human-auth-qr

human-auth-qr is a skill for Claude Code, Codex from pockebot/openpocket. It costs 30 tokens per session (582 once invoked), scanned A, original, MIT.

A guide for getting QR-code scan results from a user's real phone when an agent or emulator cannot scan the code itself.

In plain words
What is it for?
Use it when a user must scan a QR code and return its text or a photo so the app can enter or process the result.
Why use it?
It removes the gap between an on-screen or physical QR code and the app that needs its contents for login, payments, tickets, products, or linking.

Skill for Claude CodeCodex

Which agent this was written for is unclear — built for openclaw. Also seen: built for openclaw.

Good fit Use it when a user must scan a QR code and return its text or a photo so the app can enter or process the result.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/pockebot/openpocket/human-auth-qr
Install

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.

Any agent
npx skills add pockebot/openpocket --skill human-auth-qr
Clone the repo
git clone --depth 1 https://github.com/pockebot/openpocket

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for human-auth-qr

README.md
[![agentmods](https://agentmods.dev/badge/skills/pockebot/openpocket/human-auth-qr/github.svg)](https://agentmods.dev/skills/pockebot/openpocket/human-auth-qr)
Your own site
<a href="https://agentmods.dev/skills/pockebot/openpocket/human-auth-qr"><img src="https://agentmods.dev/badge/skills/pockebot/openpocket/human-auth-qr/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.

agentmods 80×15 button for human-auth-qr

Your own site · 80×15
<a href="https://agentmods.dev/skills/pockebot/openpocket/human-auth-qr"><img src="https://agentmods.dev/badge/skills/pockebot/openpocket/human-auth-qr.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 30 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 582 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00030 $0.00582
Opus 5 $0.00015 $0.00291
Sonnet 5 $0.00006 $0.00116
Haiku 4.5 $0.00003 $0.00058

Measured 9d ago against content hash ed4f01addb64, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

human-auth-qr 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 9d 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.

skills/human-auth-qr/SKILL.md · 62 lines

How it starts

The opening of the file, as written. The whole thing — 62 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Human Auth: QR Code

Use this when an app displays a QR code that needs to be scanned by the user's real phone, or when the app needs QR scan input.

When to Trigger

  • App shows a QR code for "Scan to log in" (e.g., WhatsApp Web, Telegram Desktop, WeChat).
  • App requires scanning a QR code from a physical object (ticket, product, receipt).
  • App needs barcode/QR input but the emulator camera cannot scan.

How to Call

request_human_auth(
  capability: "qr",
  instruction: "Please scan the QR code shown on the Agent Phone screen (or scan [describe target]).",
  uiTemplate: {
    allowTextAttachment: true,
    allowPhotoAttachment: true,
    title: "QR Code Scan Needed",
    summary: "Scan the QR code and provide the result."
  }
)

What You Receive

  • If the human entered the QR text: artifact_kind: text, value: "<qr_content>"
  • If the human took a photo of the QR: artifact_type: image/jpeg

How to Apply

Text Result (QR content decoded)

  1. Read the artifact to get the decoded text.
  2. If the app has a "Enter code manually" option, type the code there.
  3. If the code is a URL, you may need to open it via:
    shell("am start -a android.intent.action.VIEW -d '<url>'")
    

Photo of QR Code

  1. If the app has its own QR scanner and needs the image:
    • Push the photo to device and import via the scanner's gallery option.
  2. If you need to decode the QR from the photo, this requires a QR decoder (not built-in).

"Scan to Log In" Flows

For apps like WhatsApp Web where the QR just needs to be scanned by the user's phone app:

  1. The human uses their phone's native app to scan the QR displayed on the emulator screen.
  2. No artifact is needed — the human just approves after scanning.
  3. The app on Agent Phone will automatically proceed after the scan completes.

Tips

  • For "scan to login" flows, use Remote Takeover so the human can see the QR code on their phone and scan it with their native app.
  • QR codes may expire. If the login times out, the app usually regenerates a new QR.

Read the full file on GitHub · 62 lines

Changes

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.

  1. 9d ago First seen · 62 lines · 30 tokens per session scan A ed4f01addb64

Subscribe to this mod's changes

human-auth-qr is a skill published in the GitHub repository pockebot/openpocket (841 stars, last pushed 2mo ago), licensed MIT. It adds 30 tokens to every session and 582 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.

Related

Other skills, from other repositories

orca-emulator-android

Android device and emulator control from inside Orca over adb, with the live device view in Orca's emulator pane. Use when driving an adb-connected emulator or phone on Windows, Linux, or macOS: booting AVDs, taps, swipes, typing, hardware buttons, rotation, app install and launch, runtime permissions, the…

stablyai/orca · 102 tokens

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…

dotnet/skills · 176 tokens

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.

callstack/agent-device · 55 tokens

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.

microsoft/winappCli · 71 tokens

apple-search-ads

When the user wants to set up, optimize, or scale Apple Search Ads (ASA) campaigns — including keyword bidding, match types, campaign structure, Creative Product Sets, CPP routing, and ROAS optimization. Use when the user mentions "Apple Search Ads", "ASA", "Search Ads", "Search tab ads", "Today tab ads", "CPT"…

Eronred/aso-skills · 127 tokens

android-pentest

A guide for authorized security testing of Android apps, covering APK inspection, runtime testing, traffic capture, code review, and function hooking. An APK is the installable package used by an Android app.

Netw0rkNoob/VulnClaw · 32 tokens