Mail

Mail is a skill for Claude Code, Codex from mupengi-bot/mupengism. It costs 14 tokens per session (587 once invoked), scanned A, original, MIT.

An instruction set for carrying out email tasks using different methods on macOS and across other systems. It covers Apple Mail’s local database and the Himalaya command-line tool for IMAP and SMTP email.

In plain words
What is it for?
Use it to list and search email, find senders, inspect attachments, move messages between folders, and work with Apple Mail or Himalaya.
Why use it?
It provides specific ways to find, filter, move, and inspect messages while avoiding conflicting methods. It also addresses details such as refreshing mail before reading the local database.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it to list and search email, find senders, inspect attachments, move messages between folders, and work with Apple Mail or Himalaya.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/mupengi-bot/mupengism/mail
Install

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.

Any agent
npx skills add mupengi-bot/mupengism --skill mail
Clone the repo
git clone --depth 1 https://github.com/mupengi-bot/mupengism

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for Mail

README.md
[![agentmods](https://agentmods.dev/badge/skills/mupengi-bot/mupengism/mail/github.svg)](https://agentmods.dev/skills/mupengi-bot/mupengism/mail)
Your own site
<a href="https://agentmods.dev/skills/mupengi-bot/mupengism/mail"><img src="https://agentmods.dev/badge/skills/mupengi-bot/mupengism/mail/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.

agentmods 80×15 button for Mail

Your own site · 80×15
<a href="https://agentmods.dev/skills/mupengi-bot/mupengism/mail"><img src="https://agentmods.dev/badge/skills/mupengi-bot/mupengism/mail.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 14 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 587 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00014 $0.00587
Opus 5 $0.00007 $0.00293
Sonnet 5 $0.00003 $0.00117
Haiku 4.5 $0.00001 $0.00059

Measured 9d ago against content hash 350e6da0de76, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

Mail 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 9d 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.

skills/mail/SKILL.md · 67 lines

How it starts

The opening of the file, as written. The whole thing — 67 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Platform Detection & Routing

macOS: Use Apple Mail SQLite queries (100x faster than AppleScript).

Cross-platform: Use himalaya CLI for full IMAP/SMTP operations.

Never mix approaches in same task. Commit to one to avoid state conflicts.

Apple Mail SQLite Gotchas

Query path: ~/Library/Mail/V*/MailData/Envelope\ Index

Key tables: messages (subject, sender, date_received), addresses, mailboxes.

Force sync first: osascript -e 'tell app "Mail" to check for new mail'. SQLite reads stale data otherwise.

Recent mail filter: WHERE date_received > strftime('%s','now','-7 days')

Join pattern: messages→addresses on message_id for sender lookup.

Attachments: Check messages.attachment_count > 0, files in ~/Library/Mail/V*/MAILBOX/Messages/.

himalaya CLI Patterns

Install: cargo install himalaya or brew install himalaya.

Always use: --output json flag for programmatic parsing.

List emails: himalaya envelope list -o json (NOT message list).

Folder operations: himalaya message move <id> <folder> - folder names are case-sensitive.

Cache refresh: Run himalaya folder list after server-side folder changes.

Send Protocol

Draft-review-send workflow: Compose → show user full content → send after explicit OK.

Reply threading: Include In-Reply-To and References headers or thread breaks.

himalaya send: himalaya message send reads RFC 2822 from stdin.

SMTP rejection: Some servers reject if From header doesn't match authenticated user.

Credential Management

macOS Keychain: security add-internet-password -s imap.gmail.com -a [email protected] -w 'app-password'

Gmail/Google Workspace: Requires App Password with 2FA enabled, NOT regular password.

OAuth tokens: himalaya supports XOAUTH2 via token_cmd in config.toml.

Thread Intelligence

Thread by In-Reply-To chain, not subject matching. "Re:" prefix is unreliable.

Polling intervals: 15-30 min max. Use himalaya envelope watch for real-time when available.

Read the full file on GitHub · 67 lines

Files

What ships with it

2 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.

Changes

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.

  1. 9d ago First seen · 67 lines · 14 tokens per session scan A 350e6da0de76

Subscribe to this mod's changes

Mail is a skill published in the GitHub repository mupengi-bot/mupengism (10 stars, last pushed 2mo ago), licensed MIT. It adds 14 tokens to every session and 587 once invoked, about $0.0001 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.