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 arcadeai-labs/omnimcp --skill managing-arcade-appsgit clone --depth 1 https://github.com/arcadeai-labs/omnimcpWrote 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/arcadeai-labs/omnimcp/managing-arcade-apps)<a href="https://agentmods.dev/skills/arcadeai-labs/omnimcp/managing-arcade-apps"><img src="https://agentmods.dev/badge/skills/arcadeai-labs/omnimcp/managing-arcade-apps/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.
<a href="https://agentmods.dev/skills/arcadeai-labs/omnimcp/managing-arcade-apps"><img src="https://agentmods.dev/badge/skills/arcadeai-labs/omnimcp/managing-arcade-apps.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00108 | $0.00830 |
| Opus 5 | $0.00054 | $0.00415 |
| Sonnet 5 | $0.00022 | $0.00166 |
| Haiku 4.5 | $0.00011 | $0.00083 |
Grade A, and why
managing-arcade-apps 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 10d 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 — 81 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Managing connected apps
Arcade_Apps lives on the arcade MCP server.
Quick start
Arcade_Apps(action: "list") # all apps + connected state + account
Arcade_Apps(action: "disconnect", app_id: "...") # remove one app (confirm first)
Use apps language: app, connected, not connected, permissions, sign in, disconnect. Avoid authorization, OAuth, scopes, provider, token.
List
Call Arcade_Apps(action: "list") and show each app, whether it's connected,
and the account it's connected as. Connected apps first. Don't show internal
ids or raw permission strings.
Example
Arcade_Apps(action: "list")
→ {apps: [{app_id: "google", name: "Google", connected: true, account: "[email protected]"},
{app_id: "slack", name: "Slack", connected: false}, ...]}
Reply:
Connected: Google ([email protected]), GitHub (spartee)
Not connected: Slack, Notion, Dropbox, …
Disconnect
Call Arcade_Apps(action: "disconnect", app_id: "<id from list>"). Confirm
with the user first — disconnecting removes Arcade's access to that app.
Report the outcome plainly.
Signing in to an app
The first time a task needs an app the user hasn't connected, a tool returns a
one-time sign-in link. The response may say success: true — an
authorization_url in the output still means sign-in required, not a completed
task.
- Present the link: "Sign in to connect your here, then tell me to continue."
- Stop and wait for the user — never poll or retry in a loop.
- After they confirm, retry the original request once.
Fixing an app connection
For wrong account, expired sign-in, missing permissions, or an explicit
"reconnect" request, use Arcade_ManageToolAuthorization (same arcade MCP
server) with a tool_name from the affected app:
Arcade_ManageToolAuthorization(action: "status", tool_name: "...") # check the connection
Arcade_ManageToolAuthorization(action: "switch_account", tool_name: "...",
provider_id: "<from status>") # sign in as a different account
Arcade_ManageToolAuthorization(action: "reauthorize", tool_name: "...",
provider_id: "<from status>") # expired / missing permissions
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.
- 10d ago First seen · 81 lines · 108 tokens per session scan A 3aca49efb3ad
managing-arcade-apps is a skill published in the GitHub repository arcadeai-labs/omnimcp (5 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 108 tokens to every session and 830 once invoked, about $0.0005 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.
Other skills, from other repositories
artifact-deploy
One-click deploy a user's pre-built app/artifact into their OWN AWS account and get a global public HTTPS link (Vercel-like), with a default TTL and promote-to-persistent. Use when the user says "deploy this", "ship this demo", "give me a public link", "share this externally", or "deploy to AWS".
explain-for
Explain a topic, a piece of code, an error, or a design decision calibrated to one named audience — a 5-year-old, a 5th grader, a manager, a designer, a graduate student, a parent. Resolves who the explanation is for (from the request, or from what memory already records about that person), establishes the ground…
learn-from-sage
Detection-gap (miss) analysis for Code Review Sage. Learn from shipped fixes, acted-on human comments, and design outcomes to close reviewer blind spots. Inline during review stages a candidate; a human triggers a one-shot AI consolidation into the live ruleset.
papyrus-latex-suggestions
Propose actual inline replacement text (old → new) as accept/reject suggestions — LaTeX "suggesting mode" / track changes — that render directly in the PDF. Use when the author wants concrete edit proposals they can see and accept or reject. For remarks ABOUT the text (notes, not replacements), use…
mochi-remind
Handle due reminders — notify the user with natural language and mark them done.
agent-initialization
Initialize an Agent's settings from a user requirement by writing AGENTS.md, setting identity metadata, and installing only needed Skills.