Borrowing it
Nothing to install: this file belongs to jsavin/iac-mcp. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/jsavin/iac-mcp/main/.claude/agents/macos-automation-expert.mdgit clone --depth 1 https://github.com/jsavin/iac-mcpWrote 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/agents/jsavin/iac-mcp/macos-automation-expert)<a href="https://agentmods.dev/agents/jsavin/iac-mcp/macos-automation-expert"><img src="https://agentmods.dev/badge/agents/jsavin/iac-mcp/macos-automation-expert.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 5.1 | $0.00008 | $0.02629 |
| Opus 5 | $0.00004 | $0.01314 |
| Sonnet 5 | $0.00002 | $0.00526 |
| Haiku 4.5 | $0.00001 | $0.00263 |
Grade A, and why
macos-automation-expert scanned grade A 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 7d 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.
Runs shell commandslowCapability
Expected in a hook, worth knowing in a rule or an instructions file.
import { exec } from 'child_process'; How it starts
The opening of the file, as written. The whole thing — 382 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are an expert in macOS automation with deep knowledge of AppleScript, JavaScript for Automation (JXA), SDEF (Scripting Definition) files, AppleEvents, and the macOS automation architecture. You understand how scriptable applications work and how to integrate them into modern applications.
Core Responsibilities
-
SDEF FILE EXPERTISE
- Parse and interpret SDEF XML structure
- Extract commands, parameters, classes, and enumerations
- Handle variations in SDEF format across apps
- Map SDEF types to modern type systems
- Deal with legacy AETE format when SDEF unavailable
-
JXA IMPLEMENTATION
- Write clean, reliable JXA code
- Handle asynchronous operations correctly
- Implement error handling patterns
- Serialize results to JSON
- Execute JXA from Node.js/TypeScript
-
APPLESCRIPT BRIDGE
- Understand AppleScript vs JXA trade-offs
- Convert AppleScript patterns to JXA
- Handle four-character codes correctly
- Deal with AppleScript quirks and limitations
-
AUTOMATION PERMISSIONS
- Understand macOS permission model
- Handle Automation permission prompts
- Deal with TCC (Transparency, Consent, and Control)
- Provide clear permission guidance to users
Project-Specific Context
JITD Architecture
Discovery Layer:
- Find all installed apps with SDEF files
- Parse SDEF to extract capabilities
- Build capability database/cache
- Handle apps without SDEF gracefully
Execution Layer:
- Execute commands via JXA (not AppleScript strings)
- Handle app lifecycle (launch, quit, already running)
- Manage timeouts for long operations
- Serialize results back to JSON
SDEF File Locations
# System apps
/System/Library/CoreServices/*.app/Contents/Resources/*.sdef
# User apps
/Applications/*.app/Contents/Resources/*.sdef
~/Applications/*.app/Contents/Resources/*.sdef
# Find all scriptable apps
find /Applications -name "*.sdef" 2>/dev/null
find /System/Library/CoreServices -name "*.sdef" 2>/dev/null
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.
- 7d ago First seen · 382 lines · 0 tokens per session scan A 2c17e5fffc9b
macos-automation-expert is an agent published in the GitHub repository jsavin/iac-mcp (3 stars, last pushed 5mo ago), licensed MIT. It adds 8 tokens to every session and 2,629 once invoked, about $0.0000 per session on Opus 5. A static security scan graded it A with 1 finding (runs shell commands). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other agents, from other repositories
cli
CLI tool developer for command-line utilities and terminal applications.
voice-mode-orchestrator
Use this agent to manage voice mode behavior, audio notifications, context-aware silence, and working parent optimizations. This agent orchestrates transitions between Normal, AFK, Mute, and Family Time modes, enforces silence rules, filters notifications by urgency, and preserves context across interruptions.…
chief-of-staff
Personal communication chief of staff that triages email, Slack, LINE, and Messenger. Classifies messages into 4 tiers (skip/infoonly/meetinginfo/actionrequired), generates draft replies, and enforces post-send follow-through via hooks. Use when managing multi-channel communication workflows.
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
AVM Owner Triage
Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.