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 vincentkoc/dotskills --skill agent-device-labgit clone --depth 1 https://github.com/vincentkoc/dotskillsWrote 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/vincentkoc/dotskills/agent-device-lab)<a href="https://agentmods.dev/skills/vincentkoc/dotskills/agent-device-lab"><img src="https://agentmods.dev/badge/skills/vincentkoc/dotskills/agent-device-lab/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/vincentkoc/dotskills/agent-device-lab"><img src="https://agentmods.dev/badge/skills/vincentkoc/dotskills/agent-device-lab.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 | $0.00039 | $0.01566 |
| Opus 5.5 | $0.00016 | $0.00626 |
| Sonnet 5.5 | $0.00008 | $0.00313 |
| Haiku 4.5 | $0.00004 | $0.00157 |
Grade A, and why
agent-device-lab 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 1mo 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 — 154 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent Device Lab
Purpose
Prepare a Mac and one physical Android or iPhone for an authorized test.
This skill owns host readiness and device enrollment. Use the installed upstream
agent-device skill or version-matched CLI help for app-driving commands.
When to use
- Auditing or preparing host tooling for a physical Android phone or iPhone.
- Diagnosing device trust, Developer Mode, or runner-signing blockers.
- Setting up iPhone Mirroring or proving one bounded device interaction.
For ordinary app testing on an already prepared target, use the app automation workflow directly. Simulator setup and fleet deployment are separate tasks.
Workflow
- Identify the requested mode, host, physical device, app, and observable result. An audit or plan does not authorize installation, enrollment, settings changes, or app interaction. Continue within existing authorization; obtain only any missing authority for the specific change.
- Inspect only the selected mode's prerequisites. Mirroring alone needs no ADB,
XCTest runner, or agent-device installation. For agent-device, resolve the
installed binary and version; follow its
help workflowand current installation requirements. Prefer a trusted installed or project-pinned CLI. Installing a skill does not install that CLI; do not silently fetch and execute a mutable@latestpackage. - Report missing prerequisites before changing them. Limit authorized host preparation to official platform tools and the selected device platform. Device Trust/RSA prompts, passcodes, Developer Mode confirmation, Apple Account, 2FA, and signing-account authentication belong to the owner. Wait at that boundary; never collect their credentials or bypass the prompt.
Android
Use Google's Android SDK Platform Tools.
The owner enables USB debugging and approves this host's RSA key on the phone.
adb devices -l must identify the intended physical serial in state device;
unauthorized, offline, or a missing device is a blocker. A device entry alone
does not prove Android has finished booting. Bind subsequent ADB commands with
-s <serial> and agent-device with --platform android --serial <serial>.
What ships with it
2 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.
- 1mo ago First seen · 154 lines · 39 tokens per session scan A 059e433efe7e
agent-device-lab is a skill published in the GitHub repository vincentkoc/dotskills (109 stars, last pushed yesterday), licensed MIT. It adds 39 tokens to every session and 1,566 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 2026-09-15.
Other skills, from other repositories
openhue
Control Philips Hue lights, rooms, and scenes via the OpenHue CLI. Turn lights on/off, adjust brightness, color, color temperature, and activate scenes.
blucli
BluOS CLI (blu) for discovery, playback, grouping, and volume.
eightctl
Control Eight Sleep pods (status, temperature, alarms, schedules).
autofish-control
Control Android devices with Autofish via the af CLI. Use this skill when you need reliable observe-act-verify loops, ref-based tapping, overlay management, screenshots, and recovery steps.
designing-hardware-products
AI-automated hardware product pipeline: from requirements to manufacturable Gerber + compiled firmware + cross-platform app. Orchestrates system design, ESP-IDF firmware, KiCad PCB, UniApp client, and release packaging in a zero-human-touch flow.
axiom-camera-capture
AVCaptureSession, camera preview, photo capture, video recording, RotationCoordinator, session interruptions, deferred processing, capture responsiveness, zero-shutter-lag, photoQualityPrioritization, front camera mirroring.