apple-tools

apple-tools is a skill for Claude Code, Codex from BlackBeltTechnology/pi-agent-dashboard. It costs 92 tokens per session (725 once invoked), scanned A, original, MIT.

A macOS connection to Apple personal data through iMCP, including Calendar, Contacts, Reminders, Messages, Location, Maps, and Weather. Messages means iMessage or SMS, not email.

In plain words
What is it for?
Finding calendar events, contacts, reminders, messages, location, map information, or weather from a pi session on macOS.
Why use it?
It gives an agent a defined way to access supported Apple data while respecting macOS permissions, and avoids treating Apple Mail as supported.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Finding calendar events, contacts, reminders, messages, location, map information, or weather from a pi session on macOS.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/blackbelttechnology/pi-agent-dashboard/apple-tools
Install

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.

Any agent
npx skills add BlackBeltTechnology/pi-agent-dashboard --skill apple-tools
Clone the repo
git clone --depth 1 https://github.com/BlackBeltTechnology/pi-agent-dashboard

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for apple-tools

README.md
[![agentmods](https://agentmods.dev/badge/skills/blackbelttechnology/pi-agent-dashboard/apple-tools/github.svg)](https://agentmods.dev/skills/blackbelttechnology/pi-agent-dashboard/apple-tools)
Your own site
<a href="https://agentmods.dev/skills/blackbelttechnology/pi-agent-dashboard/apple-tools"><img src="https://agentmods.dev/badge/skills/blackbelttechnology/pi-agent-dashboard/apple-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.

agentmods 80×15 button for apple-tools

Your own site · 80×15
<a href="https://agentmods.dev/skills/blackbelttechnology/pi-agent-dashboard/apple-tools"><img src="https://agentmods.dev/badge/skills/blackbelttechnology/pi-agent-dashboard/apple-tools.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 92 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 725 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00092 $0.00725
Opus 5 $0.00046 $0.00362
Sonnet 5 $0.00018 $0.00145
Haiku 4.5 $0.00009 $0.00072

Measured 10d ago against content hash 2a8f91920f3e, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

apple-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 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.

packages/apple-tools/.pi/skills/apple-tools/SKILL.md · 69 lines

How it starts

The opening of the file, as written. The whole thing — 69 lines — stays where its author put it; the contents beside it link to each section on GitHub.

apple-tools (iMCP)

Access Apple personal-information-management data on macOS through iMCP, a menu-bar app that brokers the OS permission grants, reached over MCP by pi-mcp-adapter.

Reachable services (seven)

Calendar · Contacts · Location · Maps · Messages · Reminders · Weather

  • Messages here means iMessage / SMS — it is NOT email.
  • There is no Mail service. iMCP exposes no Apple Mail access.

Mail is out of scope — redirect

If the user asks to read, search, or summarize Apple Mail / email:

  • iMCP exposes no Mail service; do not attempt an iMCP/adapter tool call for Mail.
  • Use the apple-mail-fast-export skill instead — it exports .eml files directly from the on-disk Apple Mail store.

"Messages" satisfying an email request is a category error: Messages is iMessage/SMS only.

Access pattern — search then invoke via the adapter

The agent reaches iMCP tools through pi-mcp-adapter, not by spawning the server. Do not run imcp-server directly. Use the adapter's MCP tool surface (search the available tools, then invoke).

Provisioning check (run at load)

This skill runs the installer's --check traversal on load (one sw_vers plus a few stat calls; short-circuits instantly on non-macOS). If iMCP is not provisioned it reports the gap and names the fix:

pi-apple-tools-install

Terminal states mirror the CLI and the dashboard panel: UNSUPPORTED_PLATFORM, OS_VERSION_UNKNOWN, OS_TOO_OLD, NO_INSTALL_METHOD, INSTALL_FAILED, CONFIG_UNPARSEABLE, CONFIG_WRITE_FAILED, READY_PENDING_GRANTS.

READY is NOT one of them. It is a live-access result — reachable only by a successful tool round-trip through the adapter, never by the provisioning traversal, which cannot know whether the TCC grants were given.

If the state is anything other than READY_PENDING_GRANTS, do NOT attempt Apple-data tool calls — report the gap and the pi-apple-tools-install command first.

Read the full file on GitHub · 69 lines

Changes

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.

  1. 10d ago First seen · 69 lines · 92 tokens per session scan A 2a8f91920f3e

Subscribe to this mod's changes

apple-tools is a skill published in the GitHub repository BlackBeltTechnology/pi-agent-dashboard (278 stars, last pushed today), licensed MIT. It adds 92 tokens to every session and 725 once invoked, about $0.0005 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.