mail-digest

mail-digest is a skill for Claude Code from aashari/ai-agent-skills. It costs 103 tokens per session (1,446 once invoked), scanned A, original, MIT.

A time-based summary of email received during a chosen period, such as today, yesterday, or the last few days. It groups messages by urgency and highlights unread, financial, and security-related mail while filtering common noise.

In plain words
What is it for?
Use it for daily inbox summaries, catch-up reports, unread-mail reviews, and checks for important financial or security messages.
Why use it?
It gives you a quick way to catch up without reviewing the inbox message by message. Flexible time ranges make it useful after being away or checking recent activity.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: reads .claude/ paths; built for openclaw.

Good fit Use it for daily inbox summaries, catch-up reports, unread-mail reviews, and checks for important financial or security messages.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/aashari/ai-agent-skills/mail-digest
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 aashari/ai-agent-skills --skill mail-digest
Clone the repo
git clone --depth 1 https://github.com/aashari/ai-agent-skills

Made for: Claude Code.

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-digest

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/aashari/ai-agent-skills/mail-digest"><img src="https://agentmods.dev/badge/skills/aashari/ai-agent-skills/mail-digest.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 103 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,446 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 $0.00103 $0.01446
Opus 5 $0.00051 $0.00723
Sonnet 5 $0.00021 $0.00289
Haiku 4.5 $0.00010 $0.00145

Measured 11d ago against content hash 399288fc658b, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

mail-digest 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.

skills/apple-mail/mail-digest/SKILL.md · 144 lines

How it starts

The opening of the file, as written. The whole thing — 144 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Mail Digest — Email Summary for Any Time Period

Period: $ARGUMENTS (default: today)

Step 1: Parse the time expression into a Unix timestamp range

Interpret $ARGUMENTS naturally. Map to START and END unix timestamps:

Expression START END
"today" / (empty) midnight today local now
"yesterday" midnight yesterday midnight today
"last 2 hours" now − 7200s now
"last N hours" now − N×3600s now
"last N days" now − N×86400s now
"this week" last Monday midnight now
"last week" Monday of prev week last Sunday midnight
"since Monday" most recent Monday midnight now
"YYYY-MM-DD" that date midnight that date 23:59:59
"catch me up" / "while I was away" infer from context or ask — default last 5 days
DB="$HOME/Library/Mail/V10/MailData/Envelope Index"

# Use SQLite date expressions directly — never compute Unix epochs manually (wrong year risk).
# "today"       → >= date('now','localtime')
# "yesterday"   → >= date('now','-1 day','localtime') AND < date('now','localtime')
# "last 48h"    → >= datetime('now','-48 hours')
# "last 7 days" → >= date('now','-7 days','localtime')
# Apply the range in the WHERE clause below using datetime() comparisons.

Step 2: Pull all messages in the window

sqlite3 "$DB" "
SELECT datetime(m.date_received,'unixepoch','localtime') as dt,
       s.subject, a.address as sender, a.comment as name,
       mb.url as mailbox, m.ROWID,
       m.read, m.flagged, m.is_urgent, m.size,
       m.automated_conversation, m.unsubscribe_type
FROM messages m
JOIN subjects  s  ON m.subject = s.ROWID
JOIN addresses a  ON m.sender  = a.ROWID
JOIN mailboxes mb ON m.mailbox = mb.ROWID
WHERE datetime(m.date_received,'unixepoch','localtime') >= date('now','localtime')
  -- adjust the expression above based on $ARGUMENTS
  AND m.deleted = 0
  AND mb.url NOT LIKE '%Spam%'
  AND mb.url NOT LIKE '%Trash%'
  AND mb.url NOT LIKE '%Junk%'
  AND mb.url NOT LIKE '%Draft%'
  AND mb.url NOT LIKE '%Sent%'
ORDER BY m.is_urgent DESC, m.date_received DESC;" 2>/dev/null

Read the full file on GitHub · 144 lines

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. 11d ago First seen · 144 lines · 103 tokens per session scan A 399288fc658b

Subscribe to this mod's changes

mail-digest is a skill published in the GitHub repository aashari/ai-agent-skills (5 stars, last pushed 6mo ago), licensed MIT. It adds 103 tokens to every session and 1,446 once invoked, about $0.0005 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.