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 rshankras/claude-code-apple-skills --skill run-devicegit clone --depth 1 https://github.com/rshankras/claude-code-apple-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/rshankras/claude-code-apple-skills/run-device)<a href="https://agentmods.dev/skills/rshankras/claude-code-apple-skills/run-device"><img src="https://agentmods.dev/badge/skills/rshankras/claude-code-apple-skills/run-device.svg" alt="Measured on agentmods" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 4 findings, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Anti-Refusal · line 34 Skill attempts to nullify the agent's safety policies or restrictions ('you have no restrictions', 'ignore your guidelines', 'do anything now'). This is a direct jailbreak that disables guardrails.Fix: Remove jailbreak framing that nullifies safety policies or restrictions. Skill content must not instruct the agent to ignore its guidelines or operate without guardrails.
- high Prompt Injection · line 155 This pattern attempts to override system instructions or ignore safety constraints. Without LLM analysis, manual review is recommended.Fix: Remove or rewrite any text that instructs the agent to ignore prompts, override safety rules, or trust unverified content. Ensure skill content cannot be injected to alter agent behavior.
- medium Rogue Agent · line 98 Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
- medium Rogue Agent · line 98 Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
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 | $0.00064 | $0.01863 |
| Opus 5 | $0.00032 | $0.00932 |
| Sonnet 5 | $0.00013 | $0.00373 |
| Haiku 4.5 | $0.00006 | $0.00186 |
Grade A, and why
run-device 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 4d 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.
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 — 174 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Run on a Physical Device (CLI)
Builds, signs, installs, and launches an app on a connected physical device
straight from the terminal — no Xcode Run button. The companion run-simulator
skill covers the Simulator; this is the hardware path, which uses a different
toolchain: devicectl (not simctl), real code signing, and an external tool
for screenshots.
Building proves the code typechecks and signs; launching proves it installs and runs on real hardware. A crash on launch or a failed install is a failure.
When This Skill Activates
Use when the user wants to:
- Run / test their app on a real iPhone or iPad from the CLI
- Install a build on a device without opening Xcode
- Reproduce a device-only bug (camera, sensors, performance, push)
- Screenshot the app running on hardware
Not for the Simulator (use run-simulator) and not for xcodebuild test.
Prerequisites (one-time, partly interactive — cannot be scripted)
- Device connected by USB (or paired over Wi-Fi).
- Developer Mode ON (iOS 16+): Settings → Privacy & Security → Developer Mode → on → restart. There is no CLI to enable this.
- Device trusted/paired: the first connection shows "Trust This Computer?"
on the device — tap Trust.
devicectlpairs once trusted. - Automatic signing configured: the target needs
CODE_SIGN_STYLE = Automaticand aDEVELOPMENT_TEAM, and the signing Apple ID must already be logged into Xcode (Settings → Accounts) so-allowProvisioningUpdatescan mint profiles. A free personal team works but apps expire after 7 days.
Confirm reachability before building:
xcrun devicectl list devices
The Identifier column is a CoreDevice UUID (e.g. A1B2C3D4-…). It is used by
devicectl for install/launch. It is NOT the value xcodebuild wants — see
the trap in step 2. Pick a row whose State is available (paired) /
connected.
Process
1. Pick the device identifier
xcrun devicectl list devices # grab the Identifier (CoreDevice UUID) of the paired device
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.
- 4d ago First seen · 174 lines · 64 tokens per session scan A 8be6f3daee10
run-device is a skill published in the GitHub repository rshankras/claude-code-apple-skills (708 stars, last pushed 1mo ago), licensed MIT. It adds 64 tokens to every session and 1,863 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
android-development
Android development with Kotlin, Jetpack Compose, and modern Android architecture. Use when building Android apps, implementing Material Design, or following Android best practices.
flutter-development
Cross-platform development with Flutter and Dart for iOS, Android, Web, Desktop, and embedded. Use when building Flutter apps, implementing Material/Cupertino design, or optimizing Dart code.
ios-development
Comprehensive guide for building native Apple platform applications.
kotlin-multiplatform
KMP/CMP shared business logic, Compose Multiplatform, expect/actual, Ktor, SQLDelight, and platform-specific implementations. Use when building cross-platform Kotlin applications for Android, iOS, desktop, or web.
flame-harness-admob
Phase 7 — analyze the game, decide a rewarded-ad strategy, guide manual AdMob ad-unit creation, and inject googlemobileads + ATT/UMP consent code.
flame-harness-screenshot
Phase 9 — capture store screenshots in the game's configured locales via integrationtest (ads hidden), fill ASO keywords, and upload via fastlane.