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.
git 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/rules/arcadeai-labs/omnimcp/arcade)<a href="https://agentmods.dev/rules/arcadeai-labs/omnimcp/arcade"><img src="https://agentmods.dev/badge/rules/arcadeai-labs/omnimcp/arcade/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/rules/arcadeai-labs/omnimcp/arcade"><img src="https://agentmods.dev/badge/rules/arcadeai-labs/omnimcp/arcade.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 | $0.00340 | $0.00340 |
| Opus 5.5 | $0.00136 | $0.00136 |
| Sonnet 5.5 | $0.00068 | $0.00068 |
| Haiku 4.5 | $0.00034 | $0.00034 |
Grade A, and why
arcade 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 yesterday.
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.
What it actually says
Gateway: Arcade is connected as the "arcade" MCP server at api.arcade.dev. It may appear as plugin-arcade-arcade. That is the same gateway. Prefer arcade. Authentication: A gateway showing needsAuth or a plugin namespace with zero tools needs authentication in this host's MCP settings. A missing, unavailable, or failing gateway needs setup or connection repair. If blocked: For authentication, stop and ask the user to authenticate; do not poll. For permission denial, stop and ask the user to resolve it. Do not bypass either by switching gateways or tools. For other failures, report the error, advise checking plugin and MCP settings for setup or connection failures, then apply fallback. Fallback: If the arcade server cannot finish, the parent may use another already-authorized Arcade gateway or other available tools within the authorized task. Discover tools on each gateway; never reuse another gateway's query IDs. Do not broaden authorization or copy secrets, credentials, or user sessions. On another gateway, confirm the intended app account with the app's who-am-I tool. Write only through a confirmed account, and name the source account for reads. If you can't, ask the user. Routing: Use try-arcade first for external app tasks (email, calendar, chat, docs, issues, CRM); use scale-arcade for team or org rollout. Delegate bounded app tasks to arcade-operator when available. Privacy: Keep tool discovery and tool names out of the conversation.
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.
- yesterday First seen · 14 lines · 340 tokens per session scan A ee0678b81749
arcade is a cursor rule published in the GitHub repository arcadeai-labs/omnimcp (5 stars, last pushed yesterday), licensed MIT. It adds 340 tokens to every session, about $0.0014 per session on Opus 5.5. 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 2026-10-17.
Other cursor rules, from other repositories
simplify
Structural-quality review of changed code — score against the four-dimension rubric, gate at 10/10, and (in auto-fix mode or with --fix) apply reuse/simplification/efficiency/altitude cleanups. Includes a diff-economy lens; correctness is /validate, full-repo survey is /audit.
create-pr
Create a pull request for the current branch and immediately subscribe to PR activity. Use when the user wants to open a PR, submit changes for review, or push and create a pull request.
statusline
Configure model, context, and usage status display — Codex uses its built-in statusline picker; Claude Code uses bin/install-statusline.sh. Turn the status line on or off without clobbering other settings.
conventional-commits
Always use Conventional Commits for git commit messages.
ponytail
Ponytail, lazy senior dev mode. Always pick the simplest solution that works.
angular-20
This rule provides comprehensive best practices and coding standards for Angular development, focusing on modern TypeScript, standalone components, signals, and performance optimizations.