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 commands/omarshahine/apple-pim/authorizegit clone --depth 1 https://github.com/omarshahine/apple-pimWrote 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/commands/omarshahine/apple-pim/authorize)<a href="https://agentmods.dev/commands/omarshahine/apple-pim/authorize"><img src="https://agentmods.dev/badge/commands/omarshahine/apple-pim/authorize.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 | $0.00017 | $0.01028 |
| Opus 5 | $0.00009 | $0.00514 |
| Sonnet 5 | $0.00003 | $0.00206 |
| Haiku 4.5 | $0.00002 | $0.00103 |
Grade A, and why
authorize 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 — 105 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Authorize Apple PIM Access
Check and request macOS privacy permissions for the Apple PIM plugin.
Available Operations
Check Authorization Status
Use apple-pim with action status to check current permission status for all domains:
- Returns authorization state for each domain: calendars, reminders, contacts, mail
- Does not trigger any system prompts
- Useful for diagnosing "access denied" errors
Status values:
authorized- Full access granteddenied- User denied access (must enable in System Settings)restricted- System-level restriction (MDM, parental controls)notDetermined- Never requested (use actionauthorizeto prompt)writeOnly- Limited write-only access (upgrade in System Settings)unavailable- Domain disabled in plugin config or Mail.app not running
Request Authorization
Use apple-pim with action authorize to trigger macOS permission prompts:
- Optional:
domainto request access for a specific domain only - If no domain specified, requests access for all enabled domains
- Only triggers prompts for domains with
notDeterminedstatus - For
denieddomains, directs user to System Settings
Examples
Check all permissions:
/apple-pim:authorize status
Request all permissions:
/apple-pim:authorize request
Request specific domain:
/apple-pim:authorize request --domain reminders
Parsing User Intent
- "Can the plugin access my calendars?" ->
apple-pimwith actionstatus - "I'm getting permission errors" ->
apple-pimwith actionstatusthen guide user - "Grant access to reminders" ->
apple-pimwith actionauthorizeand domain "reminders" - "Set up permissions" ->
apple-pimwith actionauthorizefor all domains
The PIMHelper.app route (agent shells / embedded runtimes)
When the CLIs run under an agent runtime (Claude Code, OpenClaw, launchd
jobs), macOS attributes TCC to that runtime — which usually has no grant and
cannot even raise a prompt. The plugin handles this via
~/Applications/PIMHelper.app: calls route through the helper, the grant
binds to the helper's bundle + signature, and it persists across host apps.
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 · 105 lines · 17 tokens per session scan A fc6f5b98158f
authorize is a command published in the GitHub repository omarshahine/apple-pim (50 stars, last pushed today), licensed MIT. It adds 17 tokens to every session and 1,028 once invoked, about $0.0001 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 commands, from other repositories
prep-for-task
Bootstrap context for a new session on the rem project. Run this BEFORE starting any implementation work.
journal
Write a journal entry for today's work session on the rem project.
release
Create a new release for the rem project.
app
Control macOS apps via peekaboo app.
mcp
Run Peekaboo as an MCP server via peekaboo mcp.
drag
Execute drag-and-drop flows via peekaboo drag.