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 agentmods add skills/mitsuhiko/agent-stuff/apple-mailnpx skills add mitsuhiko/agent-stuff --skill apple-mailgit clone --depth 1 https://github.com/mitsuhiko/agent-stuffWrote 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/mitsuhiko/agent-stuff/apple-mail)<a href="https://agentmods.dev/skills/mitsuhiko/agent-stuff/apple-mail"><img src="https://agentmods.dev/badge/skills/mitsuhiko/agent-stuff/apple-mail.svg" alt="Measured on agentmods" 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 | $0.00045 | $0.00703 |
| Opus 5 | $0.00023 | $0.00351 |
| Sonnet 5 | $0.00009 | $0.00141 |
| Haiku 4.5 | $0.00005 | $0.00070 |
Grade A, and why
apple-mail 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 4d 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 — 73 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Apple Mail Skill
Search, read, and extract attachments from Apple Mail's local storage on macOS.
Tool
apple-mail.sh — a bash script that queries the Apple Mail SQLite envelope
index and reads .emlx files from disk. Read-only — it never modifies
mail data.
Quick Reference
TOOL=~/Development/agent-stuff/skills/apple-mail/apple-mail.sh
# Search emails
$TOOL search --from "peter@" --subject "dinner" --limit 5
$TOOL search --after 2026-02-01 --has-attachment
$TOOL search --body "invoice" --mailbox "INBOX" --unread
$TOOL search --to "armin@" --before 2025-12-31
# Show message metadata, recipients, attachments, and summary
$TOOL info 783660
# Read the raw RFC822 email (headers + body)
$TOOL read 783660
# Extract attachments to a temp directory (prints the path)
$TOOL attachment 783660 # all attachments
$TOOL attachment 783660 "Rechnung.pdf" # specific file
# List all mailboxes with counts
$TOOL mailboxes
Search Options
| Flag | Description |
|---|---|
--from <addr> |
Sender address substring |
--to <addr> |
Recipient address substring |
--subject <text> |
Subject substring |
--body <text> |
Body/summary text substring |
--mailbox <name> |
Mailbox URL substring (e.g. INBOX, Sent, Trash) |
--after <YYYY-MM-DD> |
Received after date |
--before <YYYY-MM-DD> |
Received before date |
--unread |
Only unread messages |
--flagged |
Only flagged messages |
--has-attachment |
Only messages with attachments |
--limit <n> |
Max results (default: 20) |
Output Format
searchreturns pipe-delimited table with header row:id|sender|sender_name|subject|received|status|flagged|mailbox|attachmentsinforeturns structured metadata sectionsreadoutputs raw RFC822 email to stdoutattachmentprints the temp directory path to stdout, file listing to stderr
Notes
- Message IDs are Apple Mail internal ROWIDs (integers), shown in the
idcolumn .partial.emlxfiles contain headers only (body not downloaded);readwarns about this- Attachments are copied to a temp directory under
/tmp/; clean up when done - The
bodysearch queries thesummariestable (Apple Mail's plaintext preview), not the full email body - Mailbox URLs are percent-encoded (e.g.,
%5BGmail%5D=[Gmail],%20= space) - Deleted messages are excluded from search by default
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 4d ago First seen · 73 lines · 45 tokens per session scan A 29b6e85500df
apple-mail is a skill published in the GitHub repository mitsuhiko/agent-stuff (3,044 stars, last pushed 3d ago), licensed Apache-2.0. It adds 45 tokens to every session and 703 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 2026-08-30.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
auto-perf-optimize
Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.
chat-perf
Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.
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…