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 skills/gaelic-ghost/socket/xcode-device-hub-workflownpx skills add gaelic-ghost/socket --skill xcode-device-hub-workflowgit clone --depth 1 https://github.com/gaelic-ghost/socketWrote 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/skills/gaelic-ghost/socket/xcode-device-hub-workflow)<a href="https://agentmods.dev/skills/gaelic-ghost/socket/xcode-device-hub-workflow"><img src="https://agentmods.dev/badge/skills/gaelic-ghost/socket/xcode-device-hub-workflow.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 | $0.00054 | $0.00994 |
| Opus 5 | $0.00027 | $0.00497 |
| Sonnet 5 | $0.00011 | $0.00199 |
| Haiku 4.5 | $0.00005 | $0.00099 |
Grade A, and why
xcode-device-hub-workflow 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 yesterday.
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 — 52 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Xcode Device Hub Workflow
Purpose
Use Device Hub as Xcode's native surface for simulated and physical device work. It owns device selection, interaction, environment inspection, pairing, captures, and diagnostics; it does not replace project build/run, test, debugger, provisioning, or browser-mirror ownership. Use xcrun devicectl as its scriptable companion only for a bounded device-management or diagnostic need, never as a substitute for an XCUITest result.
When To Use
- Use this workflow for a Device Hub request, a run-destination decision, simulator or physical-device inspection, screenshots, videos, environment variants, pairing, or downloaded diagnostics.
- Use it when a running Xcode app should be observed or interacted with through Device Hub rather than by opening a separate Simulator window.
- Hand project build, install, launch, and scheme selection to
xcode-build-run-workflow. - Hand test design and execution to
xcode-testing-workflow; hand breakpoints and stack inspection toxcode-debugger-mcp-workflow. - Hand a future local browser mirror or Swift Package preview host to the future AgentDeck runtime; do not substitute a browser bridge for Device Hub until that runtime exists and reports ready.
Workflow
- Read the target app, device type, runtime, and evidence goal. Distinguish a normal simulated-device check from a hardware-only, performance, camera, sensor, or pairing requirement.
- Open the intended Xcode app and Device Hub. Open it from the run-destination menu's Manage Devices action or Xcode's Open Developer Tool menu when no app run has already opened the compact view.
- Select the device and record its name, platform, operating-system version, and device identifier from the inspector. Keep the selected run destination and the recorded identifier aligned; do not guess a matching simulator from its name alone.
- For a simulated device, start it and change only the requested environment setting. Treat appearance, Liquid Glass, text size, and resize-mode checks as named variants with visible before/after evidence.
- For a physical device, inspect pairing and Developer Mode state before attempting a run. Pairing, trust prompts, Developer Mode, unpairing, and configuration changes require explicit user intent at the point of mutation.
- Run or interact with the app through its owning build/run workflow. Device Hub interaction is proof of the same target device state, not a separate app runtime.
- Capture a screenshot or video only after the requested state is visible. Record the device identity, app state, and destination path; Device Hub screenshots are full device resolution and may contain sensitive content.
- Download diagnostics only when they are relevant to the reported failure, then hand the artifact to the debugger, runtime-forensics, or test workflow. State the artifact's source and avoid copying private device data into logs or commits. For a repeatable script or CI need, inspect the selected toolchain's
xcrun devicectl --helpcontract first and preserve the same device identifier in the resulting evidence. - Stop the app or device session through its owner. Do not erase, remove, unpair, or reset a device as routine cleanup.
What ships with it
3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- yesterday First seen · 52 lines · 54 tokens per session scan A 9ae512ad3dbb
xcode-device-hub-workflow is a skill published in the GitHub repository gaelic-ghost/socket (7 stars, last pushed 9d ago), licensed Apache-2.0. It adds 54 tokens to every session and 994 once invoked, about $0.0003 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 2026-09-03.
Other skills, from other repositories
app-store-optimization
Improves visibility and conversion in the App Store and Google Play — metadata, keywords, screenshots, ratings, and the listing experience that turns an impression into an install. Use this to audit or optimize an app listing, plan a launch listing, diagnose poor install conversion, or improve store search visibility.
flutter-ui
Build Flutter UI from Figma MCP or image input. Scans src for design tokens (colors, sizes, text styles), existing components, and naming conventions before writing a single line of code. Never hard-codes values.
flutter-dart-code-review
Library-agnostic Flutter/Dart code review checklist covering widget best practices, state management patterns (BLoC, Riverpod, Provider, GetX, MobX, Signals), Dart idioms, performance, accessibility, security, and clean architecture.
setup
Start DeployGate onboarding — set up app distribution from first upload to team-wide deployment.
pipeline
Use when the user wants a feature idea taken end-to-end in one autonomous run — phrases like "run the whole pipeline", "take this feature from idea to finished branch", "brainstorm then build it autonomously", "do everything from idea to merged", "implement all phases without stopping". Triggers when they want…
sdk-setup
Add the DeployGate SDK to your Android app for crash reporting and screen capture.