invompt-local-beta-onboarding

invompt-local-beta-onboarding is a skill for Claude Code, Codex from Invompt/invompt-mcp. It costs 66 tokens per session (1,257 once invoked), scanned A, original, MIT.

A setup guide for connecting the local-beta Invompt service to Claude Code or Codex. Invompt is a service used through an MCP connection, and the guide explains whether to use Guest access or OAuth sign-in.

In plain words
What is it for?
It is for checking connection status, choosing an access method, configuring the local service, and confirming the connection before using Invompt tools.
Why use it?
It prevents billing-document tools from being used before the connection is configured and avoids changing the wrong Invompt connection. It also handles the different setup rules for local coding tools and ChatGPT web.

Skill for Claude CodeCodex

Written for Claude Code and Codex: shipped in a Claude Code plugin, but also agents/openai.yaml present. Also seen: mentions Claude Code; installed under .agents/ (shared by several agents); mentions Codex.

Part of the invompt-local-beta plugin — 2 skills, 1 command, 1 agent shipped together

Good fit It is for checking connection status, choosing an access method, configuring the local service, and confirming the connection before using Invompt tools.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/invompt/invompt-mcp/invompt-local-beta-onboarding
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 Invompt/invompt-mcp --skill invompt-local-beta-onboarding
Clone the repo
git clone --depth 1 https://github.com/Invompt/invompt-mcp

Made for: Claude Code, Codex.

Or install invompt-local-beta, the plugin that ships this one along with the rest of its 2 skills, 1 command, 1 agent.

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 invompt-local-beta-onboarding

README.md
[![agentmods](https://agentmods.dev/badge/skills/invompt/invompt-mcp/invompt-local-beta-onboarding/github.svg)](https://agentmods.dev/skills/invompt/invompt-mcp/invompt-local-beta-onboarding)
Your own site
<a href="https://agentmods.dev/skills/invompt/invompt-mcp/invompt-local-beta-onboarding"><img src="https://agentmods.dev/badge/skills/invompt/invompt-mcp/invompt-local-beta-onboarding/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 invompt-local-beta-onboarding

Your own site · 80×15
<a href="https://agentmods.dev/skills/invompt/invompt-mcp/invompt-local-beta-onboarding"><img src="https://agentmods.dev/badge/skills/invompt/invompt-mcp/invompt-local-beta-onboarding.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 66 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,257 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.
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 $0.00066 $0.01257
Opus 5 $0.00033 $0.00629
Sonnet 5 $0.00013 $0.00251
Haiku 4.5 $0.00007 $0.00126

Measured 3d ago against content hash 982f13afe2bd, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

invompt-local-beta-onboarding 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 3d 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.

packages/invompt-mcp/.agents/skills/invompt-local-beta-onboarding/SKILL.md · 95 lines

How it starts

The opening of the file, as written. The whole thing — 95 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Invompt Onboarding

Run this workflow before calling an Invompt MCP tool for the first time in a conversation. Keep the user in control: do not configure a host, issue a Guest credential, log in, or reset state until the user has explicitly chosen a mode.

1. Identify the host

  • In Claude Code or Codex, this is a local-beta macOS workflow.
  • In ChatGPT web, use remote OAuth only. Do not run local status, inspect device state, read local paths, request a Guest credential, or use a local bridge. Tell the user that ChatGPT connects to https://mcp.invompt.com/mcp through its remote OAuth flow.
  • Gemini CLI and Qwen Code package files are templates only and are not supported runtimes.

2. Check redacted state first (local hosts only)

Use the command for the current host. status --json reports only mode, Guest status/backend, and host bindings; it does not print the credential.

This local-beta flow owns only the host server invompt-local-beta. Never remove, log out, or reconfigure the separate global invompt provider; it remains hosted OAuth-only.

Treat a current host binding as usable only when its status is active, binding.mode === selectedMode, and binding.epoch === state.epoch. Do not treat active status alone as usable. If state is undecided or the binding needs reconciliation, continue below.

3. Ask exactly one mode question when undecided

Ask exactly this one choice question in the user's current conversation language, adapting only the language, not the choices or meaning:

Would you like Guest (a server-issued pseudonymous local credential stored in macOS Keychain) or OAuth (sign in through Invompt in your browser)?

Briefly explain that Guest uses a local stdio bridge and OAuth uses the hosted HTTPS MCP endpoint. Then wait for an explicit Guest or OAuth choice. Do not infer a choice from an invoice request, previous account details, or an existing dormant Guest credential.

Read the full file on GitHub · 95 lines

Files

What ships with it

1 file 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.

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. 3d ago Changed 982f13afe2bd
  2. 4d ago Changed 8633d445a9ab
  3. 7d ago Changed 9cfac2cd7fdf
  4. 11d ago First seen · 95 lines · 66 tokens per session scan A f1056085b010

Subscribe to this mod's changes

invompt-local-beta-onboarding is a skill published in the GitHub repository Invompt/invompt-mcp (0 stars, last pushed yesterday), licensed MIT. It adds 66 tokens to every session and 1,257 once invoked, about $0.0003 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 2026-08-31.

Related

Other skills, from other repositories

earn-hunter

A monitoring skill for OKX Earn products, which let users put supported cryptocurrency assets into flexible, fixed-term, or short-term earning programmes.

okx/agent-trade-kit · 114 tokens

okx-cex-bot

A tool for managing Grid and DCA Martingale trading bots on OKX. Grid bots place trades across a price range, while DCA Martingale bots adjust investments as prices move; the bots run on OKX's servers.

okx/agent-trade-kit · 112 tokens

okx-cex-portfolio

This skill should be used when the user asks about 'account balance', 'how much USDT do I have', 'my funding account', 'show my positions', 'open positions', 'position P&L', 'unrealized PnL', 'closed positions', 'position history', 'realized PnL', 'account bills', 'transaction history', 'trading fees', 'fee tier'…

okx/agent-trade-kit · 236 tokens

okx-cex-trade

Use when the user asks to 'buy BTC', 'sell ETH', 'place a limit order', 'place a market order', 'cancel my order', 'amend my order', 'long BTC perp', 'short ETH swap', 'open a position', 'close a position', 'set take profit', 'limit take profit', 'immediate TP', 'set stop loss', 'self-trade prevention', 'stpMode'…

okx/agent-trade-kit · 278 tokens

okx-sentiment-tracker

Use this skill when the user asks about: 'any crypto news', 'latest news', 'market update', 'daily briefing', 'BTC news', 'ETH news', 'news on SOL', 'search SEC ETF', 'regulation news', 'Bitcoin halving', 'is BTC bullish or bearish', 'coin sentiment', 'sentiment trend', 'trending coins', 'top bullish coins', 'bearish…

okx/agent-trade-kit · 252 tokens

okx-cex-earn

A tool for managing several earning products on OKX, including savings, lending, staking, DeFi, Dual Investment, and AutoEarn. These products can use deposited cryptocurrency to generate returns, with terms that vary by product.

okx/agent-trade-kit · 274 tokens