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 agentmods add skills/pockebot/openpocket/human-auth-cameranpx skills add pockebot/openpocket --skill human-auth-cameragit clone --depth 1 https://github.com/pockebot/openpocketWrote 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/pockebot/openpocket/human-auth-camera)<a href="https://agentmods.dev/skills/pockebot/openpocket/human-auth-camera"><img src="https://agentmods.dev/badge/skills/pockebot/openpocket/human-auth-camera.svg" alt="Measured on agentmods" 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 | $0.00029 | $0.00521 |
| Opus 5 | $0.00015 | $0.00260 |
| Sonnet 5 | $0.00006 | $0.00104 |
| Haiku 4.5 | $0.00003 | $0.00052 |
Grade A, and why
human-auth-camera 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.
What it actually says
Human Auth: Camera
Use this when an app on Agent Phone needs a camera photo but the emulator has no real camera.
When to Trigger
- App opens a camera intent (e.g., profile photo, document scan, ID verification).
- You see a camera preview screen that shows black or "no camera found".
- Capability Probe detects
cameraactivity from the foreground app.
How to Call
request_human_auth(
capability: "camera",
instruction: "Please take a photo of [describe what is needed].",
uiTemplate: {
allowPhotoAttachment: true,
requireArtifactOnApprove: true,
title: "Camera Photo Needed",
summary: "Take a photo with your phone camera and attach it."
}
)
After You Receive the Artifact
You will get an artifact_path pointing to a JPEG/PNG file on the local filesystem.
The photo is already pushed to Agent Phone. The result includes device_path=/sdcard/Download/openpocket-human-auth-<ts>.jpg — the file is ready in Downloads.
You must redo the app flow to select it. Follow these steps:
-
Exit the current screen state. The app may have a camera preview or picker open. Press Back (
keyevent KEYCODE_BACK) one or more times until you are back at the screen where the photo upload/capture was initiated. -
Re-open the photo picker/upload in the app. Navigate back to the attachment point (e.g., tap the "+" button, "Upload photo" option, or "Choose from gallery" alternative).
-
Select the file from Downloads. In the file picker, navigate to Downloads folder and select the
openpocket-human-auth-*file. -
Confirm and continue the app flow (tap Send, Upload, Submit, etc.).
Tips
- If the app originally opened a camera intent, look for a "Choose from gallery" or "Upload from files" alternative after pressing Back.
- Always verify the photo was accepted by checking the next screen state.
- Some apps may need you to re-trigger the entire attachment flow from the beginning.
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 · 53 lines · 29 tokens per session scan A dd68128bbfca
human-auth-camera is a skill published in the GitHub repository pockebot/openpocket (841 stars, last pushed 1mo ago), licensed MIT. It adds 29 tokens to every session and 521 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
orca-emulator-android
Control an Android emulator / device from inside Orca using the orca CLI. Use for listing/booting AVDs, taps, swipes, typing, hardware buttons (incl. Back and Recents), rotation, app install/launch, runtime permissions, the accessibility tree, and logcat — driving a real adb-connected device or emulator.…
android-tombstone-symbolication
Symbolicate the .NET runtime frames in an Android tombstone file. Extracts BuildIds and PC offsets from the native backtrace, downloads debug symbols from the Microsoft symbol server, and runs llvm-symbolizer to produce function names with source file and line numbers. USE FOR triaging a .NET MAUI or Mono Android app…
dogfood
Systematically explore and test a mobile app on iOS/Android with agent-device to find bugs, UX issues, and other problems. Use when asked to dogfood, QA, exploratory test, find issues, bug hunt, or test this app on mobile.
winapp-maui
Package and sign .NET MAUI Windows apps with winapp, resolving the resizetizer manifest dependency. Use when packaging or signing a .NET MAUI Windows app, building a MAUI MSIX or signed unpackaged build in CI, or fixing 'manifest contains unresolved placeholders ($placeholder$)' errors from winapp package.
android-pentest
安卓应用渗透测试 — APK分析、Hook、自动化测试、运行态驱动、签名恢复、抓包分析.
react-native-ease-refactor
Scan for Animated/Reanimated code and migrate to EaseView.