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-top-sendersgit 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-top-senders)<a href="https://agentmods.dev/skills/aashari/ai-agent-skills/mail-top-senders"><img src="https://agentmods.dev/badge/skills/aashari/ai-agent-skills/mail-top-senders/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-top-senders"><img src="https://agentmods.dev/badge/skills/aashari/ai-agent-skills/mail-top-senders.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 | $0.00072 | $0.00973 |
| Opus 5 | $0.00036 | $0.00487 |
| Sonnet 5 | $0.00014 | $0.00195 |
| Haiku 4.5 | $0.00007 | $0.00097 |
Grade A, and why
mail-top-senders 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 12d 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 — 107 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Mail Top Senders — Communication Frequency Analysis
Analysis period: $ARGUMENTS (default: last 90 days)
Step 1: All senders ranked by volume
DB="$HOME/Library/Mail/V10/MailData/Envelope Index"
SINCE=$(($(date +%s) - 7776000)) # 90 days
sqlite3 "$DB" "
SELECT a.address, a.comment as name,
COUNT(*) as total,
SUM(CASE WHEN m.read=0 THEN 1 ELSE 0 END) as unread,
MIN(datetime(m.date_received,'unixepoch','localtime')) as first,
MAX(datetime(m.date_received,'unixepoch','localtime')) as latest
FROM messages m
JOIN addresses a ON m.sender = a.ROWID
JOIN mailboxes mb ON m.mailbox = mb.ROWID
WHERE m.date_received >= ${SINCE}
AND m.deleted = 0
AND mb.url NOT LIKE '%Spam%' AND mb.url NOT LIKE '%Trash%'
AND mb.url NOT LIKE '%Sent%'
GROUP BY a.address
ORDER BY total DESC
LIMIT 50;" 2>/dev/null
Step 2: Separate humans from automated senders
Use automated_conversation and unsubscribe_type columns (more reliable than address-pattern matching):
automated_conversation = 0+unsubscribe_type = 0→ real humansautomated_conversation = 1→ transactional (Jira, Slack, alerts)automated_conversation = 2ORunsubscribe_type > 0→ bulk/newsletters (noise)
# Human senders only (automated_conversation = 0, no unsubscribe header)
sqlite3 "$DB" "
SELECT a.address, a.comment as name, COUNT(*) as cnt
FROM messages m
JOIN addresses a ON m.sender = a.ROWID
JOIN mailboxes mb ON m.mailbox = mb.ROWID
WHERE m.date_received >= ${SINCE}
AND m.deleted = 0
AND mb.url NOT LIKE '%Spam%' AND mb.url NOT LIKE '%Sent%'
AND m.automated_conversation = 0
AND m.unsubscribe_type = 0
GROUP BY a.address ORDER BY cnt DESC LIMIT 20;" 2>/dev/null
Step 3: Domain-level analysis
sqlite3 "$DB" "
SELECT substr(a.address, instr(a.address,'@')+1) as domain,
COUNT(*) as cnt
FROM messages m
JOIN addresses a ON m.sender = a.ROWID
JOIN mailboxes mb ON m.mailbox = mb.ROWID
WHERE m.date_received >= ${SINCE}
AND m.deleted = 0
AND mb.url NOT LIKE '%Spam%'
GROUP BY domain ORDER BY cnt DESC LIMIT 20;" 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.
- 12d ago First seen · 107 lines · 72 tokens per session scan A 0a450d3283e7
mail-top-senders is a skill published in the GitHub repository aashari/ai-agent-skills (5 stars, last pushed 6mo ago), licensed MIT. It adds 72 tokens to every session and 973 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…