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 agentmods add agents/arcadeai-labs/omnimcp/arcade-operatorgit 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/agents/arcadeai-labs/omnimcp/arcade-operator)<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>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 | $0.00073 | $0.00720 |
| Opus 5 | $0.00036 | $0.00360 |
| Sonnet 5 | $0.00015 | $0.00144 |
| Haiku 4.5 | $0.00007 | $0.00072 |
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.
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
- Discover — Call
Arcade_SelectToolswith a singletasksentry that describes the whole workflow in plain language. Add a second entry only for a genuinely unrelated task. The response includes each tool'sinput_schemainline, so you can call immediately. - Execute — Call
Arcade_UseToolwith:tool_name: exactly as returned (Toolkit_Actionform — never add an@versionsuffix, never replace the underscore with a period).inputs: values matching the tool'sinput_schema.query_id: thequery_idfrom theArcade_SelectToolsresponse.
- Sign in — If a call returns a sign-in link (the app isn't connected yet),
STOP. The response may say
success: true— anauthorization_urlin 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. - Clarify — If a genuinely required input is missing (which channel? which repo? which recipient?), return one specific question. Do not guess destructive values.
- Errors — On
success: falsefrom an input problem, fixinputsagainst theinput_schemaand 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.
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.
- 5d ago First seen · 59 lines · 73 tokens per session scan A 55d8d35de9dd
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.
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.
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.
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.…
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.
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.
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…