auth_manager

auth_manager is a skill for Claude Code, Codex from tubecreate/tubecli. It costs 15 tokens per session (522 once invoked), scanned A, original, MIT.

A workflow for obtaining and managing OAuth permissions for Google, Facebook, and TikTok. OAuth is the sign-in process that lets an app access an account after the account owner approves it.

In plain words
What is it for?
Use it when someone needs to grant an app permission to manage a YouTube channel, Facebook page, or TikTok account.
Why use it?
It gives users the correct authorization link and scopes—the specific permissions an app requests—without handling passwords.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it when someone needs to grant an app permission to manage a YouTube channel, Facebook page, or TikTok account.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/tubecreate/tubecli/auth_manager
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 tubecreate/tubecli --skill auth_manager
Clone the repo
git clone --depth 1 https://github.com/tubecreate/tubecli

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 auth_manager

README.md
[![agentmods](https://agentmods.dev/badge/skills/tubecreate/tubecli/auth_manager/github.svg)](https://agentmods.dev/skills/tubecreate/tubecli/auth_manager)
Your own site
<a href="https://agentmods.dev/skills/tubecreate/tubecli/auth_manager"><img src="https://agentmods.dev/badge/skills/tubecreate/tubecli/auth_manager/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 auth_manager

Your own site · 80×15
<a href="https://agentmods.dev/skills/tubecreate/tubecli/auth_manager"><img src="https://agentmods.dev/badge/skills/tubecreate/tubecli/auth_manager.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 15 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 522 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 $0.00015 $0.00522
Opus 5 $0.00008 $0.00261
Sonnet 5 $0.00003 $0.00104
Haiku 4.5 $0.00002 $0.00052

Measured 9d ago against content hash 77f1c47f6bf2, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

auth_manager 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.

The scan reads SKILL.md. This mod also ships 5 executable files (__init__.py, commands.py, extension.py, …), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

tubecli/extensions/auth_manager/SKILL.md · 51 lines

How it starts

The opening of the file, as written. The whole thing — 51 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Auth Manager Extension

This skill is responsible for generating the authorization URL (Google, Facebook, TikTok) that the user can click to grant app permissions, e.g. managing video uploads to YouTube, Fanpage, TikTok.

When to use

  • The user asks to "send me the authorization link"
  • The user wants to "grant permission to manage a new youtube channel"
  • The user asks to "grant facebook/tiktok permission", "grant app permission"

How to trigger (AI OUTPUT JSON)

If the user asks for an authorization link, analyze the platform (provider) and return the following JSON:

{
  "action": "generate_auth_link",
  "provider": "google",
  "scopes": ["youtube", "youtube_upload"]
}

Supported provider values: google, facebook, tiktok. If you don't know the scopes, you can leave it empty [], and the system will automatically use the most common default scope.

Note: After the bot responds with JSON, the system will return a link for the user to click and grant permission.

Google Sheets shared through a group (gsheet_*)

When the agent sits inside a Flow Builder group that contains a Sheet node, the group prompt block lists that sheet by alias and the exact JSON syntax. Five actions are handled here (auth_manager owns the Google token):

action needs access purpose
gsheet_read read rows of a tab / range (max_rows, tail)
gsheet_tabs read list tabs
gsheet_append append add rows after the last filled row
gsheet_update write overwrite an explicit range
gsheet_create_tab manage add a tab

Rules: refer to the sheet by its alias ("sheet": "<alias>") — never by id or credential; a sheet that is not in the agent's group(s) does not exist and the action is refused. Without any group sheet the answer is "No Google Sheet is shared with this agent". The HTTP side used by the cloud Sheet node: GET /gsheets/inspect, GET /gsheets/{id}/values, POST /gsheets/{id}/append under /api/v1/auth-manager.

Read the full file on GitHub · 51 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 · 51 lines · 15 tokens per session scan A 77f1c47f6bf2

Subscribe to this mod's changes

auth_manager is a skill published in the GitHub repository tubecreate/tubecli (167 stars, last pushed yesterday), licensed MIT. It adds 15 tokens to every session and 522 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.