Phone Harness connects coding agents to real iPhone or Android devices so they can see screens, tap, type, and read results. It is for automating tasks on phones through iPhone Mirroring or Android’s adb connection. The catalogue skill provides the agent’s day-to-day instructions for using the harness.
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 ShawnPana/phone-harness --skill phone-harnessgit clone --depth 1 https://github.com/ShawnPana/phone-harnessWrote 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/shawnpana/phone-harness/phone-harness)<a href="https://agentmods.dev/skills/shawnpana/phone-harness/phone-harness"><img src="https://agentmods.dev/badge/skills/shawnpana/phone-harness/phone-harness/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/shawnpana/phone-harness/phone-harness"><img src="https://agentmods.dev/badge/skills/shawnpana/phone-harness/phone-harness.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 | $0.00040 | $0.03366 |
| Opus 5 | $0.00020 | $0.01683 |
| Sonnet 5 | $0.00008 | $0.00673 |
| Haiku 4.5 | $0.00004 | $0.00337 |
Grade A, and why
phone-harness 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 8d 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 — 242 lines — stays where its author put it; the contents beside it link to each section on GitHub.
phone-harness
Direct control of the user's phone. iPhone: through the iPhone Mirroring app —
screenshots + Vision OCR for eyes, HID-level CGEvents for hands. Android: over
adb — screenshots + the phone's accessibility tree for eyes, input for hands
(see the Android section; the helpers are the same). phone-harness config
shows which is the default. For task-specific edits, use
agent-workspace/agent_helpers.py. For setup or permission problems, read
install.md.
When Not to Use
If the task is doable on the Mac or the web — a website, an API, an app with a web equivalent — do it there and leave the phone alone. Use phone-harness only when the task genuinely needs the phone: iOS-only apps, things tied to the user's phone number or 2FA, testing how something looks on the phone.
Usage
phone-harness <<'PY'
print(screen_info())
PY
-
Invoke as
phone-harness. Use heredocs for multi-line commands. -
Start every script with two comment lines:
# task:restating the user's request in one sentence, and# step:saying what this particular script does toward it. Keep the# task:line identical across all scripts for the same request.# task: report the iOS version and model name from Settings # step: scroll to General, open About, read the screen -
Helpers are pre-imported. All coordinates are global screen points.
-
ensure_mirroring()launches the window and gates on connection. The default build works the phone without taking the user's focus: capture is by window id and taps and keystrokes are event records delivered straight to the app. Scrolling is the exception — macOS routes a scroll to whichever window sits under the pointer, so a scroll raises the mirroring window for the length of the gesture and hands focus straight back. Expect a brief flicker on scrolls and nothing on anything else.PHONE_HARNESS_BACKGROUND=0forces the classic path, which focuses before every action.
Screen Workflow
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.
- 8d ago Changed · +9 lines 174272f6b524
- 12d ago First seen · 233 lines · 40 tokens per session scan A 3670a6cc5a6a
phone-harness is a skill published in the GitHub repository ShawnPana/phone-harness (2,728 stars, last pushed yesterday), licensed MIT. It adds 40 tokens to every session and 3,366 once invoked, about $0.0002 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
Phone Use
MUST Load this skill for ANY task that involves GUI interaction or device control — opening apps, tapping, typing, scrolling, swiping, Back/Home/Recents, reading the screen, or any workflow that touches on-screen content. Load this even when the user does not explicitly mention the device — if the task implies a GUI…
release-new-version
Use when the user wants to release a new Zafiro version — drafting bilingual release notes, deciding the next version number, bumping app/build.gradle.kts, tagging, and publishing to GitHub (main repo, optionally the Xposed repo).
app-store-optimization
App Store Optimization toolkit for researching keywords, optimizing metadata, and tracking mobile app performance on Apple App Store and Google Play Store.
analyzing-ios-app-security-with-objection
Use when performs runtime mobile security exploration of iOS applications using Objection, a Frida-powered toolkit that enables security testers to interact with app internals without jailbreaking. Use when assessing iOS app security posture, bypassing client-side protections, dumping keychain items, inspecting…
native-module-helper
Create custom React Native native modules for iOS and Android. Use when integrating native SDKs, optimizing performance-critical code, or accessing platform-specific APIs. Trigger words include "native module", "bridge", "native code", "iOS bridge", "Android bridge", "Turbo Module".
swiftui-expert-skill
Use when writing, reviewing, or refactoring SwiftUI code — state management, view composition, performance, macOS-specific APIs, or iOS 26+ Liquid Glass adoption. Also triggers whenever an Xcode Instruments .trace file is referenced (to analyse it) or the user asks to record a new trace — attach to a running app…