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 pockebot/openpocket --skill human-auth-oauthgit 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-oauth)<a href="https://agentmods.dev/skills/pockebot/openpocket/human-auth-oauth"><img src="https://agentmods.dev/badge/skills/pockebot/openpocket/human-auth-oauth.svg" alt="Measured on agentmods" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00030 | $0.00590 |
| Opus 5 | $0.00015 | $0.00295 |
| Sonnet 5 | $0.00006 | $0.00118 |
| Haiku 4.5 | $0.00003 | $0.00059 |
Grade A, and why
human-auth-oauth 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 — 66 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Human Auth: OAuth / Login
Use this when an app requires the user to log in with their account credentials.
When to Trigger
- App shows a login screen with username/email and password fields.
- App redirects to a social sign-in page (Google, Apple, Facebook, etc.).
- App requires account authentication to proceed.
How to Call
request_human_auth(
capability: "oauth",
instruction: "Please provide your login credentials for [app/service name].",
uiTemplate: {
fields: [
{ id: "username", label: "Username / Email", type: "text", required: true, autocomplete: "username" },
{ id: "password", label: "Password", type: "password", required: true, autocomplete: "current-password" }
],
artifactKind: "credentials",
requireArtifactOnApprove: true,
title: "Account Login Required",
summary: "Enter your credentials to log in."
}
)
After You Receive the Artifact
-
Read the artifact:
read(<artifact_path>)to getusernameandpassword. -
Check the current screen. The login form may still be visible, or the app may have changed state during the wait.
-
If the login form is still visible:
- Tap the username/email field →
type_text(<username>) - Tap the password field →
type_text(<password>) - Tap Sign In / Log In / Submit
- Tap the username/email field →
-
If the screen changed: press
keyevent KEYCODE_BACKto return to the login form, or re-navigate to it. -
Delete the artifact immediately (contains plaintext credentials):
exec("rm <artifact_path>") -
Handle post-login flows (2FA prompt, terms acceptance, etc.) as needed.
Multi-Step Login (e.g., Google)
Some services split login into two pages (email first, then password). If the login screen only shows one field:
- Type the visible field's value, tap Next.
- On the next page, call
request_human_authagain for the password if needed, or use the already-received credentials.
Tips
- If the app has "Sign in with Google/Apple" button, consider Remote Takeover so the human can complete the OAuth flow directly.
- Never type credentials into the wrong field. Always verify the field label before typing.
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 First seen · 66 lines · 30 tokens per session scan A 850bfc81615f
human-auth-oauth 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 590 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
opencli-sitemap-author
Use when creating or maintaining OpenCLI site sitemaps: agent-facing navigation, page-state, action, workflow, API-reference, pitfall, and fallback knowledge for a website. Use after browser exploration discovers durable site context, when a sitemap is stale, or when promoting local site knowledge into the repo.
debug-optimize-lcp
Guides debugging and optimizing Largest Contentful Paint (LCP) using Chrome DevTools MCP tools. Use this skill whenever the user asks about LCP performance, slow page loads, Core Web Vitals optimization, or wants to understand why their page's main content takes too long to appear. Also use when the user mentions…
interactive-login
How to complete browser/interactive logins (aws / gh / glab / gcloud). The platform backgrounds the login poller so it survives the human's browser round-trip — and when that does NOT work.
pinchtab-mcp
Use this skill when a task requires browser automation through PinchTab's MCP server connected to a remote browser instance. Covers navigation, element interaction, data extraction, form filling, multi-step flows, and session management via MCP tools.
azure-messaging-webpubsub-java
Build real-time web applications with Azure Web PubSub SDK for Java. Use when implementing WebSocket-based messaging, live updates, chat applications, or server-to-client push notifications.
google-safe-browsing
Prevent and fix Google Safe Browsing "Dangerous site" flags. Use when launching a public web app, buying/picking a domain, building a login or signup page, or when any site shows a red "Dangerous site" / "Deceptive site" warning in Chrome, Brave, Safari, Firefox, or Edge. Triggers on "dangerous site", "deceptive…