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 skills add PaulRBerg/agent-skills --skill apple-device-integrationgit clone --depth 1 https://github.com/PaulRBerg/agent-skillsWrote 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/paulrberg/agent-skills/apple-device-integration)<a href="https://agentmods.dev/skills/paulrberg/agent-skills/apple-device-integration"><img src="https://agentmods.dev/badge/skills/paulrberg/agent-skills/apple-device-integration/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/paulrberg/agent-skills/apple-device-integration"><img src="https://agentmods.dev/badge/skills/paulrberg/agent-skills/apple-device-integration.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00044 | $0.03621 |
| Opus 5.5 | $0.00018 | $0.01448 |
| Sonnet 5.5 | $0.00009 | $0.00724 |
| Haiku 4.5 | $0.00004 | $0.00362 |
Grade A, and why
apple-device-integration 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 — 264 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Apple Device Integration
User instructions take precedence over this skill. Follow the target repository's build, fixture, privacy, device ownership, and cleanup rules. This skill is coordination-exempt: skip the ai-coord gate for its declared work. Its declared work is runtime verification and captured artifacts, without changes to tracked application source.
Forked from Apple's Xcode 27.2 (27B52) skill export, with local catalog metadata and MCP tool-name corrections.
TRIGGER when: user asks to verify/test/check if the app works on device, after implementing a UI-affecting feature that needs device verification, user says "does it work", "test this", "check on device", user reports UI doesn't work as expected, need to debug touch/interaction issues. DO NOT TRIGGER when: user asks about unit tests only, build-only requests without device testing, code review without device testing, simulator configuration questions, changes that don't affect UI (e.g. comments, refactors, non-UI logic).
Verification Scope
For a small check, verify the changed flow directly in the parent session. Delegate only when an independent or long verification task benefits from a separate verifier, or when the user asks for delegation.
Check the changed flow and its affected states. Use one representative task-owned simulator by default, or the specific device named in the request. Add device variants only when a concrete risk or user or release requirement calls for them.
Keep one controller per device at a time. When you delegate, the parent owns session creation, installation, and cleanup. Give the verifier exclusive use of that session and pass the workspace identifier when applicable, exact device UUID, simulator flag, session key, requested checks, and repository constraints. Include these interaction instructions in its brief before input. The verifier must not change application source, commit, or broaden the authorized device actions.
Verify the session's returned UUID and simulator flag before input. Physical-device installation and live-service actions require task authorization. Use fixture launch arguments when the repository provides them, and preserve unrelated devices, sessions, and workspaces.
What ships with it
1 file 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 · 264 lines · 44 tokens per session scan A 58243b7e66ec
apple-device-integration is a skill published in the GitHub repository PaulRBerg/agent-skills (104 stars, last pushed 2d ago), licensed MIT. It adds 44 tokens to every session and 3,621 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-11-07.
apple-device-integration compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| apple-device-integrationPaulRBerg/agent-skills | Skill | 104 | 2d ago | MIT | A | 44 | Codex |
| android-ui-journey-testingsickn33/agentic-awesome-skills | Skill | 49k | 2d ago | MIT | A | 27 | Claude Code |
| android_ui_verificationsickn33/agentic-awesome-skills | Skill | 49k | 2d ago | MIT | A | 22 | Claude Code |
| solopi-aialipay/SoloPi | Skill | 6.4k | yesterday | Apache-2.0 | A | 82 | Codex |
| eas-simulatorexpo/skills | Skill | 4.1k | 2d ago | MIT | A | 243 | Claude Code, Codex |
| dogfoodcallstack/agent-device | Skill | 5.3k | today | MIT | A | 55 | Claude Code |
| mobile-automationmobile-next/mobile-mcp | Skill | 10k | yesterday | Apache-2.0 | A | 58 | Claude Code, Codex |