Borrowing it
Nothing to install: this file belongs to RhombusSystems/rhombus-node-mcp. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/RhombusSystems/rhombus-node-mcp/main/AGENTS.mdgit clone --depth 1 https://github.com/RhombusSystems/rhombus-node-mcpWrote 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/instructions/rhombussystems/rhombus-node-mcp/agents-md)<a href="https://agentmods.dev/instructions/rhombussystems/rhombus-node-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/rhombussystems/rhombus-node-mcp/agents-md/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/instructions/rhombussystems/rhombus-node-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/rhombussystems/rhombus-node-mcp/agents-md.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 | $0.00766 | $0.00766 |
| Opus 5.5 | $0.00306 | $0.00306 |
| Sonnet 5.5 | $0.00153 | $0.00153 |
| Haiku 4.5 | $0.00077 | $0.00077 |
Grade A, and why
rhombus-node-mcp AGENTS.md 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 1mo 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 — 32 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md — Rhombus MCP Server
Guidance for AI coding agents working in this repository or connecting to the Rhombus MCP server.
What this is
The official Model Context Protocol (MCP) server for the Rhombus physical-security platform. It exposes Rhombus API capabilities (entity lookup, org information, users, time utilities) as MCP tools for assistants like Claude. Machine-readable server card: https://www.rhombus.com/.well-known/mcp/server-card.json.
Connecting as an agent
- Install: npm package
rhombus-node-mcp(binarymcp-server-rhombus), Docker imagerhombussystems/mcp-server-rhombus, or via Smithery. - Auth: set
RHOMBUS_API_KEY(create one at https://console.rhombus.com/settings/api-management). The key inherits the creating user's permissions. - Transports: stdio by default;
TRANSPORT_TYPE=streamable-httpserves HTTP. - The underlying API: base URL
https://api2.rhombussystems.com/api, POST + JSON everywhere; OpenAPI spec at https://api2.rhombussystems.com/api/openapi/public.json; agent auth guide at https://www.rhombus.com/auth.md.
Working on this repository
- Build:
npm run build(TypeScript →dist/). Node project; install deps withnpm install. - Run locally:
npm run start:stdioornpm run start:http. - Test:
npm test(vitest). - Tools live in
src/tools/— one file per tool, registered viasrc/tools/getTools.ts. Follow the existing pattern (zod input schemas;npm run generate-schemasregenerates derived schemas). - Tool descriptions are routing surfaces for guided workflows. The Rhombus chatbot pairs this server's tools with playbook-driven workflows (defined in the sibling
rhombus-node-private-mcprepo); a keyword-matched instruction in a tool description here can silently outcompete a workflow that covers the same request, and playbooks name this server's tools directly. Before editing a description's "when to use" language or renaming a tool, read../docs/writing-workflows.md(in therhombus-mind-rootsuperproject, when checked out side-by-side). - Docker:
npm run docker:build. - Telemetry (optional): each tool invocation emits an
mcp.tool.callOpenTelemetry span (mcp.tool.name, success, duration, arg keys — never arg values). Uses only@opentelemetry/api; spans export when a host process registers an SDK (Rhombus EB deploy loadsotel-init.mjs). Wiring:src/telemetry/tracingProxy.ts; identity from cachedgetCurrentUserinsrc/api/get-accessible-apps.ts.
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.
- 1mo ago Changed · -1 tokens per session 7a7863aecf3f
- 2mo ago First seen · 32 lines · 767 tokens per session scan A f580dbdb9983
rhombus-node-mcp AGENTS.md is an instructions file published in the GitHub repository RhombusSystems/rhombus-node-mcp (0 stars, last pushed 20d ago), licensed MIT. It adds 766 tokens to every session, about $0.0031 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 2026-08-31.
rhombus-node-mcp AGENTS.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| rhombus-node-mcp AGENTS.mdRhombusSystems/rhombus-node-mcp | Instructions file | 0 | 20d ago | MIT | A | 766 | Codex, OpenCode |
| vscode buildNext.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 9,719 | GitHub Copilot |
| next.js AGENTS.mdvercel/next.js | Instructions file | 143k | yesterday | MIT | A | 7,461 | Codex, OpenCode |
| langchain AGENTS.mdlangchain-ai/langchain | Instructions file | 149k | yesterday | MIT | A | 4,680 | Codex, OpenCode |
| vscode oss-third-party-notices.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 5,516 | GitHub Copilot |
| vscode copilot-instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 3,093 | GitHub Copilot |
| deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness | Instructions file | 274k | 2d ago | MIT | A | 4,313 | Codex, OpenCode |