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-searchgit 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-search)<a href="https://agentmods.dev/skills/aashari/ai-agent-skills/mail-search"><img src="https://agentmods.dev/badge/skills/aashari/ai-agent-skills/mail-search/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-search"><img src="https://agentmods.dev/badge/skills/aashari/ai-agent-skills/mail-search.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 | $0.00075 | $0.00671 |
| Opus 5 | $0.00037 | $0.00336 |
| Sonnet 5 | $0.00015 | $0.00134 |
| Haiku 4.5 | $0.00007 | $0.00067 |
Grade A, and why
mail-search 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.
What it actually says
Mail Search — Full-Text Search Across All Accounts
Search query: $ARGUMENTS
Argument Parsing
Parse $ARGUMENTS for modifiers:
from:[email protected]orsender:→ filter by sendersubject:keyword→ filter subject onlyaccount:gmailoraccount:work→ restrict to account typelast N days/weeks→ time filter- Anything else → search both subject and sender
Query
DB="$HOME/Library/Mail/V10/MailData/Envelope Index"
TERM="<extracted search term>" # URL-encode % as %% in shell
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,
CASE WHEN m.size > 0 THEN m.size ELSE 0 END as size
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 m.deleted = 0
AND mb.url NOT LIKE '%Spam%'
AND mb.url NOT LIKE '%Trash%'
AND mb.url NOT LIKE '%Junk%'
AND (
s.subject LIKE '%TERM%'
OR a.address LIKE '%TERM%'
OR a.comment LIKE '%TERM%'
)
ORDER BY m.date_received DESC
LIMIT 50;" 2>/dev/null
For sender-only search:
WHERE a.address LIKE '%TERM%' OR a.comment LIKE '%TERM%'
For subject-only search:
WHERE s.subject LIKE '%TERM%'
For recipient search (TO/CC):
JOIN recipients r ON r.message = m.ROWID
JOIN addresses ra ON r.address = ra.ROWID
WHERE ra.address LIKE '%TERM%'
Reading Email Bodies
If user wants to read specific results, find the emlx and parse:
python3 ~/.claude/skills/_mail-shared/parser.py <ROWID>
Output Format
Show results as a table:
| Date | From | Subject | Account | Read |
|---|
If more than 20 results, summarize by sender/thread and ask if they want to narrow down. For each result, note the account it belongs to (extract UUID from mailbox URL to identify account). Offer to read any specific email if user asks.
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 · 85 lines · 75 tokens per session scan A 703b206446b2
mail-search is a skill published in the GitHub repository aashari/ai-agent-skills (5 stars, last pushed 6mo ago), licensed MIT. It adds 75 tokens to every session and 671 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.
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.