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 aashari/ai-agent-skills --skill mail-accountsgit clone --depth 1 https://github.com/aashari/ai-agent-skillsWrote 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/aashari/ai-agent-skills/mail-accounts)<a href="https://agentmods.dev/skills/aashari/ai-agent-skills/mail-accounts"><img src="https://agentmods.dev/badge/skills/aashari/ai-agent-skills/mail-accounts/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.
<a href="https://agentmods.dev/skills/aashari/ai-agent-skills/mail-accounts"><img src="https://agentmods.dev/badge/skills/aashari/ai-agent-skills/mail-accounts.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00049 | $0.00918 |
| Opus 5 | $0.00024 | $0.00459 |
| Sonnet 5 | $0.00010 | $0.00184 |
| Haiku 4.5 | $0.00005 | $0.00092 |
Grade A, and why
mail-accounts scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 11d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 102 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Mail Accounts — Discover All Synced Accounts
List every account synced in Apple Mail with identity, type, and stats.
Steps
1. Get all account UUIDs
ls ~/Library/Mail/V10/ | grep -v MailData | grep -v "^$"
2. For each UUID, identify the email address and account type
Query the most frequent recipient address (most reliable identity signal):
DB="$HOME/Library/Mail/V10/MailData/Envelope Index"
for UUID in $(ls ~/Library/Mail/V10/ | grep -v MailData); do
# Account type from mailbox URL prefix
TYPE=$(sqlite3 "$DB" "SELECT url FROM mailboxes WHERE url LIKE '%${UUID}%' LIMIT 1;" 2>/dev/null | grep -oE '^[a-z]+')
# Sender of Sent mail = this account's address (reliable; avoids mailing list CC pollution)
EMAIL=$(sqlite3 "$DB" "
SELECT a.address
FROM messages m
JOIN mailboxes mb ON m.mailbox=mb.ROWID
JOIN addresses a ON m.sender=a.ROWID
WHERE mb.url LIKE '%${UUID}%'
AND (mb.url LIKE '%Sent%' OR mb.url LIKE '%sent%')
AND a.address LIKE '%@%'
GROUP BY a.address ORDER BY COUNT(*) DESC LIMIT 1;" 2>/dev/null)
# Fallback if no Sent mail: most frequent To: recipient in INBOX
if [ -z "$EMAIL" ]; then
EMAIL=$(sqlite3 "$DB" "
SELECT a.address
FROM messages m
JOIN mailboxes mb ON m.mailbox=mb.ROWID
JOIN recipients r ON r.message=m.ROWID
JOIN addresses a ON r.address=a.ROWID
WHERE mb.url LIKE '%${UUID}%/INBOX%' AND r.type = 0
GROUP BY a.address ORDER BY COUNT(*) DESC LIMIT 1;" 2>/dev/null)
fi
# Total message count
TOTAL=$(sqlite3 "$DB" "
SELECT COUNT(*) FROM messages m
JOIN mailboxes mb ON m.mailbox=mb.ROWID
WHERE mb.url LIKE '%${UUID}%' AND m.deleted=0;" 2>/dev/null)
# Unread count
UNREAD=$(sqlite3 "$DB" "
SELECT COUNT(*) FROM messages m
JOIN mailboxes mb ON m.mailbox=mb.ROWID
WHERE mb.url LIKE '%${UUID}%' AND m.deleted=0 AND m.read=0;" 2>/dev/null)
echo "${UUID}|${TYPE}|${EMAIL}|${TOTAL}|${UNREAD}"
done
3. List mailbox folders for each account
sqlite3 "$DB" "
SELECT DISTINCT url FROM mailboxes
WHERE url LIKE '%UUID_HERE%'
ORDER BY url;" 2>/dev/null
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.
- 11d ago First seen · 102 lines · 49 tokens per session scan A dd124811c28a
mail-accounts is a skill published in the GitHub repository aashari/ai-agent-skills (5 stars, last pushed 6mo ago), licensed MIT. It adds 49 tokens to every session and 918 once invoked, about $0.0002 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 skills, from other repositories
orbit-notion
Open Orbit briefing skill — selected by the Orbit pipeline when Notion is the user's only connected connector, or when the user explicitly scopes their daily digest to Notion. Pulls the past 24 hours of document edits, comments, mentions, and database row changes from the user's authenticated Notion connection and…
Cortex
Operate Cortex, the LifeOS memory system — the typed Knowledge Archive (People, Companies, Ideas, Research with typed related: links) plus recall of prior work sessions, ISAs, and conversations. Search, add, harvest, develop, ingest, distill, graph-navigate, recall. USE WHEN cortex, knowledge, knowledge base, search…
pinchtab-mcp
Use this skill when a task requires browser automation through PinchTab's MCP server connected to a remote browser instance. Covers navigation, element interaction, data extraction, form filling, multi-step flows, and session management via MCP tools.
feishu
Work with Feishu or Lark bots, docs, sheets, bitables, approval flows, and OpenAPI/MCP setup without hardcoding credentials.
peekaboo
Capture and automate macOS UI with the Peekaboo CLI.
mochi-remind
Handle due reminders — notify the user with natural language and mark them done.