adds 79 tokens to every session and 2,447 once invoked, about $0.0004 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
cron-task-creator
Create, manage, and run scheduled automated tasks (cron jobs) in Clacky. Use this skill whenever the user wants to create a new automated task or cron job, set up recurring automation, schedule something to run daily/weekly/hourly, view all scheduled tasks, edit an existing task prompt or cron schedule, enable or…
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-create-process
A tool for creating a new Yida approval form and configuring its workflow. An approval workflow routes submitted form data through defined review steps before it is completed.
yida-logout
A logout and account-management procedure for YiDa, a platform for building and running business applications. It distinguishes disconnecting the current project from deleting shared login profiles.
post-dev-recap
Post-development recap wrapper. Use when: AI/Codex just finished implementing a feature and the user wants a guided walkthrough with scope detection + doc generation + follow-up Q&A. Not for: generating only a doc (use /recap-doc), Q&A over an existing recap (use /recap-ask), technical share-out (use /tech-brief)…
obsidian-cli
Obsidian vault integration via official CLI. Use when: capturing dev artifacts to Obsidian vault, searching vault for context, appending to daily note, managing tasks in vault. Not for: general note-taking without Obsidian (use regular files), browsing Obsidian docs (use agent-browser). Output: vault search results…