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 sonichi/sutando --skill macos-toolsgit clone --depth 1 https://github.com/sonichi/sutandoWrote 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/sonichi/sutando/macos-tools)<a href="https://agentmods.dev/skills/sonichi/sutando/macos-tools"><img src="https://agentmods.dev/badge/skills/sonichi/sutando/macos-tools/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/sonichi/sutando/macos-tools"><img src="https://agentmods.dev/badge/skills/sonichi/sutando/macos-tools.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00052 | $0.01204 |
| Opus 5.5 | $0.00021 | $0.00482 |
| Sonnet 5.5 | $0.00010 | $0.00241 |
| Haiku 4.5 | $0.00005 | $0.00120 |
Grade A, and why
macos-tools scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 23d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 93 lines — stays where its author put it; the contents beside it link to each section on GitHub.
macOS Tools
Native macOS integrations via AppleScript. No API keys needed — works on any Mac.
Calendar, Reminders and Contacts need the owner's consent. Driving those apps raises a macOS
permission prompt on the owner's screen. The order: (1) the Superpower Station connector
(composio_find → composio_exec); (2) if it is not connected, the owner's own tools when they
are in the tool list (mcp__claude_ai_Google_Calendar__*); (3) otherwise ask the owner. Run the
scripts below with --owner-asked only when the owner asked for the local app in this
conversation — without it they refuse (exit 2). A macOS denial (exit 3) is final and stored in
<workspace>/state/<app>-automation-denied: say so, never retry or re-prompt. The native-pim-guard
hook denies raw osascript/open -a commands against these apps for the same reason.
The owner can allow the local apps for this host once, in their own terminal (never run it yourself — the hook denies it to you):
python3 "$SKILL_DIR/scripts/native_pim_consent.py" grant # writes state/native-pim-consent, clears stored denials
python3 "$SKILL_DIR/scripts/native_pim_consent.py" status # marker, env var, per-app denial
python3 "$SKILL_DIR/scripts/native_pim_consent.py" revoke
--owner-asked and SUTANDO_ALLOW_NATIVE_PIM=1 are strings you write: they stop you acting on your
own initiative, they do not prove who asked (see hooks/README.md, native-pim-guard). Where the
session says whose task is running (state/bindings/active-execution.json), the scripts refuse every
form of consent on a non-owner task (exit 2, "not the owner's"). The consent record itself —
state/native-pim-consent and the *-automation-denied markers — is the owner's: never write, copy,
delete or touch it, and never import native_pim_consent to call grant(); the hook denies all of
those, and status is how you read the state.
When to Use
- Screen: "What's on my screen?", "help me with this", "describe what I'm looking at"
- Calendar: "What's on my schedule?", "do I have meetings today?"
- Reminders: "Add a reminder", "what's on my todo list?", "mark X as done"
- Contacts: "What's Bob's email?", "find contact for..."
- Email: "Send an email to...", "draft a message to..."
- File search: "Find my resume", "where's that PDF?"
What ships with it
8 files 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.
- 23d ago Changed · +24 lines 8769a70984d6
- 1mo ago Changed · +3 lines 16a9133dd84b
- 1mo ago First seen · 66 lines · 52 tokens per session scan A b7868a8f9511
macos-tools is a skill published in the GitHub repository sonichi/sutando (397 stars, last pushed today), licensed MIT. It adds 52 tokens to every session and 1,204 once invoked, about $0.0002 per session on Opus 5.5. 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
gmail
Manage Gmail email — drafting, sending, organizing, filters, vacation replies, and inbox analysis.
schedule
Reminders, automations, and recurring page, dashboard, or status monitoring (cron, RRULE, or fire-at).
inbox-management
Ongoing Gmail inbox management via scheduled runs. Archives known noise, flags urgent items, drafts replies in-thread (never auto-sends), and catches stale follow-ups. Empty polls spend no model tokens. Starts in flag-only mode.
inbox-cleanup
Run a high-recall, multi-pass email inbox cleanup. Pattern-based subject queries catch 25x more archivable email than sender scans alone. Includes urgency triage, classification signals, and post-cleanup filter setup.
notifications
Send notifications through the unified notification router.
outlook
Manage Outlook email — drafting, sending, organizing, rules, vacation replies, and inbox analysis.