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 laborany/laborany --skill email-assistantgit clone --depth 1 https://github.com/laborany/laboranyWrote 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/laborany/laborany/email-assistant)<a href="https://agentmods.dev/skills/laborany/laborany/email-assistant"><img src="https://agentmods.dev/badge/skills/laborany/laborany/email-assistant.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 | $0.00138 | $0.04457 |
| Opus 5 | $0.00069 | $0.02228 |
| Sonnet 5 | $0.00028 | $0.00891 |
| Haiku 4.5 | $0.00014 | $0.00446 |
Grade A, and why
邮箱助手 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.
How it starts
The opening of the file, as written. The whole thing — 625 lines — stays where its author put it; the contents beside it link to each section on GitHub.
邮箱助手
智能邮箱管理助手，自动化处理邮件收发、阅读、分析和回复拟稿。
安全特性
- 加密存储: 凭据使用 AES-256-GCM 加密存储
- 用户隔离: 与 LaborAny 用户ID绑定，不同用户凭据完全隔离
- 自动过期: 凭据30天自动过期，需要重新验证
- 机器绑定: 密钥基于用户ID和机器指纹派生，防止凭据文件被挪用
工作流程
连接邮箱 → 获取未读 → AI分析总结 → 识别待办/会议 → 辅助拟稿 → [发送邮件]
发送邮件功能已集成凭据缓存，使用已保存的凭据自动发送。
快速开始
Step 1: 连接邮箱并获取未读邮件
方式一：自动模式（推荐，用于 AI 调用）
自动使用缓存的凭据，无需用户交互：
# 自动使用第一个缓存的凭据
python scripts/fetch_with_cache.py <用户ID> --auto
方式二：带缓存的智能模式
自动保存凭据，下次无需重复登录，与用户绑定安全加密：
# 首次使用 - 需要提供邮箱和密码
python scripts/fetch_with_cache.py <用户ID>
# 指定邮箱（首次或更换邮箱）
python scripts/fetch_with_cache.py <用户ID> [email protected]
注意:
<用户ID>应该是 LaborAny 的当前用户ID，用于隔离不同用户的凭据。--auto参数启用非交互模式，直接使用第一个缓存的凭据，无需用户确认。
方式二：命令行模式
# 获取未读邮件
python scripts/fetch_emails.py <邮箱地址> <密码/授权码> [数量]
# 示例
python scripts/fetch_emails.py [email protected] YOUR_AUTH_CODE
方式三：批处理模式
python scripts/imap_client_batch.py <邮箱地址> <密码/授权码> [数量] [--all]
# 示例
python scripts/imap_client_batch.py [email protected] YOUR_AUTH_CODE 50
方式四：交互式模式
python scripts/imap_client.py
邮件会自动保存到 emails.json。
Step 2: 分析邮件内容
python scripts/email_analyzer.py emails.json
查看摘要:
python scripts/email_analyzer.py --summary emails_analyzed.json
支持的邮箱服务
| 邮箱 | IMAP服务器 | SMTP服务器 | 特殊要求 |
|---|---|---|---|
| Gmail | imap.gmail.com:993 | smtp.gmail.com:587 | 需应用专用密码 |
| Outlook | outlook.office365.com:993 | smtp.office365.com:587 | - |
| QQ邮箱 | imap.qq.com:993 | smtp.qq.com:587 | 需开启SMTP服务 |
| 163邮箱 | imap.163.com:993 | smtp.163.com:465 | 需授权码 + IMAP ID |
| 126邮箱 | imap.126.com:993 | smtp.126.com:465 | 需授权码 + IMAP ID |
| Yahoo | imap.mail.yahoo.com:993 | smtp.mail.yahoo.com:587 | - |
重要提示
163/126邮箱特殊说明
网易邮箱要求客户端发送 IMAP ID 信息，否则会报 "Unsafe Login" 错误。
本技能已在所有脚本中添加了 IMAP ID 支持，但使用时仍需注意：
- 必须使用授权码，不是登录密码
- 开启IMAP服务：设置 → POP3/SMTP/IMAP
- 如果仍报错，尝试在网页端邮箱设置中重新生成授权码
Gmail 专用密码
- 访问 https://myaccount.google.com/apppasswords
- 生成应用专用密码
- 使用该密码而非Google账号密码
What ships with it
8 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.
- scripts/credential_cache.py 16 KB runs code
- scripts/email_analyzer.py 7.5 KB runs code
- scripts/email_drafter.py 4.6 KB runs code
- scripts/fetch_emails.py 14 KB runs code
- scripts/fetch_with_cache.py 7.3 KB runs code
- scripts/imap_client_batch.py 8.1 KB runs code
- scripts/imap_client.py 7.8 KB runs code
- scripts/send_email.py 12 KB runs code
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 · 625 lines · 138 tokens per session scan A f1b88bc5f9f5
邮箱助手 is a skill published in the GitHub repository laborany/laborany (81 stars, last pushed 3mo ago), licensed MIT. It adds 138 tokens to every session and 4,457 once invoked, about $0.0007 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
disk-cleaner
A Mac disk-cleaning assistant built around the Mole cleanup tool. It checks the environment, previews removable files, and can run cleanup using different safety levels with reports and protected paths.
work-relax-planner
A schedule planner that adds user-chosen sports or leisure activities to a class or work timetable. It asks for a lucky number, uses that number to choose how many activities to enter, and can optionally place activities during class time with a warning.
andreessen
Marc Andreessen-mode decision and productivity skill. A blunt, market-first operator that pressure-tests ideas, ventures, features, and career bets through Andreessen's actual frameworks — market dominates team and product; the only milestone that matters is product/market fit; bias to build over deliberate. Use when…
caveman
Ultra-compressed communication mode. Cuts token usage 75% by dropping filler, articles, and pleasantries while keeping full technical accuracy. Use when user says "caveman mode", "talk like caveman", "use caveman", "less tokens", "be brief", or invokes /caveman.
schedule
A skill for creating and managing scheduled tasks, including tasks that run automatically at regular times.
自动化建议
A guide for turning signs of repeated or time-sensitive work into an automation suggestion that the user can choose to set up.