arcade-operator

arcade-operator is an agent for Claude Code from arcadeai-labs/omnimcp. It costs 73 tokens per session (720 once invoked), scanned A, original, Apache-2.0.

An operator for carrying out requests in external services such as email, calendars, chat, project trackers, and code-hosting sites. It finds the appropriate connected tool and uses it to complete the requested action.

In plain words
What is it for?
Use it for tasks such as sending messages, handling email, managing calendar events, working with GitHub, or updating records in connected services.
Why use it?
It keeps the details of finding and calling service tools out of the main conversation. It also reports plainly when a service is unavailable, needs sign-in, or returns no result.

Agent for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the arcade plugin — 2 skills, 3 commands, 1 agent, 1 hook, 1 MCP server shipped together

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.

agentmods
npx agentmods add agents/arcadeai-labs/omnimcp/arcade-operator
Clone the repo
git clone --depth 1 https://github.com/arcadeai-labs/omnimcp

Made for: Claude Code.

Or install arcade, the plugin that ships this one along with the rest of its 2 skills, 3 commands, 1 agent, 1 hook, 1 MCP server.

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 arcade-operator

README.md
[![agentmods](https://agentmods.dev/badge/agents/arcadeai-labs/omnimcp/arcade-operator.svg)](https://agentmods.dev/agents/arcadeai-labs/omnimcp/arcade-operator)
Your own site
<a href="https://agentmods.dev/agents/arcadeai-labs/omnimcp/arcade-operator"><img src="https://agentmods.dev/badge/agents/arcadeai-labs/omnimcp/arcade-operator.svg" alt="Measured on agentmods" height="20"></a>
Per session 73 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 720 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00073 $0.00720
Opus 5 $0.00036 $0.00360
Sonnet 5 $0.00015 $0.00144
Haiku 4.5 $0.00007 $0.00072

Measured 5d ago against content hash 55d8d35de9dd, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

arcade-operator 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 5d 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.

components/agents/arcade-operator.md · 59 lines

How it starts

The opening of the file, as written. The whole thing — 59 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are the Arcade operator. Turn a plain-language task into a completed action using the Arcade tools, then return a concise result. The main agent delegated to you specifically so the discovery details stay in your context, not theirs.

The Arcade MCP tools (Arcade_SelectTools, Arcade_UseTool) are available to you — actually call them. Never write a tool call as text, and never fabricate or guess results. If the tools are not available, or a call errors or returns no data, say so plainly and stop — do not invent placeholder data.

Loop

  1. Discover — Call Arcade_SelectTools with a single tasks entry that describes the whole workflow in plain language. Add a second entry only for a genuinely unrelated task. The response includes each tool's input_schema inline, so you can call immediately.
  2. Execute — Call Arcade_UseTool with:
    • tool_name: exactly as returned (Toolkit_Action form — never add an @version suffix, never replace the underscore with a period).
    • inputs: values matching the tool's input_schema.
    • query_id: the query_id from the Arcade_SelectTools response.
  3. Sign in — If a call returns a sign-in link (the app isn't connected yet), STOP. The response may say success: true — an authorization_url in the output still means sign-in required, not a completed task. Return the link with a one-line instruction ("Sign in to connect your app here, then ask me to retry"). Never poll or retry in a loop.
  4. Clarify — If a genuinely required input is missing (which channel? which repo? which recipient?), return one specific question. Do not guess destructive values.
  5. Errors — On success: false from an input problem, fix inputs against the input_schema and retry once; otherwise report the tool's error message verbatim and stop.

Domain care

  • Email — Before sending or replying, confirm the recipient and subject are known; for "summarize my inbox" tasks, fetch and summarize — never send anything.
  • Calendar — Resolve relative dates ("tomorrow", "next Tuesday") against the user's current date before calling tools; state times with their timezone. Before creating or canceling an event, confirm the title, time, and attendees are known.

Read the full file on GitHub · 59 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. 5d ago First seen · 59 lines · 73 tokens per session scan A 55d8d35de9dd

Subscribe to this mod's changes

arcade-operator is an agent published in the GitHub repository arcadeai-labs/omnimcp (5 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 73 tokens to every session and 720 once invoked, about $0.0004 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 agents, from other repositories

session-agent-builder

Analyze the current interactive work session and compile its reusable working method into an owner-reviewed Agentlas agent or team without carrying private conversation data forward.

agentlas-ai/Agentlas-OS · 32 tokens

explore

Codebase explorer — answers "where is X?" / "find the code that does Y" / "list all callers of Z". Read-only grep + glob + read, no memory injection.

Timeflys2018/zeyi · 42 tokens

alfred-pennyworth

The steward and right-hand — keeps your operation running and ready. Use for setting up and maintaining the working environment, standing chores and logistics, readiness and upkeep, prep before a task, and cleanup and restore after one. The one who quietly has things in order and ready before you reach for them.…

takoyaro/the-agency · 76 tokens

agentlas-core-engine-meta-agent

Use this agent when the user asks for /meta-agent, a single agent builder, multi-agent team builder, or packaging existing agents into Agentlas architecture.

agentlas-ai/Agentlas-OS · 38 tokens

relay-reviewer

A code review agent that checks for bugs, regressions, and testing gaps then reports via Agent Relay. Use when you need a second pair of eyes on changes.

AgentWorkforce/relay · 37 tokens

rn-code-architect

Designs implementation blueprints for React Native features by analyzing existing codebase patterns, then providing specific files to create/modify, component designs, testID placement, store slice design, and build sequences. Triggers: "design the architecture", "plan the implementation", "create a blueprint", "what…

Lykhoyda/rn-dev-agent · 238 tokens