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-coregit 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-core)<a href="https://agentmods.dev/skills/aashari/ai-agent-skills/mail-core"><img src="https://agentmods.dev/badge/skills/aashari/ai-agent-skills/mail-core/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-core"><img src="https://agentmods.dev/badge/skills/aashari/ai-agent-skills/mail-core.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 | $0.00042 | $0.02022 |
| Opus 5 | $0.00021 | $0.01011 |
| Sonnet 5 | $0.00008 | $0.00404 |
| Haiku 4.5 | $0.00004 | $0.00202 |
Grade A, and why
mail-core 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.
How it starts
The opening of the file, as written. The whole thing — 171 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Apple Mail Local Data — Technical Reference
Storage Root
~/Library/Mail/V10/
├── MailData/Envelope Index ← SQLite, central index of ALL mail across all accounts
└── <UUID>/ ← one directory per synced account
└── <Mailbox>.mbox/.../Data/[0/5/1/]Messages/<ROWID>.emlx
Critical: emlx File Location
The Data/ subfolder depth is unpredictable (Data/Messages/, Data/1/Messages/, Data/0/4/1/Messages/, Data/0/5/1/Messages/). Always locate by ROWID using find:
find ~/Library/Mail/V10/ -name "<ROWID>.emlx" 2>/dev/null | head -1
Two emlx variants exist:
<ROWID>.emlx— full message downloaded (headers + complete body)<ROWID>.partial.emlx— IMAP lazy-load: headers + truncated body (Apple Mail downloaded the start but not everything). Body is usually readable; just may cut off near the end.
The shared parser (~/.claude/skills/_mail-shared/parser.py) tries full emlx first, then falls back to partial automatically. Do not treat partial files as "not cached" — read them and extract what body is available.
SQLite Database
DB="$HOME/Library/Mail/V10/MailData/Envelope Index"
sqlite3 "$DB" "..."
Key Tables
| Table | Key Columns |
|---|---|
| messages | ROWID, date_received (Unix epoch), date_sent (Unix epoch), sender→addresses, subject→subjects, mailbox→mailboxes, read, flagged, deleted, size, conversation_id, is_urgent, automated_conversation, unsubscribe_type, list_id_hash, summary→summaries |
| mailboxes | ROWID, url (format: imap://UUID/INBOX, ews://UUID/Inbox), total_count (reliable), unread_count (EWS only, IMAP always 0) |
| addresses | ROWID, address (email string), comment (display name) |
| subjects | ROWID, subject (text) |
| recipients | message, address, type (0=To, 1=CC) |
| attachments | message, name (filename) |
| summaries | ROWID, summary (full body text — Apple-extracted, sparse: ~5% of recent messages) |
| conversations | thread grouping via conversation_id on messages |
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.
- 10d ago First seen · 171 lines · 42 tokens per session scan A 8c17ef459149
mail-core is a skill published in the GitHub repository aashari/ai-agent-skills (5 stars, last pushed 6mo ago), licensed MIT. It adds 42 tokens to every session and 2,022 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
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…
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…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…