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 instructions/omarshahine/apple-pim/agents-mdgit 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/instructions/omarshahine/apple-pim/agents-md)<a href="https://agentmods.dev/instructions/omarshahine/apple-pim/agents-md"><img src="https://agentmods.dev/badge/instructions/omarshahine/apple-pim/agents-md.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 | $0.05607 | $0.05607 |
| Opus 5 | $0.02804 | $0.02804 |
| Sonnet 5 | $0.01121 | $0.01121 |
| Haiku 4.5 | $0.00561 | $0.00561 |
Grade C, and why
apple-pim AGENTS.md scanned grade C with 1 finding 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 today.
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.
Reaches for credential fileshighPrivilege escalation
SSH keys, cloud credentials, git-credentials, .npmrc, /etc/shadow: reading these is how a config file becomes a credential leak.
`~/.ssh/id_rsa` to an outbound email. How it starts
The opening of the file, as written. The whole thing — 350 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Apple PIM Plugin
macOS PIM (Personal Information Management) tools for Calendar, Reminders, Contacts, and Mail.app. Works with Claude Code (via MCP) and OpenClaw (via native tool registration). Both adapters share a common lib/ layer that delegates to native Swift CLIs using EventKit, Contacts framework, and JXA.
Quick Commands
# Initial setup
./setup.sh
# Swift CLIs
cd swift
swift build -c release
swift test
# MCP server
cd mcp-server
npm install
npm test
npm run build
# Agent evals (from repo root)
npm run eval
Architecture
Handler logic, schemas, and sanitization live in lib/ (shared). The MCP server and OpenClaw plugin are thin adapters. All access control, filtering, and default resolution is handled by the Swift CLIs via the shared PIMConfig library:
Claude Code <--MCP--> mcp-server/server.js ---+
+--> lib/ (handlers, schemas, sanitize)
OpenClaw <--tools--> openclaw/src/index.ts ---+ |
Swift CLIs (EventKit / Contacts / JXA)
|
PIMConfig (~/.config/apple-pim/)
Each Swift CLI is a standalone binary that reads from macOS frameworks, validates access via PIMConfig, and writes JSON to stdout.
Repo Layout
| Path | Purpose |
|---|---|
lib/ |
Shared handler logic, schemas, sanitize (used by both MCP and OpenClaw) |
lib/handlers/ |
Domain handlers: calendar, reminder, contact, mail, apple-pim |
swift/Sources/PIMConfig |
Shared config library (filtering, profiles, validation) |
swift/Sources/CalendarCLI |
EventKit calendar CLI |
swift/Sources/ReminderCLI |
EventKit reminders CLI |
swift/Sources/ContactsCLI |
Contacts framework CLI |
swift/Sources/MailCLI |
Mail.app JXA-based CLI |
mcp-server/server.js |
MCP adapter (imports lib/, thin pass-through) |
mcp-server/dist/server.js |
Bundled server artifact (rebuild after source changes) |
openclaw/ |
OpenClaw plugin package (NPM: apple-pim-cli) |
openclaw/src/index.ts |
OpenClaw tool registration with per-call isolation |
evals/ |
Agent eval suite (YAML scenarios, JSON fixtures, vitest tests) |
evals/helpers/ |
Mock CLI runner, scenario loader, grading functions |
evals/fixtures/ |
Canned CLI JSON responses for deterministic testing |
evals/scenarios/ |
YAML eval case definitions (4 categories) |
evals/tests/ |
Vitest test files (tool-call, response, multi-turn, safety) |
.github/workflows/tests.yml |
CI checks for Node, Swift, and agent eval jobs |
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.
- today Changed · +2 lines · +167 tokens per session be92bcccf115
- yesterday Changed · +6 lines · +193 tokens per session 688bafae0ae3
- 5d ago First seen · 342 lines · 5,247 tokens per session scan C 80fba89fc970
apple-pim AGENTS.md is an instructions file published in the GitHub repository omarshahine/apple-pim (51 stars, last pushed today), licensed MIT. It adds 5,607 tokens to every session, about $0.0280 per session on Opus 5. A static security scan graded it C with 1 finding (reaches for credential files). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other instructions, from other repositories
mcp-server-apple-events CLAUDE.md
Claude Code instructions for FradSer/mcp-server-apple-events, covering claude.md, commands, run all tests, run a single test file and run tests matching a pattern.
mcp-server-apple-events AGENTS.md
AGENTS.md instructions for FradSer/mcp-server-apple-events, covering repository guidelines, project structure & module organization, build, test, and development commands, coding style & naming conventions and testing guidelines.
mcp-server-apple-events GEMINI.md
Gemini CLI instructions for FradSer/mcp-server-apple-events, covering apple events mcp server, project overview, architecture, building and running and prerequisites.
che-ical-mcp CLAUDE.md
Claude Code instructions for PsychQuant/che-ical-mcp, covering spectra instructions, use /spectra: skills when, workflow, parked changes and mcp 功能驗證的表面選擇（.claude/rules/mcp-binary-version-testing.md）.
che-ical-mcp AGENTS.md
AGENTS.md instructions for PsychQuant/che-ical-mcp, covering spectra instructions, use $spectra- skills when, workflow and parked changes.
orchard-mcp AGENTS.md
Instructions for l22-io/orchard-mcp, covering agents.md, project overview, commands, architecture and key patterns.