mail-from

mail-from is a skill for Claude Code from aashari/ai-agent-skills. It costs 76 tokens per session (794 once invoked), scanned A, original, MIT.

A tool for finding every email sent by a particular person, email address, or internet domain. It also summarizes the communication history with that sender.

In plain words
What is it for?
Use it to review a sender’s messages, understand contact frequency, and see recent communication with a person or organization.
Why use it?
It avoids searching through individual messages when you need the broader relationship or full history. Matching can use a name, address, or company domain.

Skill for Claude Code

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

Good fit Use it to review a sender’s messages, understand contact frequency, and see recent communication with a person or organization.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/aashari/ai-agent-skills/mail-from
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-from
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-from

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/aashari/ai-agent-skills/mail-from"><img src="https://agentmods.dev/badge/skills/aashari/ai-agent-skills/mail-from.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 76 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 794 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 $0.00076 $0.00794
Opus 5 $0.00038 $0.00397
Sonnet 5 $0.00015 $0.00159
Haiku 4.5 $0.00008 $0.00079

Measured 10d ago against content hash d1d422eaa0fc, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

mail-from 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 10d 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-from/SKILL.md · 89 lines

How it starts

The opening of the file, as written. The whole thing — 89 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Mail From — All Emails From a Sender

Sender query: $ARGUMENTS

Steps

1. Find matching senders

DB="$HOME/Library/Mail/V10/MailData/Envelope Index"
QUERY="$ARGUMENTS"  # treat as search term against address + comment fields

sqlite3 "$DB" "
SELECT DISTINCT a.address, a.comment, COUNT(*) as cnt
FROM messages m
JOIN addresses a ON m.sender = a.ROWID
JOIN mailboxes mb ON m.mailbox = mb.ROWID
WHERE (a.address LIKE '%${QUERY}%' OR a.comment LIKE '%${QUERY}%')
  AND m.deleted = 0
GROUP BY a.address
ORDER BY cnt DESC
LIMIT 10;" 2>/dev/null

If multiple matches, show options and ask which one (or proceed with all if they're clearly the same person/org).

2. Get all emails from the matched address(es)

sqlite3 "$DB" "
SELECT datetime(m.date_received,'unixepoch','localtime') as dt,
       s.subject, mb.url as mailbox, m.ROWID, m.read, m.flagged
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 a.address LIKE '%SENDER%'
  AND m.deleted = 0
  AND mb.url NOT LIKE '%Spam%'
  AND mb.url NOT LIKE '%Trash%'
ORDER BY m.date_received DESC
LIMIT 100;" 2>/dev/null

3. Compute relationship stats

sqlite3 "$DB" "
SELECT
  COUNT(*) as total,
  SUM(CASE WHEN m.read = 0 THEN 1 ELSE 0 END) as unread,
  SUM(CASE WHEN m.flagged = 1 THEN 1 ELSE 0 END) as flagged,
  MIN(datetime(m.date_received,'unixepoch','localtime')) as first_email,
  MAX(datetime(m.date_received,'unixepoch','localtime')) as latest_email,
  strftime('%Y-%m', datetime(m.date_received,'unixepoch','localtime')) as busiest_month
FROM messages m
JOIN addresses a ON m.sender = a.ROWID
JOIN mailboxes mb ON m.mailbox = mb.ROWID
WHERE a.address LIKE '%SENDER%' AND m.deleted = 0
GROUP BY busiest_month
ORDER BY COUNT(*) DESC LIMIT 1;" 2>/dev/null

4. Read recent emails if user wants details

python3 ~/.claude/skills/_mail-shared/parser.py <ROWID1> <ROWID2> ...

Output Format

Lead with relationship summary:

  • X emails from [name/address], spanning [date range]
  • First contact: [date] — Latest: [date]
  • Unread: X | Flagged: X

Read the full file on GitHub · 89 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. 10d ago First seen · 89 lines · 76 tokens per session scan A d1d422eaa0fc

Subscribe to this mod's changes

mail-from is a skill published in the GitHub repository aashari/ai-agent-skills (5 stars, last pushed 6mo ago), licensed MIT. It adds 76 tokens to every session and 794 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 2026-08-31.