Borrowing it
Nothing to install: this file belongs to BariBariGood/manzanas. 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/BariBariGood/manzanas/main/.agents/skills/drive-a-mirrored-iphone/SKILL.mdgit clone --depth 1 https://github.com/BariBariGood/manzanasWrote 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/baribarigood/manzanas/drive-a-mirrored-iphone)<a href="https://agentmods.dev/skills/baribarigood/manzanas/drive-a-mirrored-iphone"><img src="https://agentmods.dev/badge/skills/baribarigood/manzanas/drive-a-mirrored-iphone/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/baribarigood/manzanas/drive-a-mirrored-iphone"><img src="https://agentmods.dev/badge/skills/baribarigood/manzanas/drive-a-mirrored-iphone.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 | $0.00092 | $0.01632 |
| Opus 5 | $0.00046 | $0.00816 |
| Sonnet 5 | $0.00018 | $0.00326 |
| Haiku 4.5 | $0.00009 | $0.00163 |
Grade A, and why
drive-a-mirrored-iphone 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 12d 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 — 115 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Drive a mirrored iPhone (mirror backend)
Mirror-backed physical devices are driven by injecting CoreGraphics input
into the iPhone Mirroring window via the helpers/mirrord Swift helper
(Unix-socket HTTP/JSON). The Go side lives in
internal/actions/device_mirror.go + internal/actions/mirror/client.go.
Coordinate space and scale
- ALL mirror coordinates (tap/swipe/scroll input AND observed frames) are
capture-image pixels, not device points.
observe/screenshotresults carryimg_w/img_h(the tap coordinate space) andcapture_scale— the capture's pixels-per-window-point factor (≈2.0 on a HiDPI/Retina host, 1.0 headless; 0/absent means the helper predates the field). Divide bycapture_scaleto get window points. - Size-capped screenshots still report the pre-transform
img_w/img_h, so map detected pixels back through those before tapping.
Action kinds specific to mirror
- Long-press:
tap {x,y,duration_ms}withduration_msin 1..10000 (the helper is single-threaded and sleeps the whole press — an unbounded press would wedge every later action). Sim (touch-down → delay → touch-up) and WDA (W3C pointer chain) implement the same field with the same bound. - Wheel scroll:
scroll {x,y,dy}(dynon-zero; positive scrolls content down). Mirror-only — it's the trackpad-scroll analog for fine list movement without swipe momentum. Sim/WDA returnnot_implemented(useswipe). Note velocity swipes can't advance paged feeds like TikTok (#190) — wheel scroll doesn't either; that needs the phone-harness movement work (#196). scrollandtypeneed focus, everything else doesn't (real-phone findings, #241/#244):tap/swipe/buttonall land ininput_mode: backgroundwith iPhone Mirroring behind other windows, butscrollfailsunavailable("could not be brought frontmost") whenever another app holds focus on a shared Mac — fall back to a shortswipe.typedegrades automatically: background key events reach the mirroring process (Cmd shortcuts work) but iOS routes keys into text input only while the window is frontmost, so the helper briefly activates the window, types, and hands focus back best-effort — the ack saysinput_mode:"focused-degrade"with aninput_note. Expect the mirroring window to steal focus for the duration of atypeeven in background mode.- The iOS on-screen keyboard never appears during
type— iPhone Mirroring attaches a virtual hardware keyboard, so iOS suppresses the soft keyboard by design. A missing keyboard is NOT a focus failure; verify typing by the ack'sverify:"ocr-delta"/pixel delta or by re-observing the field. - CLI:
manzanas tap X Y --duration-ms N,manzanas scroll X Y DY.
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.
- 12d ago First seen · 115 lines · 92 tokens per session scan A b0dc878fcee4
drive-a-mirrored-iphone is a skill published in the GitHub repository BariBariGood/manzanas (20 stars, last pushed 10d ago), licensed Apache-2.0. It adds 92 tokens to every session and 1,632 once invoked, about $0.0005 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 2026-08-30.
Other skills, from other repositories
benchmark
Run performance + quality benchmarks. ASR reports WER, RTF, process memory, and throughput across engines/variants. Arguments include asr, tts, vad, diarize, asr-quick.
review-pr
Review a pull request for conceptual fit, architecture impact, adversarial failure modes, security risk, docs impact, regression risk, test coverage, and merge readiness. Use when asked to review a PR, check whether a PR is safe to merge, decide if more tests are needed, perform adversarial or security review, or…
boutique-best-practices
Best practices for using Boutique with Swift 6 concurrency, @Observable, @ObservationIgnored, Sendable conformance, testing with preview stores, and dependency injection. Use when troubleshooting Boutique issues, migrating to Swift 6, or setting up tests.
boutique-store
Create and use Boutique Store for Swift data persistence, including initialization, @Stored controllers, CRUD operations, operation chaining, and granular event monitoring. Use when persisting arrays of items, building data controllers, or working with Boutique's Store type.
boutique-stored-values
Persist individual values with Boutique's @StoredValue (UserDefaults) and @SecurelyStoredValue (Keychain), including set, reset, toggle, bindings, keypath setters, array and dictionary helpers, and async observation. Use when storing preferences, settings, feature flags, or sensitive data like auth tokens.
boutique-swiftui
Integrate Boutique with SwiftUI views using onChange, onStoreDidLoad, bindings, and preview stores. Use when building SwiftUI views that display or react to Boutique-persisted data.