Works with the AI Agents you already use
User Detection & Session Context Reviewer
Review macOS admin scripts for reliable current-user detection and safe session-context handling.
$14.99
User Detection & Session Context Reviewer
Example session with this skill installed
Review this Jamf check-in script that uses $3 to identify the user and tell me if the UI prompt will work reliably during background runs.
- Read your context and instructions
- Compiled the user detection
Context Review
- Issue: Script uses static Jamf $3 which is empty during check-in policies.
- Fix: Implement 'stat -f %Su /dev/console' with a loginwindow check.
- Risk: UI prompt will hang if no user is logged in.
- Test: Verify behavior during Fast User Switching and Setup Assistant.
Connects securely to your tools. The creator never sees your data.
About this skill
Defensive review for macOS current-user logic
User Detection & Session Context Reviewer reviews Jamf, Kandji, and Iru scripts that need to identify the logged-in user or show a user-facing prompt.
What it checks
- Current-user patterns such as
stat -f %Su /dev/console,scutil, Jamf$3, and related approaches. - Root execution versus user UI context, including
launchctl asuser. - Loginwindow, logout, setup assistant, Fast User Switching, and stale-user edge cases.
- Prompt patterns that avoid logs, process listings, and persistent files.
- Jamf, Kandji, and Iru workflow differences.
Boundaries
This is a defensive admin-review skill. Use redacted or synthetic examples. It does not collect, validate, store, transmit, or request real passwords, tokens, recovery keys, or private tenant values.
Output
You get a context-readiness verdict, edge-case notes, safer detection and prompt patterns, validation checklist, and open questions for local policy or vendor documentation.
- Cannot execute or test scripts on live hardware.
- Reviews logic only; does not verify MDM server-side API permissions.
- Limited to shell scripts (zsh/bash), not Swift or Objective-C binaries.
How to use
- 1
Connect your agent to the Agensi MCP
Copy the prompt and paste it into Claude, ChatGPT, Cursor or any agent that supports MCP. It sets up the connection for you. Manual setup
- 2
Sign in to Agensi
Your agent shows a sign-in link. Sign in and click Allow.
- 3
Ask for what you need
Your agent loads this skill and uses it on your task. It always asks before any payment.
Reviews
No reviews yet
Be one of the first to try it. Every listed skill goes through the trust checks below.
Security scanned
Checked by our 8-point scan before listing
Fresh listing
Recently published to Agensi
Money-back guarantee
Doesn't do what its page promises? You get your money back.
Trust & safety
Security scan
Security scan passed 5 months ago
Requires
Permissions
No special permissions declared or detected