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 instructions/theia-pro/email-mentor/agents-mdgit clone --depth 1 https://github.com/Theia-pro/email-mentorWrote 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/instructions/theia-pro/email-mentor/agents-md)<a href="https://agentmods.dev/instructions/theia-pro/email-mentor/agents-md"><img src="https://agentmods.dev/badge/instructions/theia-pro/email-mentor/agents-md.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 | $0.01693 | $0.01693 |
| Opus 5 | $0.00847 | $0.00847 |
| Sonnet 5 | $0.00339 | $0.00339 |
| Haiku 4.5 | $0.00169 | $0.00169 |
Grade A, and why
email-mentor AGENTS.md 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.
How it starts
The opening of the file, as written. The whole thing — 120 lines — stays where its author put it; the contents beside it link to each section on GitHub.
邮件管家（Email Mentor）· 通用版
一个与具体 AI 工具无关的邮件整理工作流：把英文邮件翻译成中文、分类、标注发件人、提取处理截止时间（DDL），并生成整理清单、日历文件和可视化报告。只读整理，绝不回复、不删除、不发送任何邮件。
本文件是什么
AGENTS.md 是给所有主流 AI 编程工具读取的通用指令（Codex、Claude Code、Cursor、Gemini CLI、OpenCode 等均支持）。当你（agent）在本项目中工作时，请按本文件的流程执行。
目录约定
- 邮件数据：优先自动定位 Thunderbird 的本地同步数据（
scripts/find_thunderbird.py）；备选目录~/Documents/EmailMentor/inbox/存放用户手动放入的.eml/.txt/.md - 输出目录：
~/Documents/EmailMentor/output/整理清单_YYYY-MM-DD.md：每次整理的中文清单deadlines.ics：DDL 日历文件（可导入飞书/Outlook/Google 日历）weekly_report.md/monthly_report.md：定期汇总报告邮件报告.html：可视化报告（浏览器直接打开）processed/processed.jsonl：历史处理记录（累积所有已处理邮件的分类、翻译、DDL）
工作流程
第 1 步：定位并解析邮件
先自动定位 Thunderbird 邮件数据：
python scripts/find_thunderbird.py --json
- 输出
"found": true时，取第一个mail_dirs路径作为解析输入 - 输出
"found": false时，提示用户：a) 先启动一次 Thunderbird 完成邮箱登录；b) 或把.eml/.txt邮件放入~/Documents/EmailMentor/inbox/
然后运行解析脚本，把邮件转成 JSON：
python scripts/parse_mailbox.py --input "<Thunderbird Mail 目录或 inbox 路径>" --output "<输出>/emails.json" [--since YYYY-MM-DD]
--since传入上次处理日期，只处理新邮件- 若用户指定了邮件路径，优先使用用户指定的路径
第 2 步：逐封整理（LLM 核心工作）
读取 emails.json，对每一封邮件执行：
- 翻译：把正文翻译成通顺的中文摘要（1-3 句），保留关键信息（时间、地点、数字、金额、链接、截止日期）
- 分类：按下面的分类体系归入唯一类别
- 发件人：标注发件人身份（如"课程教授""学校财务处""公司 HR"），帮助用户判断重要性
- 关键词：提取 3-5 个关键词
- 重要性：高 / 中 / 低（结合 DDL 紧迫度与发件人身份判断）
- DDL：若邮件明确包含截止时间/会议时间/回复期限，提取为
ddl（title、start、end，格式YYYY-MM-DD HH:MM）；只有日期没时间就写YYYY-MM-DD；没有则省略ddl字段
整理结果写入 processed/processed.jsonl（新邮件在文件末尾追加一行，不重复记录已处理邮件）。
第 3 步：生成整理清单
输出 整理清单_YYYY-MM-DD.md，包含每封邮件的：日期、发件人（含身份）、主题、翻译摘要、分类、重要性、关键词、DDL，按 DDL 临近程度排序。
第 4 步：生成日历文件
从有 DDL 的邮件生成 .ics 文件：
python scripts/make_calendar.py --input "<输出>/emails_ddl.json" --output "<输出>/deadlines.ics"
emails_ddl.json只包含本次整理中有 DDL 的邮件（脚本会自动提取其中的ddl字段，也可直接传入整个 processed.jsonl）- 生成后提示用户导入飞书日历（飞书 → 日历 → 设置 → 导入日历）
第 5 步：生成定期汇总（用户要求时）
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 · 120 lines · 1,693 tokens per session scan A 3103cf8e55c5
email-mentor AGENTS.md is an instructions file published in the GitHub repository Theia-pro/email-mentor (4 stars, last pushed 1mo ago), licensed MIT. It adds 1,693 tokens to every session, about $0.0085 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 2026-08-31.
Other instructions, from other repositories
KKTerm CLAUDE.md
Claude Code instructions for ryantsai/KKTerm: Constitution, Repository workflow, domain language, source-area boundaries, i18n rules, and engineering defaults live in AGENTS.md. Product terminology lives in CONTEXT.md. Read both before changing behavior or terminology.
spellbook AGENTS.md
AGENTS.md instructions for majiayu000/spellbook, covering spellbook agent contract, routing, scope rules, threads long-run guardrails and validation.
codemark GEMINI.md
Gemini CLI instructions for DanielCardonaRojas/codemark, covering development workflow and debugging with the tui logging system.
minimalist copilot-instructions.md
Instructions for DivyeshJayswal/minimalist, covering minimalist (coding tasks), persistence, fast path, bias and output.
totem AGENTS.md
AGENTS.md instructions for mmnto-ai/totem, covering totem: agent instructions, what totem is, session start protocol (mandatory), essentials and totem workflow.
hovmester frontend.instructions.md
Nav-spesifikke frontend-standarder — TypeScript, Aksel, auth, lokalisering.